llms.txt@17-Billing-Plans · git:20260802.073248b · 2026-08-02 · sha256 19acb1a1ce760c4c

llms.txt@17-Billing-Plans git:20260802.073248bF

Immutable. This exact content never changes and is served at /api/v1/blob/19acb1a1ce760c4c.

# Billing Plans

All documentation for Billing Plans.

---
## about-claude-pricing-50846cd1ff.md

- [Managed Agents](/docs/en/managed-agents/overview)

- [Admin](/docs/en/manage-claude/admin-api)

- Resources
- [Best practices](/docs/en/about-claude/use-case-guides/overview)
- [Models & pricing](/docs/en/about-claude/models/overview)
- [CLI, SDKs, and libraries](/docs/en/cli-sdks-libraries/overview)
- [Claude API skill](/docs/en/agents-and-tools/agent-skills/claude-api-skill)
- [Release notes](/docs/en/release-notes/overview)

API reference



Console







Models

[Models overview](/docs/en/about-claude/models/overview)[Model IDs and versioning](/docs/en/about-claude/models/model-ids-and-versions)[Choosing a model](/docs/en/about-claude/models/choosing-a-model)[Introducing Claude Fable 5 and Claude Mythos 5](/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5)[What's new in Claude Sonnet 5](/docs/en/about-claude/models/whats-new-sonnet-5)[What's new in Claude Opus 5](/docs/en/about-claude/models/whats-new-opus-5)[Upgrade between model versions](/docs/en/about-claude/models/migration-guide)[Model deprecations](/docs/en/about-claude/model-deprecations)[Model cards](/docs/en/resources/overview)[System prompts](/docs/en/release-notes/system-prompts)[Pricing](/docs/en/about-claude/pricing)

[](/login)



Models & pricing

Pricing

Models & pricing/Models

# Pricing



Learn about Anthropic's pricing structure for models and features



This page provides detailed pricing information for Anthropic's models and features. All prices are in USD.

For the most current pricing information, visit [claude.com/pricing](https://claude.com/pricing).



Model pricing

The following table shows pricing for all Claude models:

[TABLE]



Introductory pricing of \$2/\$10 per million input/output tokens is in effect through August 31, 2026, after which the standard pricing of \$3/\$15 per million input/output tokens will take effect.



MTok = Million tokens. The "Base Input Tokens" column shows standard input pricing, the "5m Cache Writes", "1h Cache Writes", and "Cache Hits & Refreshes" columns are specific to [prompt caching](#prompt-caching), and "Output Tokens" shows output pricing. See [prompt caching pricing](#prompt-caching) for an explanation of the cache columns and pricing multipliers.



Claude 4.7 and later models and Claude Mythos Preview use a newer tokenizer that contributes to their improved performance on a wide range of tasks. This tokenizer produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. Claude Sonnet 4.6 and earlier models use the previous tokenizer.

For Claude Platform on AWS pricing, see [Claude Platform on AWS pricing](#claude-platform-on-aws-pricing).



Cloud platform pricing

This section covers partner-operated cloud platforms, where the cloud provider invoices you. For Anthropic-operated cloud platforms billed through a marketplace, see [Claude Platform on AWS pricing](#claude-platform-on-aws-pricing) and [Claude in Microsoft Foundry pricing](#claude-in-microsoft-foundry-pricing).

Claude models are available on [Amazon Bedrock](/docs/en/build-with-claude/claude-in-amazon-bedrock) and [Google Cloud](/docs/en/build-with-claude/claude-on-vertex-ai). For official pricing, visit:

- [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/)
- [Google Cloud pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models)



**Regional and multi-region endpoint pricing for Claude 4.5 models and beyond**

Starting with Claude Sonnet 4.5, Haiku 4.5, and Opus 4.5:

- **Bedrock** offers two endpoint types: global endpoints (dynamic routing for maximum availability) and regional endpoints (guaranteed data routing through specific geographic regions).
- **Google Cloud** offers three endpoint types: global endpoints, multi-region endpoints (dynamic routing within a geographic area), and regional endpoints.

Regional and multi-region endpoints include a 10% premium over global endpoints. The Claude API (first-party) is global by default; for first-party data residency options and pricing, see [Data residency pricing](#data-residency-pricing).

**Scope:** This pricing structure applies to Claude Sonnet 4.5, Haiku 4.5, Opus 4.5, and all future models. Earlier models (Claude Opus 4.1 (deprecated) and prior releases) retain their existing pricing.

For implementation details and code examples:

- [Amazon Bedrock global vs regional endpoints](/docs/en/build-with-claude/claude-in-amazon-bedrock#regions) for Opus 4.7, Haiku 4.5, and later models, or [the legacy integration](/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#global-vs-regional-endpoints) for all other models on Bedrock
- [Google Cloud global, multi-region, and regional endpoints](/docs/en/build-with-claude/claude-on-vertex-ai#global-multi-region-and-regional-endpoints)



Claude Platform on AWS pricing

[Claude Platform on AWS](/docs/en/build-with-claude/claude-platform-on-aws) bills through AWS Marketplace using Claude Consumption Units (CCUs). Anthropic rates your token usage in USD at standard per-model, per-feature rates, applies any negotiated discount, converts the result to CCUs at \$0.01 per CCU, and reports the CCU quantity to AWS Marketplace hourly. Your AWS bill shows a single CCU line item.

| Concept | Details |
|---------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|
| **Billing unit** | Claude Consumption Unit (CCU) |
| **CCU price** | \$0.01 per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price) |
| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Claude API pricing](#model-pricing)), then converted to CCUs at \$0.01 per CCU |
| **Billing cadence** | Hourly metering to AWS Marketplace; monthly invoices |
| **Payment model** | Arrears only (postpaid); no prepaid credits |
| **Discounts** | Applied as fewer CCUs metered |
| **Tax** | Pre-tax metering; AWS Marketplace handles tax |
| **Cost visibility** | Real-time breakdown in the Claude Console (access through the AWS Console); AWS Cost Explorer shows aggregated CCU |



**Claude Consumption Units.** If Customer accesses the Services through certain Marketplace Platforms (e.g., Claude Platform on AWS), usage will be invoiced in Claude Consumption Units ("CCU") rather than per MTok. A CCU is a unit of measure used solely for Marketplace Platform invoicing. One hundred (100) CCU represents \$1.00 USD of fees owed for the Services, calculated at the applicable prices on [claude.com/pricing#api](https://claude.com/pricing#api), after application of any discounts.



Inference geography

For Claude 4.6 and later models, using `inference_geo: "us"` applies a 1.1x pricing multiplier. `inference_geo: "global"` (default) uses standard pricing. See [Data residency](/docs/en/manage-claude/data-residency) for details.



Private offers

When you sign up on the AWS Console **Claude Platform on AWS** service page, the AWS Console looks up any private offer associated with your account and prompts you to accept it in AWS Marketplace. Contact your Anthropic account representative for private offer terms.



If you have an existing Amazon Bedrock private offer, contact your Anthropic or AWS account representative before getting started with Claude Platform on AWS to ensure your discounts are applied correctly. Discounts cannot be applied retroactively to usage incurred before your private offer is accepted.



Claude in Microsoft Foundry pricing

[Claude in Microsoft Foundry](/docs/en/build-with-claude/claude-in-microsoft-foundry) bills through the Azure Marketplace using Claude Consumption Units (CCUs). Anthropic rates your token usage in USD at standard per-model, per-feature rates, applies any negotiated discount, converts the result to CCUs at \$0.01 per CCU, and reports the CCU quantity to the Azure Marketplace hourly. Your Azure bill shows a single CCU line item.

| Concept | Details |
|---------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|
| **Billing unit** | Claude Consumption Unit (CCU) |
| **CCU price** | \$0.01 per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price) |
| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Claude API pricing](#model-pricing)), then converted to CCUs at \$0.01 per CCU |
| **Billing cadence** | Hourly metering to the Azure Marketplace; monthly invoices |
| **Payment model** | Arrears only (postpaid); no prepaid credits |
| **Discounts** | Applied as fewer CCUs metered |
| **Tax** | Pre-tax metering; Azure Marketplace handles tax |
| **Cost visibility** | Azure Cost Management shows aggregated CCU |



**Claude Consumption Units.** If Customer accesses the Services through certain Marketplace Platforms (e.g., Claude Platform on AWS, Claude in Microsoft Foundry), usage will be invoiced in Claude Consumption Units ("CCU") rather than per MTok. A CCU is a unit of measure used solely for Marketplace Platform invoicing. One hundred (100) CCU represents \$1.00 USD of fees owed for the Services, calculated at the applicable prices on [claude.com/pricing#api](https://claude.com/pricing#api), after application of any discounts.



Inference geography

Deployments hosted on Azure can use the US Data Zone Standard deployment type, which keeps inference within the United States. This is equivalent to `inference_geo: "us"` on the Claude API and applies the same 1.1x pricing multiplier. See [Data residency](/docs/en/manage-claude/data-residency) for details.



Feature-specific pricing



Prompt caching

Prompt caching reduces costs and latency by reusing previously processed portions of your prompt across API calls. Instead of reprocessing the same large system prompt, document, or conversation history on every request, the API reads from cache at a fraction of the standard input price.

There are two ways to enable prompt caching:

- **Automatic caching:** Add a single `cache_control` field at the top level of your request. The system automatically manages cache breakpoints as conversations grow. This is the recommended starting point for most use cases.
- **Explicit cache breakpoints:** Place `cache_control` directly on individual content blocks for fine-grained control over exactly what gets cached.

Prompt caching uses the following pricing multipliers relative to base input token rates:

| Cache operation | Multiplier | Duration |
|----------------------|------------------------|--------------------------------------|
| 5-minute cache write | 1.25x base input price | Cache valid for 5 minutes |
| 1-hour cache write | 2x base input price | Cache valid for 1 hour |
| Cache read (hit) | 0.1x base input price | Same duration as the preceding write |

Cache write tokens are charged when content is first stored. Cache read tokens are charged when a subsequent request retrieves the cached content. A cache hit costs 10% of the standard input price, which means caching pays off after just one cache read for the 5-minute duration (1.25x write), or after two cache reads for the 1-hour duration (2x write).

These multipliers stack with other pricing modifiers, including the Batch API discount and data residency.

For implementation details, supported models, and code examples, see [Prompt caching](/docs/en/build-with-claude/prompt-caching).



Data residency pricing

For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. Global routing (the default) uses standard pricing.

This applies to the Claude API (first-party) and Claude Platform on AWS. On Claude in Microsoft Foundry, the same 1.1x multiplier applies to deployments that use the US Data Zone Standard deployment type (see [Inference geography](#foundry-inference-geography)). Partner-operated platforms (Bedrock and Google Cloud) have independent regional pricing. See [Bedrock](https://aws.amazon.com/bedrock/pricing/) and [Google Cloud](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models) for details. Earlier models do not support the `inference_geo` parameter and always use standard pricing; requests that include the parameter on these models return a 400 error.

For more information, see [Data residency](/docs/en/manage-claude/data-residency).



Fast mode pricing

[Fast mode](/docs/en/build-with-claude/fast-mode), in research preview, provides significantly faster output for Claude Opus 5 and Claude Opus 4.8 at premium pricing. Fast mode pricing applies across the full context window, including requests over 200k input tokens. Fast mode is available on the Claude API (first-party) only; it is not available on Claude Platform on AWS or partner-operated cloud platforms.

| Model | Input | Output |
|---------------------------------|-------------|-------------|
| Claude Opus 5 / Claude Opus 4.8 | \$10 / MTok | \$50 / MTok |

Fast mode is not available on Claude Opus 4.7 (requests with `speed: "fast"` return an error) or Claude Opus 4.6 (requests run at standard speed and are billed at standard rates). See [Fast mode](/docs/en/build-with-claude/fast-mode#supported-models).

Fast mode pricing stacks with other pricing modifiers:

- [Prompt caching multipliers](#prompt-caching) apply on top of fast mode pricing
- [Data residency](/docs/en/manage-claude/data-residency) multipliers apply on top of fast mode pricing

Fast mode is not available with the [Batch API](#batch-processing).

For more information, see [Fast mode](/docs/en/build-with-claude/fast-mode).



Batch processing

The Batch API allows asynchronous processing of large volumes of requests with a 50% discount on both input and output tokens.

[TABLE]

For more information about batch processing, see [Batch processing](/docs/en/build-with-claude/batch-processing).



Long context pricing

Claude 4.6 and later models and [Claude Mythos Preview](https://anthropic.com/glasswing) include the full [1M token context window](/docs/en/build-with-claude/context-windows) at standard pricing. (A 900k-token request is billed at the same per-token rate as a 9k-token request.) Prompt caching and batch processing discounts apply at standard rates across the full context window.



Tool use pricing

Tool use requests are priced based on:

1. The total number of input tokens sent to the model (including in the `tools` parameter)
2. The number of output tokens generated
3. For server-side tools, additional usage-based pricing (e.g., web search charges per search performed)

Client-side tools are priced the same as any other Claude API request, while server-side tools may incur additional charges based on their specific usage.

The additional tokens from tool use come from:

- The `tools` parameter in API requests (tool names, descriptions, and schemas)
- `tool_use` content blocks in API requests and responses
- `tool_result` content blocks in API requests

When you use `tools`, the API also automatically includes a special system prompt for the model which enables tool use. The number of tool use tokens required for each model are listed below (excluding the additional tokens listed above). Note that the table assumes at least 1 tool is provided. If no `tools` are provided, then a tool choice of `none` uses 0 additional system prompt tokens.

[TABLE]

These token counts are added to your normal input and output tokens to calculate the total cost of a request.

For current per-model prices, refer to the [model pricing](#model-pricing) section.

For more information about tool use implementation and best practices, see [Tool use](/docs/en/agents-and-tools/tool-use/overview).



Specific tool pricing



Bash tool

The bash tool definition adds the following input tokens to your request. This is in addition to the per-model [tool use system prompt](/docs/en/agents-and-tools/tool-use/overview#pricing) that applies whenever any tool is present.

| Model | Additional input tokens |
|-----------------------------------------------------|-------------------------|
| Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7 | 325 tokens |
| Claude Opus 4.6, Claude Sonnet 4.6, and earlier | 244 tokens |

Additional tokens are consumed by:

- Command outputs (stdout/stderr)
- Error messages
- Large file contents

See [tool use pricing](#tool-use-pricing) for complete pricing details.



Code execution tool

**Code execution is free when used with web search or web fetch.** When `web_search_20260209` (or later) or `web_fetch_20260209` (or later) is included in your API request, there are no additional charges for code execution tool calls beyond the standard input and output token costs.

When used without these tools, code execution is billed by execution time, tracked separately from token usage:

- Execution time has a minimum of 5 minutes
- Each organization receives **1,550 free hours** of usage per month
- Additional usage beyond 1,550 hours is billed at **\$0.05 USD per hour, per container**
- If files are included in the request, execution time is billed even if the tool is not called, because files are preloaded onto the container

Code execution usage is tracked in the response:

```python
{
"usage": {
"input_tokens": 105,
"output_tokens": 239,
"server_tool_use": {
"code_execution_requests": 1
}
}
}
```





Text editor tool

The text editor tool uses the same pricing structure as other tools used with Claude. It follows the standard input and output token pricing based on the Claude model you're using.

In addition to the base tokens, the following additional input tokens are needed for the text editor tool:

| Tool | Additional input tokens |
|-------------------------------------|-------------------------|
| `text_editor_20250429` (Claude 4.x) | 700 tokens |

See [tool use pricing](#tool-use-pricing) for complete pricing details.



Web search tool

Web search usage is charged in addition to token usage:

```python
{
"usage": {
"input_tokens": 105,
"output_tokens": 6039,
"cache_read_input_tokens": 7123,
"cache_creation_input_tokens": 7345,
"server_tool_use": {
"web_search_requests": 1
}
}
}
```



Web search is available on the Claude API for **\$10 per 1,000 searches**, plus standard token costs for search-generated content. Web search results retrieved throughout a conversation are counted as input tokens, in search iterations executed during a single turn and in subsequent conversation turns.

Each web search counts as one use, regardless of the number of results returned. If an error occurs during web search, the web search will not be billed.



Web fetch tool

Web fetch usage has **no additional charges** beyond standard token costs:

```python
{
"usage": {
"input_tokens": 25039,
"output_tokens": 931,
"cache_read_input_tokens": 0,
"cache_creation_input_tokens": 0,
"server_tool_use": {
"web_fetch_requests": 1
}
}
}
```



The web fetch tool is available on the Claude API at **no additional cost**. You only pay standard token costs for the fetched content that becomes part of your conversation context.

To protect against inadvertently fetching large content that would consume excessive tokens, use the `max_content_tokens` parameter to set appropriate limits based on your use case and budget considerations.

Example token usage for typical content:

- Average web page (10 kB): ~2,500 tokens
- Large documentation page (100 kB): ~25,000 tokens
- Research paper PDF (500 kB): ~125,000 tokens



Computer use tool

Computer use follows the standard [tool use pricing](/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:

**System prompt overhead:** The computer use beta adds 466–499 tokens to the system prompt

**Computer use tool token usage:**

| Model | Input tokens per tool definition |
|-------------------|----------------------------------|
| Claude 4.x models | 735 tokens |

**Additional token consumption:**

- Screenshot images (see [Vision pricing](/docs/en/build-with-claude/vision))
- Tool execution results returned to Claude



If you're also using bash or text editor tools alongside computer use, those tools have their own token costs as documented in their respective pages.



Claude Managed Agents pricing

[Claude Managed Agents](/docs/en/managed-agents/overview) is billed on two dimensions: tokens and session runtime.



Tokens

All tokens consumed by a Claude Managed Agents session are billed at the rates shown in [Model pricing](#model-pricing). [Prompt caching](#prompt-caching) multipliers apply identically. Web search triggered inside a session incurs the standard \$10 per 1,000 searches. On [Claude Platform on AWS](#claude-platform-on-aws-pricing), session token and runtime charges convert to Claude Consumption Units at the standard rate.

The following Messages API modifiers do **not** apply to Claude Managed Agents sessions:

| Modifier | Why it doesn't apply |
|------------------------------------------------------|----------------------------------------------------------------|
| [Batch API discount](#batch-processing) | Sessions are stateful and interactive. There is no batch mode. |
| [Fast mode premium](#fast-mode-pricing) | Inference speed is managed by the runtime. |
| [Data residency multiplier](#data-residency-pricing) | `inference_geo` is a Messages API request field. |
| [Cloud platform pricing](#cloud-platform-pricing) | Not available on partner-operated cloud platforms. |



Session runtime

| SKU | Rate | Metering |
|-----------------|-------------------------|---------------------------|
| Session runtime | \$0.08 per session-hour | `running` status duration |

Runtime is measured to the millisecond and accrues only while the session's status is `running`. Time spent `idle` (waiting for your next message or a tool confirmation), `rescheduling`, or `terminated` does not count toward runtime.



Session runtime replaces the [Code Execution](#code-execution-tool) container-hour billing model when using Claude Managed Agents. You are not separately billed for container hours on top of session runtime.



Worked example

A one-hour coding session using Claude Opus 5 that consumes 50,000 input tokens and 15,000 output tokens:

| Line item | Calculation | Cost |
|-----------------|---------------------------|-------------|
| Input tokens | 50,000 × \$5 / 1,000,000 | \$0.25 |
| Output tokens | 15,000 × \$25 / 1,000,000 | \$0.375 |
| Session runtime | 1.0 hour × \$0.08 | \$0.08 |
| **Total** | | **\$0.705** |

If prompt caching is active and 40,000 of the input tokens are cache reads:

| Line item | Calculation | Cost |
|-----------------------|--------------------------------|-------------|
| Uncached input tokens | 10,000 × \$5 / 1,000,000 | \$0.05 |
| Cache read tokens | 40,000 × \$5 × 0.1 / 1,000,000 | \$0.02 |
| Output tokens | 15,000 × \$25 / 1,000,000 | \$0.375 |
| Session runtime | 1.0 hour × \$0.08 | \$0.08 |
| **Total** | | **\$0.525** |



Example calculation for processing 10,000 support tickets:

- Average ~3,700 tokens per conversation
- Using Claude Haiku 4.5 at \$1/MTok input, \$5/MTok output
- Total cost: ~\$37.00 per 10,000 tickets

For a detailed walkthrough of this calculation, see the [customer support agent guide](/docs/en/about-claude/use-case-guides/customer-support-chat).



Additional pricing considerations



Cost optimization strategies

When building agents with Claude:

1. **Use appropriate models:** Choose Haiku for simple tasks, Sonnet for most production workloads, and Opus for the most complex reasoning
2. **Implement prompt caching:** Reduce costs for repeated context
3. **Batch operations:** Use the Batch API for non-time-sensitive tasks
4. **Monitor usage patterns:** Track token consumption to identify optimization opportunities



For high-volume agent applications, contact the [enterprise sales team](https://claude.com/contact-sales) for custom pricing arrangements.



Rate limits

Rate limits vary by usage tier and affect how many requests you can make:

- **Start tier:** Entry-level limits for getting started
- **Build tier:** Increased limits for growing applications
- **Scale tier:** Highest standard limits for production workloads

For detailed rate limit information, see [Rate limits](/docs/en/api/rate-limits).

For limits beyond the Scale tier or custom pricing arrangements, [contact the sales team](https://claude.com/contact-sales).



Volume discounts

Volume discounts may be available for high-volume users. These are negotiated on a case-by-case basis.

- Standard usage tiers use the pricing shown in [Model pricing](#model-pricing)
- Enterprise customers can [contact sales](mailto:sales@anthropic.com) for custom pricing
- Academic and research discounts may be available



Enterprise pricing

For enterprise customers with specific needs:

- Custom rate limits
- Volume discounts
- Dedicated support
- Custom terms

Contact the sales team at [sales@anthropic.com](mailto:sales@anthropic.com) or through the [Claude Console](/settings/limits) to discuss enterprise pricing options.



Billing and payment

- Billing is based on actual monthly usage
- All payments are in USD
- Credit card and invoicing options available
- Usage tracking available in the [Claude Console](/)



Frequently asked questions

**How is token usage calculated?**

Tokens are pieces of text that models process. As a rough estimate, 1 token is approximately 4 characters or 0.75 words in English. The exact count varies by language and content type.

**Are there free tiers or trials?**

New users receive a small amount of free credits to test the API. [Contact sales](mailto:sales@anthropic.com) for information about extended trials for enterprise evaluation.

**How do discounts stack?**

Batch API and prompt caching discounts can be combined. For example, using both features together provides significant cost savings compared to standard API calls. See [prompt caching pricing](#prompt-caching) for how the multipliers interact.

**What payment methods are accepted?**

Major credit cards are accepted for standard accounts. Enterprise customers can arrange invoicing and other payment methods.

For additional questions about pricing, contact [support@anthropic.com](mailto:support@anthropic.com).

---
## about-claude-pricing-820bbf24dd.md

# Pricing

Learn about Anthropic's pricing structure for models and features

---

This page provides detailed pricing information for Anthropic's models and features. All prices are in USD.

For the most current pricing information, please visit [claude.com/pricing](https://claude.com/pricing).

## Model pricing

The following table shows pricing for all Claude models across different usage tiers:

| Model | Base Input Tokens | 5m Cache Writes | 1h Cache Writes | Cache Hits & Refreshes | Output Tokens |
|-------------------|-------------------|-----------------|-----------------|----------------------|---------------|
| Claude Opus 4.7 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |
| Claude Opus 4.6 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |
| Claude Opus 4.5 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |
| Claude Opus 4.1 | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok |
| Claude Opus 4 | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok |
| Claude Sonnet 4.6 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |
| Claude Sonnet 4.5 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |
| Claude Sonnet 4 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |
| Claude Haiku 4.5 | $1 / MTok | $1.25 / MTok | $2 / MTok | $0.10 / MTok | $5 / MTok |
| Claude Haiku 3.5 | $0.80 / MTok | $1 / MTok | $1.6 / MTok | $0.08 / MTok | $4 / MTok |
| Claude Opus 3 ([deprecated](/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok |
| Claude Haiku 3 | $0.25 / MTok | $0.30 / MTok | $0.50 / MTok | $0.03 / MTok | $1.25 / MTok |

<Note>
MTok = Million tokens. The "Base Input Tokens" column shows standard input pricing, "Cache Writes" and "Cache Hits" are specific to [prompt caching](#prompt-caching), and "Output Tokens" shows output pricing. See [prompt caching pricing](#prompt-caching) below for an explanation of the cache columns and pricing multipliers.
</Note>

<Note>
Opus 4.7 uses a new tokenizer compared to previous models, contributing to its improved performance on a wide range of tasks. This new tokenizer may use up to 35% more tokens for the same fixed text.
</Note>

## Third-party platform pricing

Claude models are available on [AWS Bedrock](/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Vertex AI](/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](/docs/en/build-with-claude/claude-in-microsoft-foundry). For official pricing, visit:
- [AWS Bedrock pricing](https://aws.amazon.com/bedrock/pricing/)
- [Google Vertex AI pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models)
- [Microsoft Foundry pricing](https://azure.microsoft.com/en-us/pricing/details/microsoft-foundry/#pricing)

<Note>
**Regional and multi-region endpoint pricing for Claude 4.5 models and beyond**

Starting with Claude Sonnet 4.5 and Haiku 4.5:
- **AWS Bedrock** offers two endpoint types: global endpoints (dynamic routing for maximum availability) and regional endpoints (guaranteed data routing through specific geographic regions).
- **Google Vertex AI** offers three endpoint types: global endpoints, multi-region endpoints (dynamic routing within a geographic area), and regional endpoints.

Regional and multi-region endpoints include a 10% premium over global endpoints. The Claude API (1P) is global by default; for 1P data residency options and pricing, see [Data residency pricing](#data-residency-pricing) below.

**Scope:** This pricing structure applies to Claude Sonnet 4.5, Haiku 4.5, and all future models. Earlier models (Claude Sonnet 4 (deprecated), Opus 4 (deprecated), and prior releases) retain their existing pricing.

For implementation details and code examples:
- [AWS Bedrock global vs regional endpoints](/docs/en/build-with-claude/claude-in-amazon-bedrock#regions) for Opus 4.7, Haiku 4.5, and newer models, or [the legacy integration](/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#global-vs-regional-endpoints) for all other models on Bedrock
- [Google Vertex AI global, multi-region, and regional endpoints](/docs/en/build-with-claude/claude-on-vertex-ai#global-multi-region-and-regional-endpoints)
</Note>

## Feature-specific pricing

### Prompt caching

There are two ways to enable prompt caching:

Prompt caching uses the following pricing multipliers relative to base input token rates:

| Cache operation | Multiplier | Duration |
|:----------------|:-----------|:---------|
| 5-minute cache write | 1.25x base input price | Cache valid for 5 minutes |
| 1-hour cache write | 2x base input price | Cache valid for 1 hour |
| Cache read (hit) | 0.1x base input price | Same duration as the preceding write |

These multipliers stack with other pricing modifiers, including the Batch API discount and data residency.

For implementation details, supported models, and code examples, see the [prompt caching documentation](/docs/en/build-with-claude/prompt-caching).

### Data residency pricing

For Claude Opus 4.7, Claude Opus 4.6, and newer models, specifying US-only inference via the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. Global routing (the default) uses standard pricing.

This applies to the Claude API (1P) only. Third-party platforms have their own regional pricing. See [AWS Bedrock](https://aws.amazon.com/bedrock/pricing/) and [Google Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models) for details. Earlier models retain their existing pricing regardless of `inference_geo` settings.

For more information, see the [data residency documentation](/docs/en/build-with-claude/data-residency).

### Fast mode pricing

[Fast mode](/docs/en/build-with-claude/fast-mode) (beta: research preview) for Claude Opus 4.6 provides significantly faster output at premium pricing (6x standard rates). Fast mode pricing applies across the full context window, including requests over 200k input tokens. Currently supported on Opus 4.6:

| Input | Output |
|:------|:-------|
| $30 / MTok | $150 / MTok |

Fast mode pricing stacks with other pricing modifiers:
- [Prompt caching multipliers](#model-pricing) apply on top of fast mode pricing
- [Data residency](/docs/en/build-with-claude/data-residency) multipliers apply on top of fast mode pricing

Fast mode is not available with the [Batch API](#batch-processing).

For more information, see the [fast mode documentation](/docs/en/build-with-claude/fast-mode).

### Batch processing

The Batch API allows asynchronous processing of large volumes of requests with a 50% discount on both input and output tokens.

| Model | Batch input | Batch output |
|-------------------|------------------|-----------------|
| Claude Opus 4.7 | $2.50 / MTok | $12.50 / MTok |
| Claude Opus 4.6 | $2.50 / MTok | $12.50 / MTok |
| Claude Opus 4.5 | $2.50 / MTok | $12.50 / MTok |
| Claude Opus 4.1 | $7.50 / MTok | $37.50 / MTok |
| Claude Opus 4 | $7.50 / MTok | $37.50 / MTok |
| Claude Sonnet 4.6 | $1.50 / MTok | $7.50 / MTok |
| Claude Sonnet 4.5 | $1.50 / MTok | $7.50 / MTok |
| Claude Sonnet 4 | $1.50 / MTok | $7.50 / MTok |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | $1.50 / MTok | $7.50 / MTok |
| Claude Haiku 4.5 | $0.50 / MTok | $2.50 / MTok |
| Claude Haiku 3.5 | $0.40 / MTok | $2 / MTok |
| Claude Opus 3 ([deprecated](/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |
| Claude Haiku 3 | $0.125 / MTok | $0.625 / MTok |

For more information about batch processing, see the [batch processing documentation](/docs/en/build-with-claude/batch-processing).

### Long context pricing

[Claude Mythos Preview](https://anthropic.com/glasswing), Opus 4.7, Opus 4.6, and Sonnet 4.6 include the full [1M token context window](/docs/en/build-with-claude/context-windows) at standard pricing. (A 900k-token request is billed at the same per-token rate as a 9k-token request.) Prompt caching and batch processing discounts apply at standard rates across the full context window.

### Tool use pricing

Tool use requests are priced based on:
1. The total number of input tokens sent to the model (including in the `tools` parameter)
2. The number of output tokens generated
3. For server-side tools, additional usage-based pricing (e.g., web search charges per search performed)

Client-side tools are priced the same as any other Claude API request, while server-side tools may incur additional charges based on their specific usage.

The additional tokens from tool use come from:

- The `tools` parameter in API requests (tool names, descriptions, and schemas)
- `tool_use` content blocks in API requests and responses
- `tool_result` content blocks in API requests

When you use `tools`, we also automatically include a special system prompt for the model which enables tool use. The number of tool use tokens required for each model are listed below (excluding the additional tokens listed above). Note that the table assumes at least 1 tool is provided. If no `tools` are provided, then a tool choice of `none` uses 0 additional system prompt tokens.

| Model | Tool choice | Tool use system prompt token count |
|--------------------------|------------------------------------------------------|---------------------------------------------|
| Claude Opus 4.7 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Opus 4.6 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Opus 4.5 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Opus 4.1 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Opus 4 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Sonnet 4.6 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Sonnet 4.5 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Sonnet 4 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Haiku 4.5 | `auto`, `none`<hr />`any`, `tool` | 346 tokens<hr />313 tokens |
| Claude Haiku 3.5 | `auto`, `none`<hr />`any`, `tool` | 264 tokens<hr />340 tokens |
| Claude Opus 3 ([deprecated](/docs/en/about-claude/model-deprecations)) | `auto`, `none`<hr />`any`, `tool` | 530 tokens<hr />281 tokens |
| Claude Sonnet 3 | `auto`, `none`<hr />`any`, `tool` | 159 tokens<hr />235 tokens |
| Claude Haiku 3 | `auto`, `none`<hr />`any`, `tool` | 264 tokens<hr />340 tokens |

These token counts are added to your normal input and output tokens to calculate the total cost of a request.

For current per-model prices, refer to the [model pricing](#model-pricing) section.

For more information about tool use implementation and best practices, see the [tool use documentation](/docs/en/agents-and-tools/tool-use/overview).

### Specific tool pricing

#### Bash tool

The bash tool adds **245 input tokens** to your API calls.

Additional tokens are consumed by:
- Command outputs (stdout/stderr)
- Error messages
- Large file contents

See [tool use pricing](#tool-use-pricing) for complete pricing details.

#### Code execution tool

**Code execution is free when used with web search or web fetch.** When `web_search_20260209` or `web_fetch_20260209` is included in your API request, there are no additional charges for code execution tool calls beyond the standard input and output token costs.

When used without these tools, code execution is billed by execution time, tracked separately from token usage:

- Execution time has a minimum of 5 minutes
- Each organization receives **1,550 free hours** of usage per month
- Additional usage beyond 1,550 hours is billed at **$0.05 per hour, per container**
- If files are included in the request, execution time is billed even if the tool is not invoked, due to files being preloaded onto the container

Code execution usage is tracked in the response:

```json
"usage": {
"input_tokens": 105,
"output_tokens": 239,
"server_tool_use": {
"code_execution_requests": 1
}
}
```

#### Text editor tool

The text editor tool uses the same pricing structure as other tools used with Claude. It follows the standard input and output token pricing based on the Claude model you're using.

In addition to the base tokens, the following additional input tokens are needed for the text editor tool:

| Tool | Additional input tokens |
| ----------------------------------------- | --------------------------------------- |
| `text_editor_20250429` (Claude 4.x) | 700 tokens |
| `text_editor_20250124` (Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations))) | 700 tokens |

See [tool use pricing](#tool-use-pricing) for complete pricing details.

#### Web search tool

Web search usage is charged in addition to token usage:

```json
"usage": {
"input_tokens": 105,
"output_tokens": 6039,
"cache_read_input_tokens": 7123,
"cache_creation_input_tokens": 7345,
"server_tool_use": {
"web_search_requests": 1
}
}
```

Web search is available on the Claude API for **$10 per 1,000 searches**, plus standard token costs for search-generated content. Web search results retrieved throughout a conversation are counted as input tokens, in search iterations executed during a single turn and in subsequent conversation turns.

Each web search counts as one use, regardless of the number of results returned. If an error occurs during web search, the web search will not be billed.

#### Web fetch tool

Web fetch usage has **no additional charges** beyond standard token costs:

```json
"usage": {
"input_tokens": 25039,
"output_tokens": 931,
"cache_read_input_tokens": 0,
"cache_creation_input_tokens": 0,
"server_tool_use": {
"web_fetch_requests": 1
}
}
```

The web fetch tool is available on the Claude API at **no additional cost**. You only pay standard token costs for the fetched content that becomes part of your conversation context.

Example token usage for typical content:
- Average web page (10&nbsp;kB): ~2,500 tokens
- Large documentation page (100&nbsp;kB): ~25,000 tokens
- Research paper PDF (500&nbsp;kB): ~125,000 tokens

#### Computer use tool

Computer use follows the standard [tool use pricing](/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:

**System prompt overhead**: The computer use beta adds 466-499 tokens to the system prompt

**Computer use tool token usage**:
| Model | Input tokens per tool definition |
| ----- | -------------------------------- |
| Claude 4.x models | 735 tokens |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | 735 tokens |

**Additional token consumption**:
- Screenshot images (see [Vision pricing](/docs/en/build-with-claude/vision))
- Tool execution results returned to Claude

<Note>
If you're also using bash or text editor tools alongside computer use, those tools have their own token costs as documented in their respective pages.
</Note>

## Claude Managed Agents pricing

[Claude Managed Agents](/docs/en/managed-agents/overview) is billed on two dimensions: tokens and session runtime.

### Tokens

All tokens consumed by a Claude Managed Agents session are billed at the rates shown in [Model pricing](#model-pricing) above. [Prompt caching](#prompt-caching) multipliers apply identically. Web search triggered inside a session incurs the standard $10 per 1,000 searches.

The following Messages API modifiers do **not** apply to Claude Managed Agents sessions:

| Modifier | Why it doesn't apply |
| --- | --- |
| [Batch API discount](#batch-processing) | Sessions are stateful and interactive. There is no batch mode. |
| [Fast mode premium](#fast-mode-pricing) | Inference speed is managed by the runtime. |
| [Data residency multiplier](#data-residency-pricing) | `inference_geo` is a Messages API request field. |
| [Long context premium](#long-context-pricing) | Context window is managed by the runtime. |
| [Third-party platform pricing](#third-party-platform-pricing) | Claude Managed Agents is available only through the Claude API directly. |

### Session runtime

| SKU | Rate | Metering |
| --- | --- | --- |
| Session runtime | $0.08 per session-hour | `running` status duration |

<Note>
Session runtime replaces the [Code Execution](#code-execution-tool) container-hour billing model when using Claude Managed Agents. You are not separately billed for container hours on top of session runtime.
</Note>

### Worked example

A one-hour coding session using Claude Opus 4.7 that consumes 50,000 input tokens and 15,000 output tokens:

| Line item | Calculation | Cost |
| --- | --- | --- |
| Input tokens | 50,000 × $5 / 1,000,000 | $0.25 |
| Output tokens | 15,000 × $25 / 1,000,000 | $0.375 |
| Session runtime | 1.0 hour × $0.08 | $0.08 |
| **Total** | | **$0.705** |

If prompt caching is active and 40,000 of the input tokens are cache reads:

| Line item | Calculation | Cost |
| --- | --- | --- |
| Uncached input tokens | 10,000 × $5 / 1,000,000 | $0.05 |
| Cache read tokens | 40,000 × $5 × 0.1 / 1,000,000 | $0.02 |
| Output tokens | 15,000 × $25 / 1,000,000 | $0.375 |
| Session runtime | 1.0 hour × $0.08 | $0.08 |
| **Total** | | **$0.525** |

<Note>
Example calculation for processing 10,000 support tickets:
- Average ~3,700 tokens per conversation
- Using Claude Haiku 4.5 at $1/MTok input, $5/MTok output
- Total cost: ~$37.00 per 10,000 tickets
</Note>

For a detailed walkthrough of this calculation, see the [customer support agent guide](/docs/en/about-claude/use-case-guides/customer-support-chat).

## Additional pricing considerations

### Cost optimization strategies

When building agents with Claude:

1. **Use appropriate models:** Choose Haiku for simple tasks, Sonnet for complex reasoning
2. **Implement prompt caching:** Reduce costs for repeated context
3. **Batch operations:** Use the Batch API for non-time-sensitive tasks
4. **Monitor usage patterns:** Track token consumption to identify optimization opportunities

<Tip>
For high-volume agent applications, contact the [enterprise sales team](https://claude.com/contact-sales) for custom pricing arrangements.
</Tip>

### Rate limits

Rate limits vary by usage tier and affect how many requests you can make:

- **Tier 1:** Entry-level usage with basic limits
- **Tier 2:** Increased limits for growing applications
- **Tier 3:** Higher limits for established applications
- **Tier 4:** Maximum standard limits
- **Enterprise:** Custom limits available

For detailed rate limit information, see the [rate limits documentation](/docs/en/api/rate-limits).

For higher rate limits or custom pricing arrangements, [contact the sales team](https://claude.com/contact-sales).

### Volume discounts

Volume discounts may be available for high-volume users. These are negotiated on a case-by-case basis.

- Standard tiers use the pricing shown above
- Enterprise customers can [contact sales](mailto:sales@anthropic.com) for custom pricing
- Academic and research discounts may be available

### Enterprise pricing

For enterprise customers with specific needs:

- Custom rate limits
- Volume discounts
- Dedicated support
- Custom terms

Contact the sales team at [sales@anthropic.com](mailto:sales@anthropic.com) or through the [Claude Console](/settings/limits) to discuss enterprise pricing options.

## Billing and payment

- Billing is based on actual monthly usage
- All payments are in USD
- Credit card and invoicing options available
- Usage tracking available in the [Claude Console](/)

## Frequently asked questions

**How is token usage calculated?**

Tokens are pieces of text that models process. As a rough estimate, 1 token is approximately 4 characters or 0.75 words in English. The exact count varies by language and content type.

**Are there free tiers or trials?**

New users receive a small amount of free credits to test the API. [Contact sales](mailto:sales@anthropic.com) for information about extended trials for enterprise evaluation.

**How do discounts stack?**

**What payment methods are accepted?**

Major credit cards are accepted for standard accounts. Enterprise customers can arrange invoicing and other payment methods.

For additional questions about pricing, contact [support@anthropic.com](mailto:support@anthropic.com).

---
## about-claude-pricing.md

# Pricing

Learn about Anthropic's pricing structure for models and features

This page provides detailed pricing information for Anthropic's models and features. All prices are in USD.

For the most current pricing information, please visit [claude.com/pricing](https://claude.com/pricing).

Model pricing

The following table shows pricing for all Claude models across different usage tiers:

| Model | Base Input Tokens | 5m Cache Writes | 1h Cache Writes | Cache Hits & Refreshes | Output Tokens |
|----|----|----|----|----|----|
| Claude Opus 4.6 | \$5 / MTok | \$6.25 / MTok | \$10 / MTok | \$0.50 / MTok | \$25 / MTok |
| Claude Opus 4.5 | \$5 / MTok | \$6.25 / MTok | \$10 / MTok | \$0.50 / MTok | \$25 / MTok |
| Claude Opus 4.1 | \$15 / MTok | \$18.75 / MTok | \$30 / MTok | \$1.50 / MTok | \$75 / MTok |
| Claude Opus 4 | \$15 / MTok | \$18.75 / MTok | \$30 / MTok | \$1.50 / MTok | \$75 / MTok |
| Claude Sonnet 4.6 | \$3 / MTok | \$3.75 / MTok | \$6 / MTok | \$0.30 / MTok | \$15 / MTok |
| Claude Sonnet 4.5 | \$3 / MTok | \$3.75 / MTok | \$6 / MTok | \$0.30 / MTok | \$15 / MTok |
| Claude Sonnet 4 | \$3 / MTok | \$3.75 / MTok | \$6 / MTok | \$0.30 / MTok | \$15 / MTok |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | \$3 / MTok | \$3.75 / MTok | \$6 / MTok | \$0.30 / MTok | \$15 / MTok |
| Claude Haiku 4.5 | \$1 / MTok | \$1.25 / MTok | \$2 / MTok | \$0.10 / MTok | \$5 / MTok |
| Claude Haiku 3.5 | \$0.80 / MTok | \$1 / MTok | \$1.6 / MTok | \$0.08 / MTok | \$4 / MTok |
| Claude Opus 3 ([deprecated](/docs/en/about-claude/model-deprecations)) | \$15 / MTok | \$18.75 / MTok | \$30 / MTok | \$1.50 / MTok | \$75 / MTok |
| Claude Haiku 3 | \$0.25 / MTok | \$0.30 / MTok | \$0.50 / MTok | \$0.03 / MTok | \$1.25 / MTok |

MTok = Million tokens. The "Base Input Tokens" column shows standard input pricing, "Cache Writes" and "Cache Hits" are specific to [prompt caching](#prompt-caching), and "Output Tokens" shows output pricing. See [prompt caching pricing](#prompt-caching) below for an explanation of the cache columns and pricing multipliers.

Third-party platform pricing

Claude models are available on [AWS Bedrock](/docs/en/build-with-claude/claude-on-amazon-bedrock), [Google Vertex AI](/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](/docs/en/build-with-claude/claude-in-microsoft-foundry). For official pricing, visit:

- [AWS Bedrock pricing](https://aws.amazon.com/bedrock/pricing/)
- [Google Vertex AI pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing)
- [Microsoft Foundry pricing](https://azure.microsoft.com/en-us/pricing/details/ai-foundry/#pricing)

**Regional endpoint pricing for Claude 4.5 models and beyond**

Starting with Claude Sonnet 4.5 and Haiku 4.5, AWS Bedrock and Google Vertex AI offer two endpoint types:

- **Global endpoints**: Dynamic routing across regions for maximum availability
- **Regional endpoints**: Data routing guaranteed within specific geographic regions

Regional endpoints include a 10% premium over global endpoints. **The Claude API (1P) is global by default and unaffected by this change.** The Claude API is global-only (equivalent to the global endpoint offering and pricing from other providers).

**Scope**: This pricing structure applies to Claude Sonnet 4.5, Haiku 4.5, and all future models. Earlier models (Claude Sonnet 4, Opus 4, and prior releases) retain their existing pricing.

For implementation details and code examples:

- [AWS Bedrock global vs regional endpoints](/docs/en/build-with-claude/claude-on-amazon-bedrock#global-vs-regional-endpoints)
- [Google Vertex AI global vs regional endpoints](/docs/en/build-with-claude/claude-on-vertex-ai#global-vs-regional-endpoints)

Feature-specific pricing

Prompt caching

There are two ways to enable prompt caching:

Prompt caching uses the following pricing multipliers relative to base input token rates:

| Cache operation | Multiplier | Duration |
|----|----|----|
| 5-minute cache write | 1.25x base input price | Cache valid for 5 minutes |
| 1-hour cache write | 2x base input price | Cache valid for 1 hour |
| Cache read (hit) | 0.1x base input price | Same duration as the preceding write |

These multipliers stack with other pricing modifiers, including the Batch API discount, long context pricing, and data residency.

For implementation details, supported models, and code examples, see the [prompt caching documentation](/docs/en/build-with-claude/prompt-caching).

Data residency pricing

For Claude Opus 4.6 and newer models, specifying US-only inference via the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. Global routing (the default) uses standard pricing.

This applies to the Claude API (1P) only. Third-party platforms have their own regional pricing. See [AWS Bedrock](https://aws.amazon.com/bedrock/pricing/) and [Google Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/pricing) for details. Earlier models retain their existing pricing regardless of `inference_geo` settings.

For more information, see the [data residency documentation](/docs/en/build-with-claude/data-residency).

Fast mode pricing

| Input | Output |
|-------------|--------------|
| \$30 / MTok | \$150 / MTok |

Fast mode pricing stacks with other pricing modifiers:

- [Prompt caching multipliers](#model-pricing) apply on top of fast mode pricing
- [Data residency](/docs/en/build-with-claude/data-residency) multipliers apply on top of fast mode pricing

Fast mode is not available with the [Batch API](#batch-processing).

For more information, see the [fast mode documentation](/docs/en/build-with-claude/fast-mode).

Batch processing

The Batch API allows asynchronous processing of large volumes of requests with a 50% discount on both input and output tokens.

| Model | Batch input | Batch output |
|----|----|----|
| Claude Opus 4.6 | \$2.50 / MTok | \$12.50 / MTok |
| Claude Opus 4.5 | \$2.50 / MTok | \$12.50 / MTok |
| Claude Opus 4.1 | \$7.50 / MTok | \$37.50 / MTok |
| Claude Opus 4 | \$7.50 / MTok | \$37.50 / MTok |
| Claude Sonnet 4.6 | \$1.50 / MTok | \$7.50 / MTok |
| Claude Sonnet 4.5 | \$1.50 / MTok | \$7.50 / MTok |
| Claude Sonnet 4 | \$1.50 / MTok | \$7.50 / MTok |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | \$1.50 / MTok | \$7.50 / MTok |
| Claude Haiku 4.5 | \$0.50 / MTok | \$2.50 / MTok |
| Claude Haiku 3.5 | \$0.40 / MTok | \$2 / MTok |
| Claude Opus 3 ([deprecated](/docs/en/about-claude/model-deprecations)) | \$7.50 / MTok | \$37.50 / MTok |
| Claude Haiku 3 | \$0.125 / MTok | \$0.625 / MTok |

For more information about batch processing, see the [batch processing documentation](/docs/en/build-with-claude/batch-processing).

Long context pricing

Claude Opus 4.6 and Sonnet 4.6 include the full [1M token context window](/docs/en/build-with-claude/context-windows) at standard pricing. (A 900k-token request is billed at the same per-token rate as a 9k-token request.) Prompt caching and batch processing discounts apply at standard rates across the full context window.

For Claude Sonnet 4.5 and Sonnet 4, the 1M token context window is in beta for organizations in [usage tier](/docs/en/api/rate-limits) 4 and organizations with custom rate limits. When the `context-1m-2025-08-07` beta header is included, requests that exceed 200k input tokens are automatically charged at premium long context rates:

[TABLE]

Long context pricing for Sonnet 4.5 and Sonnet 4 stacks with other pricing modifiers:

- The [Batch API 50% discount](#batch-processing) applies to long context pricing
- [Prompt caching multipliers](#model-pricing) apply on top of long context pricing

Even with the beta flag enabled, requests with fewer than 200k input tokens are charged at standard rates. If your request exceeds 200k input tokens, all tokens incur premium pricing.

The 200k threshold is based solely on input tokens (including cache reads/writes). Output token count does not affect pricing tier selection, though output tokens are charged at the higher rate when the input threshold is exceeded.

For Claude Sonnet 4.5 and Sonnet 4, to check if your API request was charged at premium long context rates, examine the `usage` object in the API response:

```python
{
"usage": {
"input_tokens": 250000,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"output_tokens": 500
}
}
```

Calculate the total input tokens by summing:

- `input_tokens`
- `cache_creation_input_tokens` (if using prompt caching)
- `cache_read_input_tokens` (if using prompt caching)

If the total exceeds 200,000 tokens, the entire request was billed at premium long context rates.

For more information about the `usage` object, see the [API response documentation](/docs/en/api/messages#response-usage).

Tool use pricing

Tool use requests are priced based on:

Client-side tools are priced the same as any other Claude API request, while server-side tools may incur additional charges based on their specific usage.

The additional tokens from tool use come from:

- The `tools` parameter in API requests (tool names, descriptions, and schemas)
- `tool_use` content blocks in API requests and responses
- `tool_result` content blocks in API requests

[TABLE]

These token counts are added to your normal input and output tokens to calculate the total cost of a request.

For current per-model prices, refer to the [model pricing](#model-pricing) section.

For more information about tool use implementation and best practices, see the [tool use documentation](/docs/en/agents-and-tools/tool-use/overview).

Specific tool pricing

Bash tool

The bash tool adds **245 input tokens** to your API calls.

Additional tokens are consumed by:

- Command outputs (stdout/stderr)
- Error messages
- Large file contents

See [tool use pricing](#tool-use-pricing) for complete pricing details.

Code execution tool

When used without these tools, code execution is billed by execution time, tracked separately from token usage:

- Execution time has a minimum of 5 minutes
- Each organization receives **1,550 free hours** of usage per month
- Additional usage beyond 1,550 hours is billed at **\$0.05 per hour, per container**
- If files are included in the request, execution time is billed even if the tool is not invoked, due to files being preloaded onto the container

Code execution usage is tracked in the response:

```python
"usage": {
"input_tokens": 105,
"output_tokens": 239,
"server_tool_use": {
"code_execution_requests": 1
}
}
```

Text editor tool

The text editor tool uses the same pricing structure as other tools used with Claude. It follows the standard input and output token pricing based on the Claude model you're using.

In addition to the base tokens, the following additional input tokens are needed for the text editor tool:

| Tool | Additional input tokens |
|----|----|
| `text_editor_20250429` (Claude 4.x) | 700 tokens |
| `text_editor_20250124` (Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations))) | 700 tokens |

See [tool use pricing](#tool-use-pricing) for complete pricing details.

Web search tool

Web search usage is charged in addition to token usage:

```python
"usage": {
"input_tokens": 105,
"output_tokens": 6039,
"cache_read_input_tokens": 7123,
"cache_creation_input_tokens": 7345,
"server_tool_use": {
"web_search_requests": 1
}
}
```

Each web search counts as one use, regardless of the number of results returned. If an error occurs during web search, the web search will not be billed.

Web fetch tool

Web fetch usage has **no additional charges** beyond standard token costs:

```python
"usage": {
"input_tokens": 25039,
"output_tokens": 931,
"cache_read_input_tokens": 0,
"cache_creation_input_tokens": 0,
"server_tool_use": {
"web_fetch_requests": 1
}
}
```

The web fetch tool is available on the Claude API at **no additional cost**. You only pay standard token costs for the fetched content that becomes part of your conversation context.

Example token usage for typical content:

- Average web page (10 kB): ~2,500 tokens
- Large documentation page (100 kB): ~25,000 tokens
- Research paper PDF (500 kB): ~125,000 tokens

Computer use tool

Computer use follows the standard [tool use pricing](/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:

**System prompt overhead**: The computer use beta adds 466-499 tokens to the system prompt

**Computer use tool token usage**:

| Model | Input tokens per tool definition |
|----|----|
| Claude 4.x models | 735 tokens |
| Claude Sonnet 3.7 ([deprecated](/docs/en/about-claude/model-deprecations)) | 735 tokens |

**Additional token consumption**:

- Screenshot images (see [Vision pricing](/docs/en/build-with-claude/vision))
- Tool execution results returned to Claude

If you're also using bash or text editor tools alongside computer use, those tools have their own token costs as documented in their respective pages.

Agent use case pricing examples

Understanding pricing for agent applications is crucial when building with Claude. These real-world examples can help you estimate costs for different agent patterns.

Customer support agent example

When building a customer support agent, here's how costs might break down:

Example calculation for processing 10,000 support tickets:

- Average ~3,700 tokens per conversation
- Using Claude Opus 4.6 at \$5/MTok input, \$25/MTok output
- Total cost: ~\$37.00 per 10,000 tickets

For a detailed walkthrough of this calculation, see the [customer support agent guide](/docs/en/about-claude/use-case-guides/customer-support-chat).

General agent workflow pricing

For more complex agent architectures with multiple steps:

1. **Initial request processing**

- Typical input: 500-1,000 tokens
- Processing cost: ~\$0.003 per request

2. **Memory and context retrieval**

- Retrieved context: 2,000-5,000 tokens
- Cost per retrieval: ~\$0.015 per operation

3. **Action planning and execution**

- Planning tokens: 1,000-2,000
- Execution feedback: 500-1,000
- Combined cost: ~\$0.045 per action

For a comprehensive guide on agent pricing patterns, see the [agent use cases guide](/docs/en/about-claude/use-case-guides).

Cost optimization strategies

When building agents with Claude:

1. **Use appropriate models**: Choose Haiku for simple tasks, Sonnet for complex reasoning
2. **Implement prompt caching**: Reduce costs for repeated context
3. **Batch operations**: Use the Batch API for non-time-sensitive tasks
4. **Monitor usage patterns**: Track token consumption to identify optimization opportunities

For high-volume agent applications, contact the [enterprise sales team](https://claude.com/contact-sales) for custom pricing arrangements.

Additional pricing considerations

Rate limits

Rate limits vary by usage tier and affect how many requests you can make:

- **Tier 1**: Entry-level usage with basic limits
- **Tier 2**: Increased limits for growing applications
- **Tier 3**: Higher limits for established applications
- **Tier 4**: Maximum standard limits
- **Enterprise**: Custom limits available

For detailed rate limit information, see the [rate limits documentation](/docs/en/api/rate-limits).

For higher rate limits or custom pricing arrangements, [contact the sales team](https://claude.com/contact-sales).

Volume discounts

Volume discounts may be available for high-volume users. These are negotiated on a case-by-case basis.

- Standard tiers use the pricing shown above
- Enterprise customers can [contact sales](mailto:sales@anthropic.com) for custom pricing
- Academic and research discounts may be available

Enterprise pricing

For enterprise customers with specific needs:

- Custom rate limits
- Volume discounts
- Dedicated support
- Custom terms

Contact the sales team at [sales@anthropic.com](mailto:sales@anthropic.com) or through the [Claude Console](/settings/limits) to discuss enterprise pricing options.

Billing and payment

- Billing is calculated monthly based on actual usage
- Payments are processed in USD
- Credit card and invoicing options available
- Usage tracking available in the [Claude Console](/)

Frequently asked questions

**How is token usage calculated?**

Tokens are pieces of text that models process. As a rough estimate, 1 token is approximately 4 characters or 0.75 words in English. The exact count varies by language and content type.

**Are there free tiers or trials?**

New users receive a small amount of free credits to test the API. [Contact sales](mailto:sales@anthropic.com) for information about extended trials for enterprise evaluation.

**How do discounts stack?**

**What payment methods are accepted?**

Major credit cards are accepted for standard accounts. Enterprise customers can arrange invoicing and other payment methods.

For additional questions about pricing, contact [support@anthropic.com](mailto:support@anthropic.com).

---
## about-claude-s-max-plan-usage.md

# Search for answers or browse by topic

Search for articles...

Uh oh. That page doesn’t exist.

Try searching for your answer or just send us a message.

---
## add-or-update-your-team-plan-s-tax-or-vat-id-ffe5797dde.md

# Add or update your Team plan's tax or VAT ID

March 16, 2026

## Add your tax or VAT ID during signup

When you sign up for a Team plan, you may have the option to enter your Tax or VAT ID depending on your location:

1. During the signup process, enter your address information.

2. If your address is eligible for tax purposes, an optional field for your Tax or VAT ID will appear.

3. Enter your Tax or VAT ID in the provided field.

4. If the ID is entered correctly, you'll be able to proceed with your signup.

**Important**: If you're signing up as a business and want to use a name other than the one tied to your payment method, an organization Owner should check the "Use a different name on invoices" box when adding or updating your payment method in **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Then, enter your company name in the "Bill to" field to ensure it is reflected correctly on your invoice.

## Update your tax or VAT ID after signup

**Note**: Updates to your billing details will only apply to future billing cycles. Previously completed invoices cannot be updated retroactively.

If you need to add or update your Tax or VAT ID after you've already signed up, follow these steps:

1. Navigate to your **[Billing Settings](https://claude.ai/settings/billing)**.

2. Click on the "Update" button next to your payment method.

3. In the payment update form, you should see a field to enter or update your Tax or VAT ID.

4. Enter or modify your Tax or VAT ID as needed.

5. Save your changes.

**Note:** Your billing address determines your tax jurisdiction. See **[Understanding your billing address and tax calculation](https://support.claude.com/en/articles/12997130-understanding-your-billing-address-and-tax-calculation)** for details on how to view or update your billing address.

---
## add-or-update-your-team-plan-s-tax-or-vat-id.md

4. Add or update your Team plan's tax or VAT ID

# Add or update your Team plan's tax or VAT ID

## Add your tax or VAT ID during signup

When you sign up for a Team plan, you may have the option to enter your Tax or VAT ID depending on your location:

1. During the signup process, enter your address information.

2. If your address is eligible for tax purposes, an optional field for your Tax or VAT ID will appear.

3. Enter your Tax or VAT ID in the provided field.

4. If the ID is entered correctly, you'll be able to proceed with your signup.

## Update your tax or VAT ID after signup

**Note**: Updates to your billing details will only apply to future billing cycles. Previously completed invoices cannot be updated retroactively.

If you need to add or update your Tax or VAT ID after you've already signed up, follow these steps:

1. Navigate to your **[Billing Settings](https://claude.ai/settings/billing)**.

2. Click on the "Update" button next to your payment method.

3. In the payment update form, you should see a field to enter or update your Tax or VAT ID.

4. Enter or modify your Tax or VAT ID as needed.

5. Save your changes.

**Note:** Your billing address determines your tax jurisdiction. See **[Understanding your billing address and tax calculation](understanding-your-billing-address-and-tax-calculation.md)** for details on how to view or update your billing address.

---
## can-you-delete-data-that-i-sent-via-team-and-enterprise-plans-41e570413f.md

# Can you delete data that I sent via Team and Enterprise plans?

March 16, 2026

*This article is about our commercial products such as Claude for Work and the Anthropic API. For our consumer products such as Claude Free, Pro, Max and when accounts from those plans use Claude Code, see* *[here](https://privacy.claude.com/en/collections/10663362-consumers).*

While using Team and Enterprise plans, prompts and conversations in the product are maintained so you can see your conversation history in the product. You can [delete your chats](https://privacy.claude.com/en/articles/11117329-how-can-i-delete-or-rename-a-conversation) to remove them from your visible history.

We also retain data in our backend systems as described [here](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data).

Read more [here](https://privacy.claude.com/en/articles/7996875-can-you-delete-data-that-i-sent-via-api) about deleting data sent via API.

Enterprise plan customers can also set [custom retention timelines](https://support.claude.com/en/articles/10440198-custom-data-retention-controls-for-claude-enterprise) for their organization’s data.

---
## can-you-delete-data-that-i-sent-via-team-and-enterprise-plans.md

4. Can you delete data that I sent via Team and Enterprise plans?

# Can you delete data that I sent via Team and Enterprise plans?

We also retain data in our backend systems as described [here](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data).

Read more [here](https://privacy.claude.com/en/articles/7996875-can-you-delete-data-that-i-sent-via-api) about deleting data sent via API.

Enterprise plan customers can also set [custom retention timelines](../13-Enterprise-Admin/custom-data-retention-controls-for-claude-enterprise.md) for their organization’s data.

---
## cancel-your-organization-s-team-plan-subscription-2f37ffeadd.md

# Cancel your organization's Team plan subscription

An Owner or Primary Owner can cancel Team plan access by navigating to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Canceling your Team plan subscription means that your organization won't be charged for the next billing cycle. Your team will continue to have access to Claude until the end of the current billing cycle.

Removing a member from your Team plan ends their access immediately. If the removed member occupied an additional seat beyond the two members included by default, you will receive a prorated credit for the current billing cycle. If there are less than two current members, you can still add up to two members until the end of the billing cycle. For all other membership changes, you would need to resubscribe.

---
## cancel-your-organization-s-team-plan-subscription.md

4. Cancel your organization's Team plan subscription

# Cancel your organization's Team plan subscription

Removing a member from your Team plan ends their access immediately. If the removed member occupied an additional seat beyond the five members included by default, you will receive a prorated credit for the current billing cycle. If there are less than five current members, you can still add up to five members until the end of the billing cycle. For all other membership changes, you would need to resubscribe.

---
## cancel-your-pro-or-max-subscription-e51c9edc35.md

# Cancel your Pro or Max subscription

You may cancel your Pro or Max plan subscription at any time by following the cancellation instructions for the platform you signed up on. Your cancellation will take effect at the end of your current billing period and you can continue using your paid plan until then.

**Note:** To avoid being charged for your next billing period, cancel your subscription at least 24 hours before your next billing date.

## Cancel your Pro or Max subscription on Claude and Claude Desktop

If you signed up for a paid plan on the web version of Claude (**[claude.ai](https://claude.ai)**) or Claude Desktop (Mac, Windows, or Linux), start by logging into your account on a web browser or opening the desktop app. Click on your initials or name in the lower left corner and select “Settings” from the menu. Navigate to **[Settings \> Billing](https://claude.ai/settings/billing)** and click the “Cancel” button.

## Cancel your Pro or Max subscription on Claude for iOS

If you subscribed to a Pro or Max plan via Claude for iOS, your subscription and payment will be handled directly on your iOS device.

To cancel your subscription, click on your initials in the top right corner of Claude for iOS, and then click “Billing” from the menu options. Select “Manage subscription” and follow the prompts for cancellation. If you’ve already removed the app from your device, you can also follow the instructions located in this App Store resource to unsubscribe: **[If you want to cancel a subscription from Apple](https://support.apple.com/en-us/118428)**.

You may cancel your Pro or Max subscription at any time from the platform you signed up on. To avoid being charged for your next billing period, cancel your subscription at least 24 hours before your next billing date.

## Cancel your Pro or Max subscription on Claude for Android

If you subscribed to a Pro or Max plan via Claude for Android, your subscription and payment will be handled directly on your Android device.

To cancel your subscription, click on your initials in the top right corner of Claude for Android, and then click “Billing” from the menu options. Select “Manage subscription” and follow the prompts for cancellation. If you’ve already removed the app from your device, you can also follow the instructions located in this Play Store resource to unsubscribe: **[Cancel, pause, or change a subscription on Google Play](https://support.google.com/googleplay/answer/7018481?hl=en&co=GENIE.Platform%3DAndroid)**.

---
## change-your-team-plan-from-monthly-to-annual-billing-596eff439e.md

# Change your Team plan from monthly to annual billing

March 16, 2026

Owners and Primary Owners of Team plans with monthly subscriptions can switch from the monthly plan to an annual plan by following these steps:

1. Navigate to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)** or **[claude.ai/upgrade](http://claude.ai/upgrade)**.

2. You’ll see a banner confirming your current monthly plan in your Billing settings; click the “Switch to Annual” button.

3. Or from /upgrade, click the “Switch to Annual plan” button:

4. The confirmation screen will display the total cost for your upgrade from monthly to annual billing:

5. Click “Confirm subscription.”

6. Your new annual Team plan will start immediately and you will be credited for any unused time on your previous monthly plan.

---
## change-your-team-plan-from-monthly-to-annual-billing.md

4. Change your Team plan from monthly to annual billing

# Change your Team plan from monthly to annual billing

Owners and Primary Owners of Team plans with monthly subscriptions can switch from the monthly plan to an annual plan by following these steps:

1. Navigate to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)** or **[claude.ai/upgrade](http://claude.ai/upgrade)**.

2. You’ll see a banner confirming your current monthly plan in your Billing settings; click the “Switch to Annual” button.

3. Or from /upgrade, click the “Switch to Annual plan” button:

4. The confirmation screen will display the total cost for your upgrade from monthly to annual billing:

5. Click “Confirm subscription.”

6. Your new annual Team plan will start immediately and you will be credited for any unused time on your previous monthly plan.

---
## choose-a-claude-plan-34cc52ef4e.md

# Choose a Claude plan

May 19, 2026

Use the following guide to determine which plan is right for you.

[TABLE]

The plans listed above are intended for individual users. Looking for a plan for your organization or company? Read more about our Team and Enterprise plans:

- **[What is the Team plan?](https://support.claude.com/en/articles/9266767-what-is-the-team-plan)**

- **[What is the Enterprise plan?](https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan)**

---
## choosing-a-claude-plan-f9c577e51e.md

# Choose a Claude plan

May 19, 2026

Use the following guide to determine which plan is right for you.

[TABLE]

The plans listed above are intended for individual users. Looking for a plan for your organization or company? Read more about our Team and Enterprise plans:

- **[What is the Team plan?](https://support.claude.com/en/articles/9266767-what-is-the-team-plan)**

- **[What is the Enterprise plan?](https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan)**

---
## choosing-a-claude-plan.md

# Choosing a Claude plan

Use the following guide to determine which plan is right for you.

[TABLE]

The plans listed above are intended for individual users. Looking for a plan for your organization or company? Read more about our Team and Enterprise plans:

- [What is the Team plan?](what-is-the-team-plan.md)

- [What is the Enterprise plan?](what-is-the-enterprise-plan.md)

---
## claude-enterprise-plan-claude-by-anthropic-b0def816fc.md

# Claude enterprise solutions

The frontier, on every desk

Put Claude to work across your organization. Help everyone think deeper, do more, and build securely.

Get Enterprise plan

[Get Enterprise plan](http://claude.ai/create/enterprise)

Get Enterprise plan

Build on Claude Platform

[Build on Claude Platform](/platform/api)

Build on Claude Platform

## Trusted by the world’s leading organizations

“Slack’s close collaboration with Anthropic has helped our Engineering and Product teams accelerate prototyping and model testing.”

97minutes per week saved by the average user through summarization and recap features

Industry:Software

Company size:Large

Product:Claude Platform

Location:North America

“With this partnership, Allianz is taking a decisive step to address critical AI challenges in insurance. Anthropic's focus on safety and transparency complements our strong dedication to customer excellence and stakeholder trust.”

90%week-over-week growth company-wide deployment, with rapid global adoption

Industry:Insurance

Company size:Large

Product:Claude Platform

Location:EMEA

“Through using Claude, we’ve saved millions, which we have reinvested in *upskilling* our customer support agents. We’ve empowered our agents to focus on those more complex issues that really require human care.”

87%reduction in customer support time

30%more accurate teams making sharper calls

Industry:Transportation

Company size:Large

Product:Claude Platform

Location:North America

“As AI becomes the interface for decisions, trust becomes the standard. Moody’s decision-grade connected intelligence is key to unlocking AI for high‑stakes credit and compliance decision‑making.”

1200%credit memo prep time cut from 40 hours to 2 minutes with Claude-built agents

Industry:Financial services

Company size:Large

Product:Claude Platform

Location:North America

“We saw 12 hours of prototyping work collapse into about 20 minutes. Then your whole team can jump in and refine it together.”

30+concurrent agent tasks from a single task board

97%reduction in prototyping time

Industry:Software

Company size:Large

Product:Claude Managed Agents

Location:North America

“In a highly regulated industry, we can't just throw our data and information into a large language model and hope for the best. Our conversations with Anthropic really guided in the ways we can securely use Claude for planning, for strategic tasks, for code generation.”

1000xclinical study documentation down from 10 weeks to 10 minutes

Industry:Life sciences

Company size:Large

Product:Claude Code

Location:Europe

## Built for enterprise

### Built on the best models

Claude leads on reasoning, coding, and analysis benchmarks. The same frontier models power every surface, from business apps to developer tools.

### No model training by default

Your prompts, data, and results are not used to train our models by default. Review our data practices at the Trust Center.

### Flexible by design

Pick the products and platform that are right for your teams, whether you’re collaborating with Claude at work or building your own products and offerings.

### Made to pass security review

The security, compliance, and admin controls your organization needs.

Learn more

[Learn more](https://trust.anthropic.com/)

Learn more

\*Data retention controls and OTEL monitoring are currently available on Claude Enterprise only.

Single sign-on (SSO/SAML) and domain capture

Usage analytics and reporting

SCIM provisioning

Spend controls

Role-based access control (RBAC)

Data retention controls\*

Audit logs and OpenTelemetry monitoring\*

SOC 2, ISO 27001, GDPR, and CCPA compliance

Compliance API

HIPAA-ready offering

## Bring Claude to your enterprise two ways

Deploy Claude to your workforce or build it into your products.

### Claude Enterprise

Give every employee secure access to Chat, Claude Cowork, Claude Code, and your company's connectors. Get the admin controls, management, and visibility your IT and security teams need.

See plans

[See plans](#pricing)

See plans

### Claude Platform

Access the Claude API to power new experiences, ship production-grade agents, and integrate Claude into the workflows and applications you're building.

Explore the platform

[Explore the platform](/platform/api)

Explore the platform

Results with Claude Code

90%

less time spent on complex code migrations

## Secure products for employees, everywhere your teams work

Claude Code

Claude Cowork

Claude Chat

Claude Security

Active

[Play video](#)

Play video

### Code faster across your enterprise stack

Build, debug, and ship using natural language from your terminal, IDE, Slack, or the web. Claude Code works wherever your team does.

Learn more

[Learn more](/product/claude-code/enterprise)

Learn more

[Play video](#)

Play video

### Delegate tasks to Claude with Cowork

Connect your files and tools, then hand off research, documents, and repetitive work. Get polished deliverables back while you focus on the work that needs your judgment.

Learn more

[Learn more](/product/cowork)

Learn more

[Play video](#)

Play video

### Chat: A thinking partner for everyday work

Chat with Claude to develop ideas, draft content, tighten reports, work through hard problems, and more.

Learn more

[Learn more](/product/overview)

Learn more

[Play video](#)

Play video

### Find and fix vulnerabilities with Claude Security

Claude helps security teams and developers by reviewing code for security issues, drafts patches, and explains the risk in language your whole team can act on.

Learn more

[Learn more](/product/claude-security)

Learn more

Tailor Claude to your business

Connect to Gmail, Google Drive, Slack and more to give Claude context from across your stack. Use Claude directly inside Microsoft 365 or with Google Chrome.

Learn more

[Learn more](/connectors)

Learn more

## Real work, across every function

Engineering

Marketing

Sales

Product Management

Human Resources

Security

Active

Prompt

Audit our use of the deprecated legacy-auth library across the monorepo. Generate a migration plan to move all 47 services to auth-v2, prioritized by risk and ordered by dependencies.

✻ Migration plan: legacy-auth → auth-v2

Audited 47 services, 312 call sites, 8 distinct usage patterns.

Recommended order

Phase 1 — Low risk (weeks 1–2, 12 services)
Internal admin tools with no external dependencies. Safe to validate the auth-v2 codemod and surface unknown patterns.

Phase 2 — Leaf services (weeks 3–5, 18 services)
No downstream consumers in the dependency graph. Failures stay contained; single staged rollout per service.

Phase 3 — Core services (weeks 6–9, 17 services)
Auth-critical paths with downstream impact. Requires feature flags, shadow traffic comparison, and per-team rollback plans.

Risk callouts

payments-api — blocker
Uses undocumented legacy-auth.signWithRotation() not present in auth-v2. Needs design discussion before migration.

mobile-bff — needs review
Integration tests pinned to legacy-auth response format. Token envelope changed (token.claims → token.payload); 23 fixtures to update.

identity-gateway — coordinated cutover
Sits in front of 31 of 47 services. Recommend cutover at the Phase 2 → 3 boundary with a 48-hour dual-write window.

Suggested next steps

1\. Open an RFC for the signWithRotation equivalent in auth-v2.
2. Run the codemod against Phase 1 services, one PR per service.
3. Add a CI check that fails on new legacy-auth imports in week 2.
4. Schedule identity-gateway cutover with platform for week 5.

### Engineering

- Convert project requirements into technical specifications
- Design system architecture and component interactions
- Troubleshoot errors and runtime issues
- Identify code optimizations and performance improvements

Claude Code for Enterprise

[Claude Code for Enterprise](/product/claude-code/enterprise)

Claude Code for Enterprise

Prompt

Build a Q1 channel performance review. Pull spend and conversions from HubSpot and paid social metrics from our LinkedIn dashboards. Show ROAS by channel over the last six months and flag the channels where performance is declining.

Attachments

HubSpot_Q1_export

24 kb

CSV

8 kb

CSV

Q1 channel performance review

ROAS by channel — last 6 months

Email Organic Direct Paid social

↓ Paid social ROAS dropped 38% after Feb iOS update

↑ Email overperforming after segmentation refresh in March

→ Organic steady at 3.4x, direct holding around 2.9x

### Marketing

- Interpret market trends and consumer behavior patterns
- Brainstorm multi-platform content items
- Develop marketing campaign strategies
- Create post campaign performance reports

Prompt

I have a renewal call with Acme Corp's VP of Operations on Thursday. Pull the account picture from HubSpot, open work in Asana, and any mentions in \#acme-account on Slack. Produce a brief covering relationship status, open risks, expansion signals, and three talking points for the call. Send to me in Slack.

Connectors

Hubspot

Slack

Asana

Camilla Lee

Messages

Jot something down

*Acme Corp – Thursday renewal prep*

📇 *Account:* Sarah Chen, VP Ops · Renewal Jun 30 · ARR \$148k · 240 seats (Team)

🤝 *Relationship:* Healthy, Y2 renewal · CSM Jordan Park · NPS 8 in April · Mar 18 QBR went well

⚠️ *Risks:* P1 SSO ticket open since Apr 29 (eng ETA slipped 2x) · Finance asked for ROI one-pager (Asana ACME-184, Wed) · Lattice ran discovery w/ ops leads last week

📈 *Expansion:* Adoption +42% MoM · Legal, Procurement, RevOps onboarded · Enterprise tier discussed in March · automation seat add-on ~\$22k upside

🎯 *Three talking points*

1. Open with the SSO ticket — bring new ETA + offer a credit if it slips again
2. Frame +42% adoption and 3 new departments as Enterprise-level value
3. Pre-empt Lattice with the Procurement cycle-time win, then tee up the automation add-on

Sent using @Claude

### Sales

- Analyze sales calls to craft tailored account plans
- Develop objection handling strategies
- Build compelling and tailored pitches
- Interpret sales metrics and KPIs

Prompt

Score the candidate features for our Q3 roadmap. Pull usage data from Amplitude, recent product feedback from \#product-feedback in Slack, and engineering effort estimates from Linear. Score each feature on reach, impact, and effort. Rank them and flag the top three to discuss in roadmap planning Thursday.

Connectors

Amplitude

Slack

Linear

Q3 Prioritization.xlsx

### Product Management

- Define product vision and objectives
- Analyze user feedback and usage data
- Create product specifications and requirements documents
- Interpret product usage metrics and KPIs

Prompt

Build a 30-60-90 day onboarding plan for our new Senior Product Designer starting Monday. Pull from the role's job description, the design team's Notion handbook, recent Figma files the team has shipped. Include who they should meet in week one, what to read, what to ship by day 30, and goals for days 60 and 90.

Connectors

Figma

Notion

#### Onboarding plan: Maya Chen, Senior Product Designer

*Start date: Monday, May 18
Manager: Priya Shah*

**Week 1 — Get oriented**

###### **People to meet (15 min each)**

- Priya Shah (managetr) — already on calendar, Monday 10am
- Jordan Lee (design lead, peer) — book Tuesday
- Sam Patel (PM partner for the checkout team)
- Two engineers from the checkout team: Ana Torres, Ben Wu

###### **Read first**

- Design system docs (Notion: /Design/System)
- Last quarter's research readouts (Notion: /Research/Q1)
- Checkout team's most recent Figma file (Onboarding-redesign-v2)

###### **Days 1–30 — Land**

- Ship one small UI fix end-to-end to learn the workflow
- Attend three user research sessions
- Present a teardown of one competitor's checkout in week 4 design crit

###### **Days 31–60 — Contribute**

- Own one in-flight project (likely the cart abandonment redesign)
- First design review on owned work by day 60

###### **Days 61–90 — Lead**

- Drive the next quarter's roadmap discussion for the checkout team
- Goal: ship one feature you scoped end-to-end

### Human Resources

Prompt

Scan our webhook service for security vulnerabilities

● Scanning 247 files across app/, services/, routes/...

● Analyzing auth flows, input validation, file handling...

● Filtering by severity ≥ high...

● Found 4 findings in acme-corp/hookrelay

CRITICAL Shell command injection via webhook payload

app/services/notifiers/script_runner.py:21 · Command injection

CRITICAL JWT authentication bypass via "none" algorithm

app/auth/jwt_handler.py:28 · Auth bypass

CRITICAL Path traversal in export file download endpoint

app/routes/exports.py:39 · Path traversal

HIGH Server-side request forgery in destination URL validation

app/services/validator.py:36 · SSRF

✓ 12 lower-severity findings filtered out

### Security

- Triage alerts and prioritize real threats
- Investigate incidents and trace attack paths
- Correlate signals across logs and tools
- Draft incident reports and post-mortems
- Build detection rules and tune existing ones

## Get the Enterprise plan

Explore features

[Explore features](/pricing#team-enterprise-features)

Explore features

### Enterprise

Get started today. Includes Enterprise security and compliance, chat, Claude Code, Cowork, connectors, SSO, SCIM, audit logs, and more.

\$20

Per seat / month, billed annually.
Usage is billed as you go at API rates, based on what your team uses. Annual commitment required. Minimum 20 seats.

Get the Enterprise plan

[Get the Enterprise plan](http://claude.ai/create/enterprise)

Get the Enterprise plan

Chat with buying specialist

[Chat with buying specialist](https://claude.ai/buying-specialist)

Chat with buying specialist

[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Prices shown don’t include applicable tax. Price and plans are subject to change at Anthropic's discretion.

[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Price and plans are subject to change at Anthropic's discretion.

## Build on the Claude Platform

Give developers access to the API to build AI-enabled products, services, and agents.

View documentation

[View documentation](https://platform.claude.com/docs)

View documentation

### Primitives

Building blocks to integrate Claude, including the Messages API and tools, with full control over every layer.

Learn more

[Learn more](https://platform.claude.com/docs)

Learn more

### Harnesses and infrastructure

Everything you need to ship production-grade agents, including Claude Managed Agents.

Learn more

[Learn more](https://claude.com/blog/claude-managed-agents)

Learn more

### Operating system

Controls to deploy and manage agents across your organization, including authorization, governance, and observability.

Learn more

[Learn more](https://platform.claude.com/)

Learn more

Customer story

Canva empowers employees across teams with Claude

Read story

[Read story](https://claude.com/customers/canva)

Read story

Customer story

GitLab enhances productivity with Claude

Read story

[Read story](https://claude.com/customers/gitlab-enterprise)

Read story

[Prev](#)

Code modernization

Modernize legacy code without starting over. Claude Code handles large-scale refactoring while keeping your existing business logic intact.

Learn more

[Learn more](https://claude.com/solutions/code-modernization)

Learn more

### Build on your own

Launch your own generative AI-enabled products with:

- Access to all Claude models
- Usage-based tiers
- Automatically increasing rate limits
- Pay-as-you-go pricing
- Self-serve deployment on workbench
- [Prompting guides and developer docs](https://docs.anthropic.com/claude/reference/getting-started-with-the-api)

Start building

[Start building](/platform/api)

Start building

### Get extra support

Need custom rate limits or hands-on help? Contact our sales team for:

- Anthropic-supported onboarding
- Custom rate limits
- Billing via monthly invoices
- Prompting support
- Deployment support

[Contact sales](/contact-sales)

## FAQ

Security and compliance

Products and capabilities

Getting started

Active

### Security and compliance

### Does Anthropic train on our data?

No. Your inputs and outputs are not used to train our models by default. Review our data practices at the [Trust Center](https://trust.anthropic.com/).

### What security and compliance controls does Claude Enterprise include?

Claude Enterprise is built for secure deployment at scale. SSO with domain capture, role-based access, SCIM provisioning, and self-serve seat management for identity; audit logs, data retention controls, the Compliance API, and HIPAA-ready BAAs for compliance; and usage analytics, the Analytics API, and spend controls for visibility. All data is encrypted in transit and at rest. Visit the Trust Center for the full overview, or our regional compliance page for data residency details.

### Do you support HIPAA? Can we get a BAA?

Yes, for both the Claude Platform and Claude Enterprise. Claude Platform: Healthcare customers can sign a BAA with no Zero Data Retention requirement. The HIPAA-ready feature set in the Messages API includes prompt caching, web search, and structured outputs, with coverage expanding over time. Claude Enterprise: HIPAA-ready configuration is available with a BAA from Anthropic. Once enabled, your organization can process Protected Health Information (PHI) through Claude in accordance with HIPAA.

[Prev](#)

### Products and capabilities

### What's included in the Claude Enterprise plan?

Claude Enterprise gives your organization the full Claude experience including Claude Code, Claude Cowork and chat all with enterprise-grade security controls, plus connectors that bring context from your existing tools into Claude. For a full feature breakdown, see [claude.com/pricing](https://claude.com/pricing).

### What's the difference between Chat, Claude Code, and Claude Cowork?

Chat is meant for research, brainstorming, writing, and analysis. Claude Code is for software development from your terminal, desktop app, or the web. Claude Cowork is for delegating complex tasks that run in the background. All three are included in every Enterprise plan and entitlements are managed with role-based access controls from organization settings.

### Can we connect Claude to the tools we already use?

Yes. Connectors bring context from Google Drive, Gmail, Slack, Microsoft 365 and many more into Claude. You can also use Claude directly inside Excel, PowerPoint, Outlook, Slack, and Chrome. See the [Enterprise administrator guide](https://claude.com/resources/tutorials/claude-enterprise-administrator-guide) for setup.

[Prev](#)

### Getting started

### Can we buy Claude through AWS Marketplace, Google Cloud, or Azure?

Claude Enterprise is available directly from Anthropic and through AWS Marketplace, where it can draw down from your existing AWS commit. Claude Platform (the API) is also available on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Azure.

### Do you support invoice billing on Claude Enterprise?

Yes. Sales-assisted Claude Enterprise plans include invoice billing. Self-serve Enterprise plans accept credit card or ACH bank transfer.

### Where do I get an API key for Claude Platform and how does billing work?

Create an API key in the [Claude Console](http://platform.claude.com/settings/keys). For production workloads, you can use [Workload Identity Federation](https://platform.claude.com/docs/en/manage-claude/workload-identity-federation) to exchange your cloud provider's identity for short-lived tokens instead of managing static keys. Self-serve accounts are prepaid: add a payment method, purchase credits, and optionally enable auto-reload. Credits cover API usage, the Workbench, and Claude Code (when authenticated with an API key). Enterprise customers can use monthly invoicing instead, [contact sales](https://claude.com/contact-sales) to set this up.

[Prev](#)

## Enterprise resources

Everything you need to integrate AI thoughtfully into your organization.

[Claude Enterprise administrator guide](https://claude.com/resources/tutorials/claude-enterprise-administrator-guide)

Claude Enterprise administrator guide

Tutorial

[Tutorial](https://claude.com/resources/tutorials/claude-enterprise-administrator-guide)

Tutorial

[Claude Cowork Enterprise admin guide](https://claude.com/resources/tutorials/claude-cowork-enterprise-administrator-guide)

Claude Cowork Enterprise admin guide

Tutorial

[Tutorial](https://claude.com/resources/tutorials/claude-cowork-enterprise-administrator-guide)

Tutorial

[Zero trust AI agents](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6a0521e14a6fed28fe4a3b3b_Claude-eBook-Zero-Trust-for-AI-Agents-05132026.pdf)

Zero trust AI agents

Guide

[Guide](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6a0521e14a6fed28fe4a3b3b_Claude-eBook-Zero-Trust-for-AI-Agents-05132026.pdf)

Guide

[Deploying Claude across your organization](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/69f24d3e09b921b92403774e_Claude-Deploying-Claude-Across-Your-Organization-04292026.pdf)

Deploying Claude across your organization

Guide

[Guide](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/69f24d3e09b921b92403774e_Claude-Deploying-Claude-Across-Your-Organization-04292026.pdf)

Guide

[The Enterprise AI transformation guide](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6a05227a9465cf77dba4c51a_The%20Enterprise%20AI%20Transformation%20Guide%20101425%20(1).pdf)

The Enterprise AI transformation guide

Guide

[Guide](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6a05227a9465cf77dba4c51a_The%20Enterprise%20AI%20Transformation%20Guide%20101425%20(1).pdf)

Guide

[The 2026 state of AI agents report](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6a0522b7ebbb33addef0d238_2026%20State%20of%20AI%20Agents%20Report%20(1).pdf)

The 2026 state of AI agents report

‍Report

[‍Report](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6a0522b7ebbb33addef0d238_2026%20State%20of%20AI%20Agents%20Report%20(1).pdf)

‍Report

## Ready to bring Claude to your organization?

Get Enterprise plan

[Get Enterprise plan](http://claude.ai/create/enterprise)

Get Enterprise plan

Build on Claude Platform

[Build on Claude Platform](/platform/api)

Build on Claude Platform

[Homepage](https://claude.com)

Homepage

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Write

[Button Text](#)

Button Text

Learn

[Button Text](#)

Button Text

Code

[Button Text](#)

Button Text

Write

- Help me develop a unique voice for an audience

Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help!

- Improve my writing style

Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

- Brainstorm creative ideas

Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

Learn

- Explain a complex topic simply

Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

- Help me make sense of these ideas

Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

- Prepare for an exam or interview

Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

Code

- Explain a programming concept

Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

- Look over my code and give me tips

Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

- Vibe code with me

Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

- Write case studies

This is another test

- Write grant proposals

Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational.

Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help!

- Write video scripts

this is a test

[Anthropic](https://www.anthropic.com/)

Anthropic

Products

- Claude

[Claude](/product/overview)
Claude

- Claude Code

[Claude Code](/product/claude-code)
Claude Code

- Claude Code for Enterprise

[Claude Code for Enterprise](/product/claude-code/enterprise)
Claude Code for Enterprise

- Claude Cowork

[Claude Cowork](/product/cowork)
Claude Cowork

- @Claude

[@Claude](/product/tag)
@Claude

- Claude Design

[Claude Design](/product/design)
Claude Design

- Claude Science

[Claude Science](/product/claude-science)
Claude Science

- Claude Security

[Claude Security](/product/claude-security)
Claude Security

- Download app

[Download app](/download)
Download app

- Pricing

[Pricing](/pricing)
Pricing

- Log in

[Log in](https://claude.ai/login)

Features

- Claude for Chrome

[Claude for Chrome](/claude-for-chrome)
Claude for Chrome

- Claude for Microsoft 365

[Claude for Microsoft 365](/claude-for-microsoft-365)
Claude for Microsoft 365

- Skills

[Skills](/skills)
Skills

Models

- Mythos

[Mythos](https://www.anthropic.com/claude/mythos)
Mythos

- Fable

[Fable](https://www.anthropic.com/claude/fable)
Fable

- Opus

[Opus](https://www.anthropic.com/claude/opus)
Opus

- Sonnet

[Sonnet](https://www.anthropic.com/claude/sonnet)
Sonnet

- Haiku

[Haiku](https://www.anthropic.com/claude/haiku)
Haiku

Solutions

- AI agents

[AI agents](/solutions/agents)
AI agents

- Code modernization

[Code modernization](/solutions/code-modernization)
Code modernization

- Coding

[Coding](/solutions/coding)
Coding

- Customer support

[Customer support](/solutions/customer-support)
Customer support

- Cybersecurity

[Cybersecurity](/solutions/cybersecurity)
Cybersecurity

- Enterprise

[Enterprise](/solutions/enterprise)
Enterprise

- Financial services

[Financial services](/solutions/financial-services)
Financial services

- Government

[Government](/solutions/government)
Government

- Healthcare

[Healthcare](/solutions/healthcare)
Healthcare

- Higher education

[Higher education](/solutions/education)
Higher education

- K-12 teachers

[K-12 teachers](/solutions/teachers)
K-12 teachers

- Legal

[Legal](/solutions/legal)
Legal

- Life sciences

[Life sciences](/solutions/life-sciences)
Life sciences

- Nonprofits

[Nonprofits](/solutions/nonprofits)
Nonprofits

- Small business

[Small business](/solutions/small-business)
Small business

Claude Platform

- Overview

[Overview](/platform/api)
Overview

- Developer docs

[Developer docs](https://platform.claude.com/docs)
Developer docs

- Pricing

[Pricing](https://claude.com/pricing#api)
Pricing

- Ecosystem

[Ecosystem](/ecosystem)
Ecosystem

- Marketplace

[Marketplace](/platform/marketplace)
Marketplace

- Claude on AWS

[Claude on AWS](/partners/claude-on-aws)
Claude on AWS

- Google Cloud

[Google Cloud](/partners/google-cloud)
Google Cloud

- Microsoft Foundry

[Microsoft Foundry](/partners/microsoft-foundry)
Microsoft Foundry

- Regional compliance

[Regional compliance](/regional-compliance)
Regional compliance

- Console login

[Console login](https://platform.claude.com/)
Console login

Resources

- Blog

[Blog](/blog)
Blog

- Claude partner network

[Claude partner network](/partners)
Claude partner network

- Community

[Community](/community)
Community

- Connectors

[Connectors](/connectors)
Connectors

- Courses

[Courses](https://www.anthropic.com/learn)
Courses

- Customer stories

[Customer stories](/customers)
Customer stories

- Engineering at Anthropic

[Engineering at Anthropic](https://www.anthropic.com/engineering)
Engineering at Anthropic

- Events

[Events](https://www.anthropic.com/events)
Events

- Plugins

[Plugins](/plugins)
Plugins

- Powered by Claude

[Powered by Claude](/partners/powered-by-claude)
Powered by Claude

- Service partners

[Service partners](/partners/services)
Service partners

- Tutorials

[Tutorials](/resources/tutorials)
Tutorials

- Use cases

[Use cases](/resources/use-cases)
Use cases

Company

- Anthropic

[Anthropic](https://www.anthropic.com/)
Anthropic

- Careers

[Careers](https://www.anthropic.com/careers)
Careers

- Policy

[Policy](https://www.anthropic.com/policy)
Policy

- Economic Futures

[Economic Futures](https://www.anthropic.com/economic-futures)
Economic Futures

- Research

[Research](https://www.anthropic.com/research)
Research

- News

[News](https://www.anthropic.com/news)
News

- Policy on the AI Exponential

---
## claude-fable-5-on-your-plan-9438480215.md

# Claude Fable 5 on your plan

We previously ran a promotion that allowed you to use up to 50% of your weekly subscription limit on Claude Fable 5 at no extra cost. After that promotion ends on July 19, 2026 at 11:59:59 PM PT, Fable 5 will still be available to you, and how you access it will depend on your plan.

On Max plans, premium seats on Team plans, and premium seats on legacy seat-based Enterprise plans, Fable 5 will be a standard part of your plan. On Pro plans, standard seats on Team plans, and standard seats on legacy seat-based Enterprise plans, Fable 5 will run on pay-as-you-go usage credits. This article explains how Fable 5 will work on each plan, how to access it, and what happens when you reach your usage limits.

Claude Fable 5 is available on all paid plans (Pro, Max, Team, and Enterprise).

## How Fable 5 works on each plan

Starting July 20, 2026:

- **Max plans, premium seats on Team plans, and premium seats on seat-based Enterprise plans:** Fable 5 is included as a standard part of your plan. You can use up to 50% of your weekly usage limits on Fable 5 at no extra cost. Fable 5 draws from your plan's regular weekly usage limits and uses them faster than other Claude models. When you reach your Fable 5 limit, you can keep using Fable 5 with usage credits, or switch to another model to stay within your plan's usage limits.

- **Pro plans and standard seats on Team plans:** Fable 5 isn't included in your plan's usage limits. You can use Fable 5 with usage credits, which let you pay for usage beyond what your plan includes. Eligible Pro and Team standard seats qualify for a one-time credit to help with the change. Learn more about the **[Claude Fable 5 one-time free credits promotion](https://support.claude.com/en/articles/15862783)**.

- **Standard seats on seat-based Enterprise plans:** Fable 5 isn't included in your plan's usage limits. You can use Fable 5 if your organization has enabled usage credits, which let you pay for usage beyond what your plan includes. Standard seats on seat-based Enterprise plans don't qualify for the one-time promotional credit.

- **Usage-based Enterprise plans:** Access to Fable 5 is billed at standard API rates. For current per-model pricing, see our **[API pricing page](https://www.anthropic.com/pricing#api).**

- **Claude API:** Access to Fable 5 is billed at standard API rates. For current per-model pricing, see our **[API pricing page](https://www.anthropic.com/pricing#api).**

## How to access Claude Fable 5

You can access Claude Fable 5 on:

- Claude on the web

- Claude Mobile

- Claude Desktop

- Claude Cowork

- Claude Code

- Claude Design

- Claude for Microsoft 365

- Claude Tag

In Claude on the web, Claude Desktop, and Claude Mobile, select "Fable 5" from the model picker. In Claude Code, Fable 5 requires version 2.1.170 or later. To use Fable 5 in Claude Cowork, you need to be on the latest version of Claude Desktop.

## When you reach your Fable 5 usage limit

On Max plans, premium seats on Team plans, and premium seats on seat-based Enterprise plans, once you use up to 50% of your weekly usage limits on Fable 5, you can continue in one of two ways: keep using Fable 5 with usage credits, or switch to another Claude model to keep working within your plan's usage limits.

On Pro plans, standard seats on Team plans, and standard seats on seat-based Enterprise plans, Fable 5 runs on pay-as-you-go usage credits from the start, since it isn't included in your plan's usage limits.

This works the same way across Claude on the web, Claude Mobile, Claude Desktop, Claude Cowork, and Claude Code. Learn more about **[usage credits](https://support.claude.com/en/articles/12429409)**.

## Frequently asked questions

### Why can’t I see Claude Fable 5?

Check the following:

- You’re on a paid Claude plan. Fable 5 isn’t available on the Free plan.

- If you’re using Claude Code, you’re on version 2.1.170 or later.

- If you’re using Cowork, you’re on the latest version of Claude Desktop.

- Your organization hasn't enabled Fable 5.

### Will this use my regular usage limits?

It depends on your plan. On the Max plan, premium seats on the Team plan, and premium seats on the seat-based Enterprise plan, Fable 5 counts toward your plan's usage limits, and you can use up to 50% of your weekly usage limits on Fable 5 at no extra cost. On the Pro plan, standard seats on the Team plan, and standard seats on the seat-based Enterprise plan, Fable 5 runs on usage credits rather than your plan's usage limits.

### Will I get 50% more for my weekly limit for Fable 5 if I’m on the Max plan, Team plan with premium seats, or a seat-based Enterprise plan with premium seats?

No. You can use up to 50% of your weekly limit on Fable 5, but your use of other models draws from the same usage limits and you can never use more than your weekly limit. You can track both in your usage settings.

### I'm on the Pro or Team plan. Why is Fable 5 no longer included?

The earlier promotion that included Fable 5 in your plan's weekly usage limits ended on July 19, 2026 at 11:59:59 PM PT. On the Pro plan and standard seats on the Team plan, you can keep using Fable 5 with usage credits or by upgrading to the Max plan. You may also be eligible for a one-time credit. Learn more about the **[Claude Fable 5 one-time free credits promotion](https://support.claude.com/en/articles/15862783)**.

---
## configure-custom-data-retention-controls-for-enterprise-plans-277abfb672.md

# Configure custom data retention controls for Enterprise plans

March 16, 2026

This feature is available to Enterprise plan customers. To set custom retention periods for your organization, you must have either a Primary Owner or Owner role.

*This article is about our commercial products such as Claude for Work and the Anthropic API. For our consumer products such as Claude Free, Pro, Max and when accounts from those plans use Claude Code, see **[here](https://privacy.claude.com/en/collections/10663362-consumers)**.*

Custom data retention controls allow organizations to manage how long Claude stores conversation and project data. This article explains how to set up and manage data retention periods for your organization.

## How data retention works

Data retention is based on the last observed activity:

- **For chats:** Retention period starts from the time of the last message in the conversation.

- **For projects:** Retention period starts from the time the project was last updated (this includes chat creation or project knowledge base modifications).

- Note that your custom data retention periods set for projects will supersede your custom retention periods for any chats.

The minimum retention period is 30 days, and each month is counted as 30 days. For example, a three-month retention period equals 90 days.

## What gets deleted

When data reaches the end of its retention period:

- **For chats:** All chats (including chats within projects) and any artifacts within those chats will be deleted.

- **For projects:** All projects will be deleted, including any chats and artifacts within those projects.

## Important considerations

- Deletion occurs at midnight UTC on the scheduled day.

- By default, data is retained indefinitely unless a custom retention period is set.

- When you modify retention settings, any data that falls outside the new retention period will be deleted immediately upon saving.

- Data past its retention period will be permanently deleted and cannot be recovered.

## Setting up data retention

## To set custom retention periods:

1. Log in to your Owner Enterprise plan account.

2. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls)**.

3. Set your desired retention period (minimum 30 days).

4. Save your changes.

## Example retention calculation

If a conversation’s last message is at 3PM UTC on March 1 with a 30-day retention period, the deletion will occur at midnight UTC on March 31.

## Monitoring retention-related activities

All retention-related actions and changes are automatically tracked in **[audit logs](https://support.claude.com/en/articles/9970975-how-to-access-audit-logs)**. You can access these logs to monitor changes to retention settings and data deletion events.

---
## configure-custom-data-retention-controls-for-enterprise-plans.md

4. Configure custom data retention controls for Enterprise plans

# Configure custom data retention controls for Enterprise plans

This feature is available to Enterprise plan customers. To set custom retention periods for your organization, you must have either a Primary Owner or Owner role.

*This article is about our commercial products such as Claude for Work and the Anthropic API. For our consumer products such as Claude Free, Pro, Max and when accounts from those plans use Claude Code, see **[here](https://privacy.claude.com/en/collections/10663362-consumers)**.*

## How data retention works

Data retention is based on the last observed activity:

- **For chats:** Retention period starts from the time of the last message in the conversation.

- **For projects:** Retention period starts from the time the project was last updated (this includes chat creation or project knowledge base modifications).

- Note that your custom data retention periods set for projects will supersede your custom retention periods for any chats.

The minimum retention period is 30 days, and each month is counted as 30 days. For example, a three-month retention period equals 90 days.

## What gets deleted

When data reaches the end of its retention period:

- **For chats:** All chats (including chats within projects) and any artifacts within those chats will be deleted.

- **For projects:** All projects will be deleted, including any chats and artifacts within those projects.

## Important considerations

- Deletion occurs at midnight UTC on the scheduled day.

- By default, data is retained indefinitely unless a custom retention period is set.

- When you modify retention settings, any data that falls outside the new retention period will be deleted immediately upon saving.

- Data past its retention period will be permanently deleted and cannot be recovered.

## Setting up data retention

## To set custom retention periods:

1. Log in to your Owner Enterprise plan account.

2. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls)**.

3. Set your desired retention period (minimum 30 days).

4. Save your changes.

## Example retention calculation

If a conversation’s last message is at 3PM UTC on March 1 with a 30-day retention period, the deletion will occur at midnight UTC on March 31.

## Monitoring retention-related activities

---
## costs.md

> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Manage costs effectively

> Track token usage, set team spend limits, and reduce Claude Code costs with context management, model selection, extended thinking settings, and preprocessing hooks.

Claude Code consumes tokens for each interaction. Costs vary based on codebase size, query complexity, and conversation length. The average cost is \$6 per developer per day, with daily costs remaining below \$12 for 90% of users.

For team usage, Claude Code charges by API token consumption. On average, Claude Code costs \~\$100-200/developer per month with Sonnet 4.5 though there is large variance depending on how many instances users are running and whether they're using it in automation.

This page covers how to [track your costs](#track-your-costs), [manage costs for teams](#managing-costs-for-teams), and [reduce token usage](#reduce-token-usage).

## Track your costs

### Using the `/cost` command

<Note>
The `/cost` command shows API token usage and is intended for API users. Claude Max and Pro subscribers have usage included in their subscription, so `/cost` data isn't relevant for billing purposes. Subscribers can use `/stats` to view usage patterns.
</Note>

The `/cost` command provides detailed token usage statistics for your current session:

```
Total cost: $0.55
Total duration (API): 6m 19.7s
Total duration (wall): 6h 33m 10.2s
Total code changes: 0 lines added, 0 lines removed
```

## Managing costs for teams

When using Claude API, you can [set workspace spend limits](../04-API-Reference/Guides/build-with-claude-workspaces-12135e8f23.md#workspace-limits) on the total Claude Code workspace spend. Admins can [view cost and usage reporting](../04-API-Reference/Guides/build-with-claude-workspaces-12135e8f23.md#usage-and-cost-tracking) in the Console.

<Note>
When you first authenticate Claude Code with your Claude Console account, a workspace called "Claude Code" is automatically created for you. This workspace provides centralized cost tracking and management for all Claude Code usage in your organization. You cannot create API keys for this workspace; it is exclusively for Claude Code authentication and usage.
</Note>

On Bedrock, Vertex, and Foundry, Claude Code does not send metrics from your cloud. To get cost metrics, several large enterprises reported using [LiteLLM](/en/llm-gateway#litellm-configuration), which is an open-source tool that helps companies [track spend by key](https://docs.litellm.ai/docs/proxy/virtual_keys#tracking-spend). This project is unaffiliated with Anthropic and we have not audited its security.

### Rate limit recommendations

When setting up Claude Code for teams, consider these Token Per Minute (TPM) and Request Per Minute (RPM) per-user recommendations based on your organization size:

| Team size | TPM per user | RPM per user |
| ------------- | ------------ | ------------ |
| 1-5 users | 200k-300k | 5-7 |
| 5-20 users | 100k-150k | 2.5-3.5 |
| 20-50 users | 50k-75k | 1.25-1.75 |
| 50-100 users | 25k-35k | 0.62-0.87 |
| 100-500 users | 15k-20k | 0.37-0.47 |
| 500+ users | 10k-15k | 0.25-0.35 |

For example, if you have 200 users, you might request 20k TPM for each user, or 4 million total TPM (200\*20,000 = 4 million).

The TPM per user decreases as team size grows because we expect fewer users to use Claude Code concurrently in larger organizations. These rate limits apply at the organization level, not per individual user, which means individual users can temporarily consume more than their calculated share when others aren't actively using the service.

<Note>
If you anticipate scenarios with unusually high concurrent usage (such as live training sessions with large groups), you may need higher TPM allocations per user.
</Note>

## Reduce token usage

Token costs scale with context size: the more context Claude processes, the more tokens you use. Claude Code automatically optimizes costs through prompt caching (which reduces costs for repeated content like system prompts) and auto-compaction (which summarizes conversation history when approaching context limits).

The following strategies help you keep context small and reduce per-message costs.

### Manage context proactively

Use `/cost` to check your current token usage, or [configure your status line](/en/statusline#context-window-usage) to display it continuously.

* **Clear between tasks**: Use `/clear` to start fresh when switching to unrelated work. Stale context wastes tokens on every subsequent message. Use `/rename` before clearing so you can easily find the session later, then `/resume` to return to it.
* **Add custom compaction instructions**: `/compact Focus on code samples and API usage` tells Claude what to preserve during summarization.

You can also customize compaction behavior in your CLAUDE.md:

```markdown theme={null}
# Compact instructions

When you are using compact, please focus on test output and code changes
```

### Choose the right model

Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session, or set a default in `/config`. For simple subagent tasks, specify `model: haiku` in your [subagent configuration](/en/sub-agents#choose-a-model).

### Reduce MCP server overhead

Each MCP server adds tool definitions to your context, even when idle. Run `/context` to see what's consuming space.

* **Prefer CLI tools when available**: Tools like `gh`, `aws`, `gcloud`, and `sentry-cli` are more context-efficient than MCP servers because they don't add persistent tool definitions. Claude can run CLI commands directly without the overhead.
* **Disable unused servers**: Run `/mcp` to see configured servers and disable any you're not actively using.
* **Tool search is automatic**: When MCP tool descriptions exceed 10% of your context window, Claude Code automatically defers them and loads tools on-demand via [tool search](/en/mcp#scale-with-mcp-tool-search). Since deferred tools only enter context when actually used, a lower threshold means fewer idle tool definitions consuming space. Set a lower threshold with `ENABLE_TOOL_SEARCH=auto:<N>` (for example, `auto:5` triggers when tools exceed 5% of your context window).

### Install code intelligence plugins for typed languages

[Code intelligence plugins](/en/discover-plugins#code-intelligence) give Claude precise symbol navigation instead of text-based search, reducing unnecessary file reads when exploring unfamiliar code. A single "go to definition" call replaces what might otherwise be a grep followed by reading multiple candidate files. Installed language servers also report type errors automatically after edits, so Claude catches mistakes without running a compiler.

### Offload processing to hooks and skills

Custom [hooks](../07-Hooks/hooks-reference-claude-code-docs.md) can preprocess data before Claude sees it. Instead of Claude reading a 10,000-line log file to find errors, a hook can grep for `ERROR` and return only matching lines, reducing context from tens of thousands of tokens to hundreds.

A [skill](../08-Plugins-Skills/extend-claude-with-skills-claude-code-docs.md) can give Claude domain knowledge so it doesn't have to explore. For example, a "codebase-overview" skill could describe your project's architecture, key directories, and naming conventions. When Claude invokes the skill, it gets this context immediately instead of spending tokens reading multiple files to understand the structure.

For example, this PreToolUse hook filters test output to show only failures:

<Tabs>
<Tab title="settings.json">
Add this to your [settings.json](/en/settings#settings-files) to run the hook before every Bash command:

```json theme={null}
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/filter-test-output.sh"
}
]
}
]
}
}
```
</Tab>

<Tab title="filter-test-output.sh">
The hook calls this script, which checks if the command is a test runner and modifies it to show only failures:

```bash theme={null}
#!/bin/bash
input=$(cat)
cmd=$(echo "$input" | jq -r '.tool_input.command')

# If running tests, filter to show only failures
if [[ "$cmd" =~ ^(npm test|pytest|go test) ]]; then
filtered_cmd="$cmd 2>&1 | grep -A 5 -E '(FAIL|ERROR|error:)' | head -100"
echo "{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"permissionDecision\":\"allow\",\"updatedInput\":{\"command\":\"$filtered_cmd\"}}}"
else
echo "{}"
fi
```
</Tab>
</Tabs>

### Move instructions from CLAUDE.md to skills

Your [CLAUDE.md](../02-Claude-Code-CLI/how-claude-remembers-your-project-claude-code-docs-f1c064262d.md) file is loaded into context at session start. If it contains detailed instructions for specific workflows (like PR reviews or database migrations), those tokens are present even when you're doing unrelated work. [Skills](../08-Plugins-Skills/extend-claude-with-skills-claude-code-docs.md) load on-demand only when invoked, so moving specialized instructions into skills keeps your base context smaller. Aim to keep CLAUDE.md under \~500 lines by including only essentials.

### Adjust extended thinking

Extended thinking is enabled by default with a budget of 31,999 tokens because it significantly improves performance on complex planning and reasoning tasks. However, thinking tokens are billed as output tokens, so for simpler tasks where deep reasoning isn't needed, you can reduce costs by disabling it in `/config` or lowering the budget (for example, `MAX_THINKING_TOKENS=8000`).

### Delegate verbose operations to subagents

Running tests, fetching documentation, or processing log files can consume significant context. Delegate these to [subagents](/en/sub-agents#isolate-high-volume-operations) so the verbose output stays in the subagent's context while only a summary returns to your main conversation.

### Write specific prompts

Vague requests like "improve this codebase" trigger broad scanning. Specific requests like "add input validation to the login function in auth.ts" let Claude work efficiently with minimal file reads.

### Work efficiently on complex tasks

For longer or more complex work, these habits help avoid wasted tokens from going down the wrong path:

* **Use plan mode for complex tasks**: Press Shift+Tab to enter [plan mode](/en/common-workflows#use-plan-mode-for-safe-code-analysis) before implementation. Claude explores the codebase and proposes an approach for your approval, preventing expensive re-work when the initial direction is wrong.
* **Course-correct early**: If Claude starts heading the wrong direction, press Escape to stop immediately. Use `/rewind` or double-tap Escape to restore conversation and code to a previous checkpoint.
* **Give verification targets**: Include test cases, paste screenshots, or define expected output in your prompt. When Claude can verify its own work, it catches issues before you need to request fixes.
* **Test incrementally**: Write one file, test it, then continue. This catches issues early when they're cheap to fix.

## Background token usage

Claude Code uses tokens for some background functionality even when idle:

* **Conversation summarization**: Background jobs that summarize previous conversations for the `claude --resume` feature
* **Command processing**: Some commands like `/cost` may generate requests to check status

These background processes consume a small amount of tokens (typically under \$0.04 per session) even without active interaction.

## Understanding changes in Claude Code behavior

Claude Code regularly receives updates that may change how features work, including cost reporting. Run `claude --version` to check your current version. For specific billing questions, contact Anthropic support through your [Console account](https://platform.claude.com/login). For team deployments, start with a small pilot group to establish usage patterns before wider rollout.

---
## cowork-for-team-and-enterprise-plans-aac1cf8e4c.md

# Use Claude Cowork on Team and Enterprise plans

This article explains important limitations and considerations for Team and Enterprise organizations using Claude Cowork.

## Availability

Claude Cowork is available for paid plans (Pro, Max, Team, Enterprise) on:

- **Claude Desktop for macOS**

- **[Click here](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect)** to download

- **Claude Desktop for Windows**

- **Windows users:** Cowork requires the latest version of Claude for Windows. Download or update at **[claude.com/download](https://claude.com/download)**.

- **Web**, at claude.ai

- **Claude Mobile**, in the latest version of Claude for iOS and Claude for Android

Starting August 3, 2026, Claude Cowork is in beta on web and mobile for Team and Enterprise plans. On web and mobile, Claude Cowork sessions run in Anthropic's cloud.

------------------------------------------------------------------------

## Where Cowork runs

During the beta, Cowork sessions can run in two places:

- **Sessions in the cloud (beta starting August 3, 2026):** Running Cowork in the cloud lets members run tasks on Anthropic's infrastructure instead of their own machines. This means work continues across desktop, web, and mobile and scheduled tasks run when the laptop closes and no device is online.

- **Local sessions:** Claude's work runs on the user’s computer, with code in an isolated virtual machine.

## Admin controls

Claude Cowork is on by default, but organization owners can manually disable it.

### Enable or disable Cowork

1. Log in to your Team or Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Cowork](https://claude.ai/admin-settings/cowork)**.

3. Locate the **Enable for your organization** toggle under **Cowork**.

4. Toggle off to disable Cowork for all users in your organization.

This toggle controls whether Cowork is available at all. Whether sessions can run in the cloud is a separate control.

**Note:** This is an organization-wide setting. On Enterprise plans, you can use groups and custom roles to enable Cowork for specific teams. See **[Access controls](#h_8465b1b558)** below.

### **Enable or disable sessions in the cloud**

For Team and Enterprise plans, there's a separate organization-wide toggle in **[Organization settings \> Cowork](https://claude.ai/admin-settings/cowork)** under "Run Cowork in the cloud."

- **Team plans:** on by default. An owner can turn it off any time from the "Run Cowork in the cloud" toggle.

- **Enterprise plans:** off by default. An owner turns on "Run Cowork in the cloud," then grants the Cowork in the cloud capability to a group with custom roles. See **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)**.

### Connector tool approvals

The organization setting **Allow "Always allow" for connector tools** in **[Organization settings \> Cowork](https://claude.ai/admin-settings/cowork)** (under **Permissions**) controls whether members can skip per-task approval for write-capable connector tools in Cowork. This setting is off by default.

When the setting is off:

- The "Allow for all tasks" option appears grayed out in Cowork's approval dialog, even when your organization-wide tool policies allow these tools.

- Previously saved always-allow preferences for write tools aren't honored. Members approve these tools per task until the setting is turned on.

Read-only tools are exempt only when the connector annotates them as read-only. Most custom connectors don't annotate their tools, so every tool on those connectors is gated.

On Enterprise plans, this setting works alongside custom role grants, and the most restrictive layer wins. Role grants can't override it. For the full layering model, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans#h_979e558d00)**.

### Plugins

Plugins are included with Cowork and controlled by the same admin toggle—there's no separate setting to manage plugin access within Cowork.

For details on what members can do with plugins, see **[Use plugins in Cowork](https://support.claude.com/en/articles/13837440-use-plugins-in-cowork)**.

------------------------------------------------------------------------

## Projects

Projects in Cowork let users organize tasks into dedicated workspaces with their own files, links, instructions, and memory. Projects are available to all Cowork users. There are no separate admin controls for projects, so owners cannot restrict project creation at the organization level at this time.

Projects are available wherever members use Cowork. Projects tied to a local folder support Cowork sessions on desktop only. For local sessions, project data is stored on the user's computer; for sessions in the cloud, projects are saved with the member's Claude account. For full details, see **[Organize your tasks with projects in Cowork](https://support.claude.com/en/articles/14116274-organize-your-tasks-with-projects-in-cowork).**

------------------------------------------------------------------------

## Manage plugins for your organization

Owners can create plugin marketplaces to distribute curated plugins across their organization. This gives you control over which plugins your team members see and use in Cowork.

- **Installed by default** — Automatically added for everyone in your organization. Members can uninstall if they choose.

- **Available** — Appears in the plugin catalog for members to install on their own.

- **Required** — Automatically installed for all members. Members cannot uninstall it.

- **Not available** — Hidden from the catalog. Useful for staging or deprecating plugins.

On Enterprise plans, admins can also override these preferences for specific groups—for example, auto-installing a plugin for one team while hiding it from everyone else. For details, see **[Manage Cowork plugins for your organization](https://support.claude.com/en/articles/13837433-manage-cowork-plugins-for-your-organization)**.

------------------------------------------------------------------------

## Company branding

Cowork now surfaces your organization's branding, including a redesigned home screen tailored to your team. Team and Enterprise owners can configure branding within **Organization settings**.

------------------------------------------------------------------------

## Compliance and monitoring

Team and Enterprise owners can stream Cowork events to your SIEM and observability tools through OpenTelemetry. This gives security teams visibility into tool calls, file access, human approval decisions, and more—though it doesn't replace audit logging for compliance purposes. For setup, supported events, and security considerations, see **[Monitor Cowork activity with OpenTelemetry](https://support.claude.com/en/articles/14477985-monitor-cowork-activity-with-opentelemetry).**

You can also refer to **[Monitoring](https://claude.com/docs/cowork/monitoring)** in our Claude Docs for more information.

Cowork via mobile and web is captured in the Compliance API. Learn more about **[retrieving remote sessions in the Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-content-data)**.

### Local conversation storage

For local sessions, Cowork stores conversation history locally on users' computers. This data is not subject to Anthropic's standard **[data retention policies](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data)** and cannot be centrally managed or exported by admins.

For sessions in the cloud, your sessions and files are saved to your Claude account.

### Access controls

The Cowork toggle is organization-wide—either all members have access or none do. On Enterprise plans, admins who need per-team control can use **[groups and custom roles](https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans)** to selectively enable Cowork or grant the "Run Cowork in the cloud" capability to specific users or teams. Team plans don't have access to these controls, so Cowork remains all-or-nothing.

Within Cowork, admins have more granular control over plugins. You can set per-plugin installation preferences to control which plugins are auto-installed, available for self-service, or hidden from your organization's catalog. On Enterprise plans, these preferences can also be customized per group. See **[Manage plugins for your organization](https://support.claude.com/en/articles/13837433-manage-cowork-plugins-for-your-organization)** for details.

------------------------------------------------------------------------

## Security considerations

### Prompt injection risks

Cowork has unique risks due to its agentic nature and internet access. While we've implemented safety measures including model training and content classifiers, the risk of prompt injection attacks is non-zero.

Users should:

- Avoid granting access to files with sensitive information

- Monitor Claude for suspicious actions

- Limit browser and web access to trusted sources

- Report suspicious behavior immediately

For detailed guidance, see **[Use Cowork safely](https://support.claude.com/en/articles/13364135-use-cowork-safely)**.

### Network access

Cowork respects your organization's current network egress permissions. Review your network access settings in **[Organization settings \> Capabilities](https://claude.ai/admin-settings/capabilities)** under **Code execution** before enabling Cowork.

Network settings are applied when a new Cowork session is created. If you change the network access mode or add domains to the allowlist while a conversation is already active, those changes will not take effect in that session. Start a new conversation for the updated settings to apply.

**Important:** Network egress permissions don't apply to the web fetch or **[web search](https://support.claude.com/en/articles/10684626-enabling-and-using-web-search)** tools or MCPs, including Claude in Chrome. Web fetch runs server-side and is limited to search results and URLs you've shared. Team or Enterprise plan owners can turn off web search for Cowork and Chat in **[Organization settings \> Capabilities](https://claude.ai/admin-settings/capabilities)**, or Claude in Chrome via **[Organization settings \> Claude in Chrome](http://claude.ai/admin-settings/browser-extension)**.

---
## cowork-for-team-and-enterprise-plans.md

4. Use Cowork on Team and Enterprise plans

# Use Cowork on Team and Enterprise plans

This article explains important limitations and considerations for Team and Enterprise organizations using Cowork during the research preview period.

## Availability

Cowork is available as a research preview for paid plans (Pro, Max, Team, Enterprise) on:

- **Claude Desktop for macOS**

- **[Click here](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect)** to download

- **Claude Desktop for Windows** (x64 only)

- **Windows users:** Cowork requires the latest version of Claude for Windows. Download or update at **[claude.com/download](https://claude.com/download)**.

- Windows arm64 is not supported.

------------------------------------------------------------------------

## Admin controls

Cowork will be on by default when the research preview launches, but organization owners can manually disable it.

**How to enable or disable Cowork:**

1. Log in to your Team or Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Capabilities](https://claude.ai/admin-settings/capabilities)**.

3. Locate the **Cowork** toggle.

4. Toggle off to disable Cowork for all users in your organization.

**Note:** This is an organization-wide setting. Granular controls by user or role are not available during the research preview.

### Plugins

Plugins are included with Cowork and controlled by the same admin toggle—there's no separate setting to manage plugin access within Cowork.

For details on what members can do with plugins, see **[Use plugins in Cowork](../15-Claude-AI-Features/use-plugins-in-cowork.md)**.

------------------------------------------------------------------------

## Projects

Project data (tasks and memory) is stored locally on each user's computer, consistent with how other Cowork data is handled. For full details, see **[Organize your tasks with projects in Cowork](https://support.claude.com/en/articles/14116274-organize-your-tasks-with-projects-in-cowork).**

------------------------------------------------------------------------

## Manage plugins for your organization

Owners can create plugin marketplaces to distribute curated plugins across their organization. This gives you control over which plugins your team members see and use in Cowork.

For each plugin, you can set one of three installation preferences:

- **Auto-install** — Automatically added for everyone in your organization. Members can uninstall if they choose.

- **Available** — Appears in the plugin catalog for members to install on their own.

- **Not available** — Hidden from the catalog. Useful for staging or deprecating plugins.

You can populate your marketplace by uploading plugin files directly. To get started, go to **Organization settings \> Plugins** in Claude Desktop.

For a full walkthrough, see **[Manage plugins for your organization](../22-Safety-Policy/manage-cowork-plugins-for-your-organization.md)**.

------------------------------------------------------------------------

## Company branding

Cowork now surfaces your organization's branding, including a redesigned home screen tailored to your team. Team and Enterprise owners can configure branding within **Organization settings**.

------------------------------------------------------------------------

## Compliance and monitoring limitations

Cowork currently lacks several enterprise monitoring and compliance capabilities. These limitations are important to understand before enabling Cowork for your organization.

### No audit logging or data exports

Cowork activity is **not captured** in:

- Audit Logs

- Compliance API

- Data Exports

If your organization requires audit trails for compliance purposes, do not enable Cowork for regulated workloads.

### OpenTelemetry support

Team and Enterprise owners can track usage, costs, and tool activity across their teams using OpenTelemetry. This provides visibility into how Cowork and plugins are being used, though it doesn't replace audit logging for compliance purposes.

For more information, see **[Monitoring](https://claude.com/docs/cowork/monitoring)** in our Claude Docs.

### Local conversation storage

Cowork stores conversation history locally on users' computers. This data is not subject to Anthropic's standard **[data retention policies](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data)** and cannot be centrally managed or exported by admins.

### Access controls

The Cowork toggle is organization-wide — either all members have access or none do. If you need to selectively enable Cowork for specific users or teams, reach out to your Anthropic Contact or our **[Sales team](https://claude.com/contact-sales)**.

Within Cowork, admins have more granular control over plugins. You can set per-plugin installation preferences to control which plugins are auto-installed, available for self-service, or hidden from your organization's catalog. See **[Manage plugins for your organization](../22-Safety-Policy/manage-cowork-plugins-for-your-organization.md)** for details.

------------------------------------------------------------------------

## Security considerations

### Prompt injection risks

Users should:

- Avoid granting access to files with sensitive information

- Monitor Claude for suspicious actions

- Limit browser and web access to trusted sources

- Report suspicious behavior immediately

For detailed guidance, see **[Use Cowork safely](../15-Claude-AI-Features/use-cowork-safely.md)**.

### Network access

**Important:** Network egress permissions don't apply to the **[web search tool](https://support.claude.com/en/articles/10684626-enabling-and-using-web-search)**. Team or Enterprise plan owners can turn off web search for Cowork and Chat in **[Organization settings \> Capabilities](https://claude.ai/admin-settings/capabilities)**.

---
## custom-data-retention-controls-for-enterprise-plans-375766dd05.md

# Configure custom data retention controls for Enterprise plans

March 16, 2026

This feature is available to Enterprise plan customers. To set custom retention periods for your organization, you must have either a Primary Owner or Owner role.

*This article is about our commercial products such as Claude for Work and the Anthropic API. For our consumer products such as Claude Free, Pro, Max and when accounts from those plans use Claude Code, see **[here](https://privacy.claude.com/en/collections/10663362-consumers)**.*

## How data retention works

Data retention is based on the last observed activity:

- **For chats:** Retention period starts from the time of the last message in the conversation.

- **For projects:** Retention period starts from the time the project was last updated (this includes chat creation or project knowledge base modifications).

- Note that your custom data retention periods set for projects will supersede your custom retention periods for any chats.

The minimum retention period is 30 days, and each month is counted as 30 days. For example, a three-month retention period equals 90 days.

## What gets deleted

When data reaches the end of its retention period:

- **For chats:** All chats (including chats within projects) and any artifacts within those chats will be deleted.

- **For projects:** All projects will be deleted, including any chats and artifacts within those projects.

## Important considerations

- Deletion occurs at midnight UTC on the scheduled day.

- By default, data is retained indefinitely unless a custom retention period is set.

- When you modify retention settings, any data that falls outside the new retention period will be deleted immediately upon saving.

- Data past its retention period will be permanently deleted and cannot be recovered.

## Setting up data retention

## To set custom retention periods:

1. Log in to your Owner Enterprise plan account.

2. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls)**.

3. Set your desired retention period (minimum 30 days).

4. Save your changes.

## Example retention calculation

If a conversation’s last message is at 3PM UTC on March 1 with a 30-day retention period, the deletion will occur at midnight UTC on March 31.

## Monitoring retention-related activities

---
## custom-data-retention-controls-for-enterprise-plans.md

4. Configure custom data retention controls for Enterprise plans

# Configure custom data retention controls for Enterprise plans

This feature is available to Enterprise plan customers. To set custom retention periods for your organization, you must have either a Primary Owner or Owner role.

*This article is about our commercial products such as Claude for Work and the Anthropic API. For our consumer products such as Claude Free, Pro, Max and when accounts from those plans use Claude Code, see **[here](https://privacy.claude.com/en/collections/10663362-consumers)**.*

## How data retention works

Data retention is based on the last observed activity:

- **For chats:** Retention period starts from the time of the last message in the conversation.

- **For projects:** Retention period starts from the time the project was last updated (this includes chat creation or project knowledge base modifications).

- Note that your custom data retention periods set for projects will supersede your custom retention periods for any chats.

The minimum retention period is 30 days, and each month is counted as 30 days. For example, a three-month retention period equals 90 days.

## What gets deleted

When data reaches the end of its retention period:

- **For chats:** All chats (including chats within projects) and any artifacts within those chats will be deleted.

- **For projects:** All projects will be deleted, including any chats and artifacts within those projects.

## Important considerations

- Deletion occurs at midnight UTC on the scheduled day.

- By default, data is retained indefinitely unless a custom retention period is set.

- When you modify retention settings, any data that falls outside the new retention period will be deleted immediately upon saving.

- Data past its retention period will be permanently deleted and cannot be recovered.

## Setting up data retention

## To set custom retention periods:

1. Log in to your Owner Enterprise plan account.

2. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls)**.

3. Set your desired retention period (minimum 30 days).

4. Save your changes.

## Example retention calculation

If a conversation’s last message is at 3PM UTC on March 1 with a 30-day retention period, the deletion will occur at midnight UTC on March 31.

## Monitoring retention-related activities

---
## data-usage.md

> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Data usage

> Learn about Anthropic's data usage policies for Claude

## Data policies

### Data training policy

**Consumer users (Free, Pro, and Max plans)**:
We give you the choice to allow your data to be used to improve future Claude models. We will train new models using data from Free, Pro, and Max accounts when this setting is on (including when you use Claude Code from these accounts).

**Commercial users**: (Team and Enterprise plans, API, 3rd-party platforms, and Claude Gov) maintain existing policies: Anthropic does not train generative models using code or prompts sent to Claude Code under commercial terms, unless the customer has chosen to provide their data to us for model improvement (for example, the [Developer Partner Program](https://support.claude.com/en/articles/11174108-about-the-development-partner-program)).

### Development Partner Program

If you explicitly opt in to methods to provide us with materials to train on, such as via the [Development Partner Program](https://support.claude.com/en/articles/11174108-about-the-development-partner-program), we may use those materials provided to train our models. An organization admin can expressly opt-in to the Development Partner Program for their organization. Note that this program is available only for Anthropic first-party API, and not for Bedrock or Vertex users.

### Feedback using the `/bug` command

If you choose to send us feedback about Claude Code using the `/bug` command, we may use your feedback to improve our products and services. Transcripts shared via `/bug` are retained for 5 years.

### Session quality surveys

When you see the "How is Claude doing this session?" prompt in Claude Code, responding to this survey (including selecting "Dismiss"), only your numeric rating (1, 2, 3, or dismiss) is recorded. We do not collect or store any conversation transcripts, inputs, outputs, or other session data as part of this survey. Unlike thumbs up/down feedback or `/bug` reports, this session quality survey is a simple product satisfaction metric. Your responses to this survey do not impact your data training preferences and cannot be used to train our AI models.

### Data retention

Anthropic retains Claude Code data based on your account type and preferences.

**Consumer users (Free, Pro, and Max plans)**:

* Users who allow data use for model improvement: 5-year retention period to support model development and safety improvements
* Users who don't allow data use for model improvement: 30-day retention period
* Privacy settings can be changed at any time at [claude.ai/settings/data-privacy-controls](https://claude.ai/settings/data-privacy-controls).

**Commercial users (Team, Enterprise, and API)**:

* Standard: 30-day retention period
* Zero data retention: Available with appropriately configured API keys - Claude Code will not retain chat transcripts on servers
* Local caching: Claude Code clients may store sessions locally for up to 30 days to enable session resumption (configurable)

Learn more about data retention practices in our [Privacy Center](https://privacy.anthropic.com/).

For full details, please review our [Commercial Terms of Service](https://www.anthropic.com/legal/commercial-terms) (for Team, Enterprise, and API users) or [Consumer Terms](https://www.anthropic.com/legal/consumer-terms) (for Free, Pro, and Max users) and [Privacy Policy](https://www.anthropic.com/legal/privacy).

## Data access

For all first party users, you can learn more about what data is logged for [local Claude Code](#local-claude-code-data-flow-and-dependencies) and [remote Claude Code](#cloud-execution-data-flow-and-dependencies). Note for remote Claude Code, Claude accesses the repository where you initiate your Claude Code session. Claude does not access repositories that you have connected but have not started a session in.

## Local Claude Code: Data flow and dependencies

The diagram below shows how Claude Code connects to external services during installation and normal operation. Solid lines indicate required connections, while dashed lines represent optional or user-initiated data flows.

Claude Code is installed from [NPM](https://www.npmjs.com/package/@anthropic-ai/claude-code). Claude Code runs locally. In order to interact with the LLM, Claude Code sends data over the network. This data includes all user prompts and model outputs. The data is encrypted in transit via TLS and is not encrypted at rest. Claude Code is compatible with most popular VPNs and LLM proxies.

Claude Code is built on Anthropic's APIs. For details regarding our API's security controls, including our API logging procedures, please refer to compliance artifacts offered in the [Anthropic Trust Center](https://trust.anthropic.com).

### Cloud execution: Data flow and dependencies

When using [Claude Code on the web](../02-Claude-Code-CLI/claude-code-on-the-web-69d53821d4.md), sessions run in Anthropic-managed virtual machines instead of locally. In cloud environments:

* **Code and data storage:** Your repository is cloned to an isolated VM. Code and session data are subject to the retention and usage policies for your account type (see Data retention section above)
* **Credentials:** GitHub authentication is handled through a secure proxy; your GitHub credentials never enter the sandbox
* **Network traffic:** All outbound traffic goes through a security proxy for audit logging and abuse prevention
* **Session data:** Prompts, code changes, and outputs follow the same data policies as local Claude Code usage

For security details about cloud execution, see [Security](/en/security#cloud-execution-security).

## Telemetry services

Claude Code connects from users' machines to the Statsig service to log operational metrics such as latency, reliability, and usage patterns. This logging does not include any code or file paths. Data is encrypted in transit using TLS and at rest using 256-bit AES encryption. Read more in the [Statsig security documentation](https://www.statsig.com/trust/security). To opt out of Statsig telemetry, set the `DISABLE_TELEMETRY` environment variable.

Claude Code connects from users' machines to Sentry for operational error logging. The data is encrypted in transit using TLS and at rest using 256-bit AES encryption. Read more in the [Sentry security documentation](https://sentry.io/security/). To opt out of error logging, set the `DISABLE_ERROR_REPORTING` environment variable.

When users run the `/bug` command, a copy of their full conversation history including code is sent to Anthropic. The data is encrypted in transit and at rest. Optionally, a Github issue is created in our public repository. To opt out of bug reporting, set the `DISABLE_BUG_COMMAND` environment variable.

## Default behaviors by API provider

By default, we disable all non-essential traffic (including error reporting, telemetry, and bug reporting functionality) when using Bedrock or Vertex. You can also opt out of all of these at once by setting the `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` environment variable. Here are the full default behaviors:

| Service | Claude API | Vertex API | Bedrock API |
| ------------------------------- | -------------------------------------------------------- | ----------------------------------------------------- | ------------------------------------------------------ |
| **Statsig (Metrics)** | Default on. `DISABLE_TELEMETRY=1` to disable. | Default off. `CLAUDE_CODE_USE_VERTEX` must be 1. | Default off. `CLAUDE_CODE_USE_BEDROCK` must be 1. |
| **Sentry (Errors)** | Default on. `DISABLE_ERROR_REPORTING=1` to disable. | Default off. `CLAUDE_CODE_USE_VERTEX` must be 1. | Default off. `CLAUDE_CODE_USE_BEDROCK` must be 1. |
| **Claude API (`/bug` reports)** | Default on. `DISABLE_BUG_COMMAND=1` to disable. | Default off. `CLAUDE_CODE_USE_VERTEX` must be 1. | Default off. `CLAUDE_CODE_USE_BEDROCK` must be 1. |

All environment variables can be checked into `settings.json` ([read more](../02-Claude-Code-CLI/claude-code-settings-claude-code-docs-d4420b4b52.md)).

---
## enterprise-plan-claude.md

# Claude Enterprise

Securely connect Claude to your company knowledge and give every team access to trusted AI. Designed for large organizations and enterprise-scale challenges. [Explore features](/pricing#team-enterprise-features)

Get Enterprise plan

[Get Enterprise plan](http://claude.ai/create/enterprise)

Get Enterprise plan

[Contact sales](/contact-sales)

89%

employee adoption, 800+ AI agents deployed, 10x app usage growth

65%

of team members use AI to increase productivity and effectiveness either "everyday" or "often"

98%

of team members surveyed reported to be satisfied or very satisfied with Claude for Work

90%

reduction in work time for business proposals and bid responses

20%

weekly time saved with Claude assistance on analytical and operational tasks

[Prev](#)

0/5

## Tackle your most complex challenges

### Get work done faster

Cut project timelines from days to hours, with 25–100% productivity gains that free up employees for more strategic work.

### Expand what your teams can do

Give every department the tools they need to tackle complex challenges beyond their usual expertise.

### Scale your institutional knowledge

Turn your organization’s expertise into something every team can access, so quality stays consistent as you grow.

[Play video](#)

Play video

See how fully integrating Claude across their organization has revolutionized Quantium's workflows.

[Read more](../15-Claude-AI-Features/customer-story-quantium-claude.md)

[Prev](#)

## Transform how your teams work

Enable every employee to spark new ideas, achieve more, and collaborate better.

Projects

Connectors

Research

Artifacts

Claude Code

Active

### Turn everyone into an expert

Add text, code, and files to dedicated projects as context for your chats. Claude can reference large amounts of information for every task, including the equivalent of:

- Ten 30-minute sales transcripts
- 15 full financial reports
- 100K lines of code

### Connect to your most important tools

Access your databases, CRM systems, project management tools, and development environments through secure, standardized integrations. Claude gains deep context about your workflows and can take actions across every surface.

### Create research reports in minutes

Get comprehensive, cited reports from your internal data and the web. Claude conducts multiple searches that build on each other, automatically exploring different angles of your question.

### Bring ideas to life with artifacts

See and build upon Claude’s output in real-time using dynamic, collaborative workspaces. Create and refine reports, visualizations, prototypes, and more—with secure sharing across your organization.

## ╭───────────────────────────╮ │ │ │ ✶ Welcome to Claude Code │ │ │ ╰───────────────────────────╯ ██████╗██╗ █████╗ ██╗ ██╗██████╗ ███████╗ ██╔════╝██║ ██╔══██╗██║ ██║██╔══██╗██╔════╝ ██║ ██║ ███████║██║ ██║██║ ██║█████╗ ██║ ██║ ██╔══██║██║ ██║██║ ██║██╔══╝ ╚██████╗███████╗██║ ██║╚██████╔╝██████╔╝███████╗ ╚═════╝╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚══════╝ ██████╗ ██████╗ ██████╗ ███████╗ ██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██║ ██║ ██║██║ ██║█████╗ ██║ ██║ ██║██║ ██║██╔══╝ ╚██████╗╚██████╔╝██████╔╝███████╗ ╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝

Claude Code can now be used with your Claude subscription or billed based on API usage through your Console account.

``` welcome-terminal__ui-code

Select login method:
❯ 1. Claude account with subscription
Pro, Max, Team, or Enterprise
2. Anthropic Console account
API usage billing

```

Flibbertigibbetting…

### Code with AI right in your terminal

Transform development workflows with an AI agent that understands your entire codebase. Execute routine tasks, build features, and handle Git workflows through natural language commands, with integrations to your existing development tools.

## Deploy with confidence

Manage access with enterprise-grade controls, and rest assured that we don't train our models on your Claude for Work data.

Single sign-on (SSO) and domain capture

Role-based access with fine-grained permissioning

System for Cross-domain Identity Management (SCIM)

Protected company data

Audit logs

Data retention controls

Compliance API

Usage analytics

Spend controls

Self-serve seat management

HIPAA-ready offering available

Connectors

Connect to Jira, Confluence, and other Atlassian tools to manage issues, access documentation, track sprints, create tickets, update project status, and coordinate development workflows.

Learn more

[Learn more](https://support.atlassian.com/rovo/docs/getting-started-with-the-atlassian-remote-mcp-server/)

Learn more

Connectors

Manage Workers deployments, D1 databases, R2 storage, and KV stores directly through Claude.

Learn more

[Learn more](https://developers.cloudflare.com/agents/guides/remote-mcp-server/)

Learn more

Connectors

Manage customer conversations, access support tickets, retrieve customer profiles, analyze conversation patterns, and handle customer service workflows through Intercom’s messaging platform.

Learn more

[Learn more](https://developers.intercom.com/docs/guides/mcp)

Learn more

[Prev](#)

## Critical cross-functional work starts with Claude

Engineering

Marketing

Sales

Product Management

Human Resources

Legal

Active

Prompt

\> claude fix the authentication error in our login flow

I'll investigate the auth error. Let me look at the relevant files.

Examining auth-related files...

\* src/services/authService.js

\* src/components/Login.jsx

\* src/store/authSlice.js

Running the login flow...

Error detected: "401 Unauthorized: Token expired"

Root cause:

\* Token refresh mechanism not handling expired tokens correctly

\* Refresh token missing from request header

\* Improper error handling for 401 responses

Updating authService.js with proper refresh logic...

Updating request interceptor for 401 handling...

Testing the fix...

\* Login successful ✓

\* Token refresh working ✓

\* Proper redirection on expired tokens ✓

Authentication error fixed! The login flow now properly handles token expiration.

### Engineering

Explore Claude Code for Enterprise

[Explore Claude Code for Enterprise ](/product/claude-code/enterprise)

Explore Claude Code for Enterprise

Note

Interact with the data—hover and toggle views to uncover patterns

Prompt

Create a multi-line trend chart showing the performance of three key business metrics over the past 12 months: marketing campaign ROI (pink line), sales conversion rate (blue line), and market share growth (green line). Display clear trend intersections and mark significant performance changes with data points. Include a legend and show month-over-month progression.

Attachments

Quarterly Performance

1,283 lines

csv

Market Analysis

71 kb

json

Content is user-generated and unverified.

Customize

Content is user-generated and unverified.

### Marketing

- Interpret market trends and consumer behavior patterns
- Brainstorm multi-platform content items
- Develop marketing campaign strategies
- Create post campaign performance reports

Note

Interact with the data—hover and toggle views to uncover patterns

Prompt

Create a scatter plot matrix showing business performance vs opportunity analysis. Plot data points by Current Performance Score (x-axis, 0-100) vs Growth Opportunity Score (y-axis, 0-100). Include quadrant divisions with labels: "Optimize" (top-right), "Develop" (top-left), "Maintain" (bottom-right), "Divest" (bottom-left). Color code by business category and size points by revenue/impact potential.

Attachments

Quarterly Performance

977 lines

csv

Strategic Metrics

92 kb

json

Content is user-generated and unverified.

Customize

Content is user-generated and unverified.

### Sales

- Analyze sales calls to craft tailored account plans
- Develop objection handling strategies
- Build compelling and tailored pitches
- Interpret sales metrics and KPIs

Prompt

Based on the uploaded user feedback survey and analytics report, create a product requirements document for a new feature that addresses the main user pain points identified in the data. Include the product vision and measurable objectives, analysis of user feedback data, technical specifications and requirements, and key performance indicators and success metrics. Keep it concise and professional.

Attachments

User Feedback Results

2.1 mb

pdf

Product Analysis Dashboard

325 lines

csv

### Product requirements document: Unified dashboard feature

#### Product vision

Create a centralized dashboard that provides users with immediate access to their most critical account information, usage data, and billing details in a single, intuitive interface. This dashboard will reduce user frustration, decrease support tickets, and improve overall product satisfaction by addressing the top three pain points identified in user feedback.

#### Measurable objectives

##### Primary objectives

- Reduce average time to find account information from 156 seconds to under 30 seconds
- Decrease billing-related support tickets by 40% within 3 months of launch
- Improve user satisfaction score from 3.2 to 3.8 within 6 months
- Increase task completion rate from current 70% to 85%

##### Secondary objectives

- Reduce session duration variability by providing faster access to key information
- Improve feature discovery rate from 34% to 50%
- Decrease user churn rate by 15% through improved user experience

#### Analysis of user feedback data

##### Key pain points identified

###### Account information access (68% of users affected)

- Users require too many clicks to access basic account details
- Current navigation structure creates confusion and frustration
- Lack of centralized information view increases task completion time

###### Usage tracking visibility (52% of users affected)

- Users cannot easily monitor their monthly usage patterns
- Absence of trend analysis and limit visibility
- Poor understanding of consumption relative to plan limits

###### Billing clarity issues (43% of users affected)

- Complex billing information presentation
- Difficulty locating payment due dates and charge breakdowns
- Users struggle to understand what they're paying for

##### User segment analysis

**Power users (22%)**: Need advanced analytics and quick access to detailed metrics**Casual users (45%)**: Require simplified, clear presentation of essential information**New users (33%)**: Need intuitive interface with guided discovery of key features

##### Supporting analytics data

- Support tickets average 289 per reporting period, with billing and account access as top categories
- Mobile users (59% of sessions) experience more navigation difficulties
- Task completion rates remain consistently below 75% across all user segments

#### Technical specifications and requirements

##### Functional requirements

###### Dashboard layout

- Single-page interface accessible from main navigation
- Responsive design optimized for both mobile and web platforms
- Customizable widget arrangement based on user preferences and behavior

###### Account information widget

- Display current plan type and status
- Show account creation date and user profile summary
- Include quick access links to account settings and profile management

###### Usage tracking widget

- Real-time usage metrics with visual progress indicators
- Monthly and weekly trend charts
- Comparison to plan limits with percentage utilization
- Historical data view for previous 12 months

###### Billing information widget

- Current billing cycle information with next payment date
- Itemized charge breakdown for current month
- Payment history with downloadable invoices
- Quick payment method management

###### Quick actions panel

- One-click access to most frequent user tasks
- Contextual actions based on account status and usage patterns
- Integration with existing feature set without duplication

#### Technical implementation requirements

###### Performance standards

- Page load time under 2 seconds on mobile devices
- Real-time data refresh capability with 30-second update intervals
- Offline capability for cached essential information

###### Data integration

- Connect with existing user management system
- Integrate with billing and payment processing systems
- Link to usage tracking and analytics backend
- Maintain data consistency across all platform touchpoints

###### Security and privacy

- Implement role-based access controls for sensitive information
- Ensure compliance with data protection regulations
- Provide audit trail for all dashboard interactions
- Secure API endpoints with appropriate authentication

#### Platform compatibility

- Native mobile app integration (iOS and Android)
- Web browser compatibility (Chrome, Safari, Firefox, Edge)
- Tablet-optimized layout with touch-friendly interface
- API availability for potential third-party integrations

### Key performance indicators and success metrics

#### User experience metrics

- **Dashboard adoption rate**: Target 80% of active users within 60 days
- **Time to complete common tasks**: Reduce by 60% compared to current flow
- **User satisfaction score**: Increase from 3.2 to 3.8 (19% improvement)
- **Feature discovery rate**: Increase from 34% to 50%

#### Operational impact metrics

- **Support ticket reduction**: 40% decrease in account and billing related tickets
- **Task completion rate**: Increase from 70% to 85%
- **Session efficiency**: Reduce average session duration while maintaining engagement
- **Mobile experience improvement**: Achieve parity with web task completion rates

#### Business impact metrics

- **User retention**: Reduce churn rate by 15% within 6 months
- **User engagement**: Increase daily active user percentage by 12%
- **Customer lifetime value**: Improve through reduced support costs and increased satisfaction
- **New user onboarding**: Improve completion rate from 67% to 80%

#### Technical performance metrics

- **Page load time**: Maintain under 2 seconds across all devices
- **System reliability**: 99.5% uptime for dashboard functionality
- **Mobile crash rate**: Keep below 1% for dashboard-related crashes
- **API response time**: Average response under 200ms for dashboard data

### Success criteria and timeline

#### Phase 1 (weeks 1-4): foundation development

- Complete technical architecture and database integration
- Develop core dashboard framework with basic widgets
- Implement responsive design for mobile and web platforms

#### Phase 2 (weeks 5-8): feature implementation

- Build and integrate all dashboard widgets
- Implement customization capabilities
- Complete security and privacy compliance requirements

#### Phase 3 (weeks 9-10): testing and optimization

- Conduct comprehensive user acceptance testing
- Performance optimization and load testing
- Security audit and penetration testing

#### Phase 4 (weeks 11-12): launch and monitoring

- Gradual rollout to user segments starting with power users
- Monitor key performance indicators and user feedback
- Rapid iteration based on initial usage patterns

### Risk mitigation

#### Technical risks

- Performance degradation under high load: Implement caching and load balancing
- Data integration complexity: Establish fallback mechanisms and error handling
- Mobile platform inconsistencies: Extensive cross-platform testing protocols

#### User adoption risks

- Resistance to interface changes: Provide optional onboarding tour and help documentation
- Feature discoverability: Implement guided first-use experience
- Customization complexity: Start with smart defaults based on user behavior patterns

### Conclusion

The unified dashboard feature directly addresses the primary pain points identified in user feedback while supporting broader business objectives of improved user satisfaction and reduced operational costs. Success metrics are designed to validate both immediate user experience improvements and long-term business value creation.

### Product Management

- Define product vision and objectives
- Analyze user feedback and usage data
- Create product specifications and requirements documents
- Interpret product usage metrics and KPIs

Prompt

Based on the uploaded marketing performance report and company growth strategy, create a job posting for a Growth Marketing Manager position that addresses the performance gaps and growth objectives identified in the documentation.

Attachments

Company Growth Strategy 2024

582 kb

pdf

Marketing Performance Report Q1 2024

1.3 MB

pdf

### Growth Marketing Manager

FlowTech \| Full-time \| Remote/Hybrid

#### About FlowTech

FlowTech is a fast-growing SaaS company positioned for explosive growth in 2025. With \$12M in annual recurring revenue and 8,400 active customers, we're ready to double our revenue and expand internationally. Our platform has proven product-market fit in North America, and we're scaling through channel optimization, international expansion, and new customer segment penetration.

#### The opportunity

We're seeking a data-driven Growth Marketing Manager to join our team during a pivotal growth phase. You'll be responsible for optimizing our marketing performance, reducing customer acquisition costs, and driving our ambitious goal of acquiring 15,000 new customers in 2024. This role is critical to achieving our target of \$24M revenue and expanding into international markets.

#### What you’ll do

##### Performance optimization and channel management

- Optimize our paid social campaigns (Meta, LinkedIn) to reduce CAC from current \$204 and improve conversion rates from 1.8%
- Scale our top-performing Google Ads channel while maintaining current \$130 CAC efficiency
- Develop and execute strategies to improve trial-to-paid conversion rate from 33% to 45%
- Reallocate marketing budget from underperforming channels (webinars, partnerships) to high-ROI opportunities

##### International expansion leadership

- Launch and manage marketing campaigns in priority international markets (UK, Germany, Australia, Canada)
- Develop localized marketing materials and campaigns for international audiences
- Establish multi-currency pricing strategies and local payment method integration
- Collaborate with sales teams to provide time zone coverage for international prospects

##### Growth experimentation and optimization

- Implement and manage A/B testing programs across all marketing channels
- Optimize onboarding experience to reduce time-to-first-value from 14 days to 5 days
- Develop product-led growth initiatives including viral sharing and team invitation features
- Create segment-specific campaigns for SMB (10-500 employees) and Enterprise (25,000+ employees) markets

##### Analytics and attribution

- Implement comprehensive multi-touch attribution to reduce "direct/unknown" conversions from 23%
- Build dashboards and reporting systems to track key growth metrics (MRR growth, CAC, LTV)
- Conduct competitive analysis and market research to identify new growth opportunities
- Optimize customer acquisition funnel to improve overall conversion rates

#### What we’re looking for

##### Required experience

- 3-5 years of growth marketing experience at a B2B SaaS company
- Proven track record of managing \$500K+ annual marketing budgets
- Experience scaling companies from \$10M to \$25M+ ARR
- Strong analytical skills with proficiency in Google Analytics, Facebook Ads Manager, and marketing automation platforms

##### Technical skills

- Advanced knowledge of paid advertising platforms (Google Ads, Meta, LinkedIn)
- Experience with marketing automation tools (HubSpot, Marketo)
- Proficiency in analytics tools (Mixpanel, Segment, attribution platforms)
- Understanding of international marketing challenges and localization requirements

##### Growth marketing expertise

- Experience improving trial-to-paid conversion rates in SaaS environments
- Track record of reducing customer acquisition costs while scaling volume
- Knowledge of product-led growth strategies and implementation
- Experience with multi-touch attribution and complex customer journey optimization

##### International expansion experience

- Previous experience launching marketing campaigns in European and APAC markets
- Understanding of GDPR compliance and international data regulations
- Knowledge of local payment methods and currency considerations
- Experience with localization and cultural adaptation of marketing materials

#### Success metrics (first 12 months)

##### Performance improvements

- Reduce overall customer acquisition cost from \$171 to \$140
- Increase monthly customer acquisition from 950 to 1,200
- Improve trial-to-paid conversion rate from 33% to 45%
- Achieve LTV:CAC ratio above 8:1

##### Growth targets

- Generate \$6M ARR from international markets (25% of total revenue)
- Acquire 5,400 new customers through optimized channels
- Launch successful campaigns in 4 international markets
- Increase organic traffic growth by 150% year-over-year

##### Channel optimization

- Reduce paid social CAC by 30% while maintaining volume
- Scale Google Ads to deliver 36% of total new customers
- Launch and optimize new customer segments (SMB and Enterprise)
- Eliminate budget allocation to channels with CAC above \$300

#### What we offer

##### Compensation and benefits

- Competitive salary and meaningful equity stake in a fast-growing company
- Comprehensive health, dental, and vision insurance
- \$2,000 annual learning and development budget

##### Growth opportunities

- Direct impact on company growth during critical scaling phase
- Opportunity to build and lead a marketing team as we grow
- Work closely with CEO and executive team on strategic initiatives
- International travel opportunities for market expansion

##### Work environment

- Remote-first culture with optional hybrid work
- Flexible working hours with core collaboration time
- Modern marketing stack and tools budget
- Quarterly team meetups and annual company retreat

#### Ready to apply?

Send us your resume along with a brief cover letter addressing:

- Your experience reducing CAC while scaling customer acquisition
- Specific examples of international marketing campaigns you've launched
- Your approach to improving trial-to-paid conversion rates
- Why you're excited about FlowTech's growth opportunity

**Apply to:** [\[email protected\]](/cdn-cgi/l/email-protection#accfcddec9c9dedfeccac0c3dbd8c9cfc482cfc3c1)\
**Subject line:** Growth Marketing Manager - \[Your Name\]

—

FlowTech is an equal opportunity employer committed to diversity and inclusion. We welcome applications from all qualified candidates regardless of race, gender, age, religion, sexual orientation, or disability status.

### Human Resources

- Craft job descriptions and postings
- Create training modules and documentation
- Create employee development plans
- Interpret employee engagement results

Prompt

Summarize the key terms, obligations, risks, and important deadlines from the uploaded enterprise software license agreement and strategic partnership agreement documents. Focus on actionable items and potential concerns for our business.

Attachments

Strategic-Partnership-Agreement.pdf

1.02 mb

pdf

Enterprise-Partnership-Agreement.pdf

521 kb

pdf

### Contract summary analysis

#### Enterprise software license agreement (CloudTech Systems)

**Agreement Number:** ESA-2024-0847\
**Effective:** April 1, 2024 - March 31, 2029

##### Key financial terms

- Initial license fee: \$450,000 (due May 1, 2024)
- Annual maintenance: \$135,000 (increases 8% yearly, capped)
- Additional users: \$900 per user above 500-user limit
- Implementation services: \$75,000 (optional)
- Late payment penalty: 1.5% monthly interest

##### Primary obligations

- User limits: Maximum 500 named users across all locations
- Geographic restrictions: US, Canada, and EU territories only
- Security requirements: SOC 2 Type II compliance, AES-256 encryption, multi-factor authentication
- Quarterly reporting: Active users, geographic distribution, third-party integrations
- Breach notification: Must notify licensor within 24 hours of security incidents

##### Major restrictions and risks

- No reverse engineering or derivative works: Violation could result in immediate termination
- Cannot exceed 500 users without written consent: Automated tracking monitors usage
- Annual audit rights: If usage exceeds license by 5%+, pay 150% retroactive fees plus audit costs
- Automatic data transmission: Monthly usage data sent to licensor for compliance
- Limited liability cap: \$100,000 or 12 months of payments (whichever is greater)

##### Critical deadlines

- May 1, 2024: Initial payment due (\$450,000)
- April 1, 2025: First maintenance payment due (\$135,000)
- October 1, 2028: Non-renewal notice deadline (180 days before expiration)
- Monthly: Usage data automatically transmitted
- Quarterly: Manual usage reports required

#### Strategic partnership agreement (NetVantage Partners)

**Agreement Number:** SPA-2024-312\
**Effective:** May 15, 2024 - May 14, 2027

##### Revenue sharing structure

- Tier-based commissions: 15% (Bronze) to 25% (Gold) based on annual revenue
- New customer commissions: 25% Year 1, 15% Year 2, 10% Years 3+
- Expansion revenue: 20% upsells, 15% services, 10% training
- Payment terms: 45 days after month-end, \$25,000 quarterly minimum

##### Annual revenue commitments

- Year 1 (2024): \$750,000 minimum
- Year 2 (2025): \$1,500,000 minimum
- Year 3 (2026): \$2,250,000 minimum
- Penalty: Tier reduction or termination for missing targets by 25%+

##### Exclusivity grants

- Geographic: Exclusive rights in Germany, France, Australia, Singapore
- Vertical: Global exclusivity in manufacturing and logistics industries
- Competitive restrictions: Cannot partner with competitors during term

##### Our key obligations

- Dedicated resources: Partner account manager (Sarah Chen), monthly planning sessions
- Training investment: 40-hour initial program for 8 NetVantage staff, quarterly updates
- Marketing funding: \$75,000 annual co-marketing fund, 50/50 trade show costs up to \$40,000
- Lead sharing: Provide marketing qualified leads in partner territories

##### Partner obligations we depend on

- Lead generation: Minimum 100 marketing qualified leads per quarter
- Sales opportunities: Minimum 20 qualified opportunities per quarter
- Marketing events: Minimum 4 events per quarter (webinars, seminars, networking)
- Multilingual support: Local language capabilities in target markets

##### Major risks and concerns

- High minimum commitments: Aggressive revenue targets with significant annual increases
- Commission liability: Long-term payment obligations (up to 10 years per customer)
- Exclusivity constraints: Limited flexibility to work with other partners in key markets
- Performance dependency: Success heavily relies on partner's marketing and sales execution
- Attribution disputes: Revenue splitting methodology may create conflicts

##### Critical deadlines

- August 15, 2024: Q1 performance review
- May 15, 2025: Year 1 minimum revenue assessment (\$750,000)
- November 15, 2026: Renewal decision deadline (180 days notice required)
- Monthly: Commission calculations and payments due

#### Immediate action items

##### High priority (next 30 days)

- Verify CloudTech payment: Confirm \$450,000 initial license fee was paid by May 1, 2024
- Assess current user count: Determine proximity to 500-user limit to avoid overage fees
- Security compliance audit: Ensure SOC 2 Type II controls are implemented
- Partnership performance review: Evaluate Q2 2024 results against minimum targets

##### Medium priority (next 90 days)

- User growth planning: Budget for additional licenses if approaching 500-user limit
- Revenue tracking system: Implement commission calculation and attribution processes
- Market expansion strategy: Leverage exclusive territories effectively with NetVantage
- Compliance documentation: Prepare quarterly usage reports and security assessments

##### Long-term planning considerations

- Contract renewal strategy: Begin planning for 2027 partnership renewal 18 months early
- Alternative partner evaluation: Consider backup options in case NetVantage underperforms
- CloudTech alternative assessment: Evaluate market alternatives before 2029 renewal
- Revenue diversification: Reduce dependency on exclusive partnership territories

Key contacts for escalation

- CloudTech Systems: Michael Chen, Enterprise Sales Director
- NetVantage Partners: Marcus Williams, VP Business Development
- Internal: Sarah Chen, Partner Director

### Legal

- Summarize complex contracts and agreements
- Assist in drafting legal documents and templates
- Monitor regulatory changes across different jurisdictions
- Automate routine legal tasks and processes

## What customers are saying

“We didn't want off-the-shelf solutions – we wanted a strategic partnership with a provider who would understand our specific needs as an institutional investor.”

Read story

[Read story](../15-Claude-AI-Features/20-time-savings-with-claude-ai-nbim-claude.md)

Read story

Stian Kirkeberg, Head of AI and Machine Learning

“With Claude, we can condense data down to make sure we’re not missing anything. It gives our teams a high-level view while still allowing us to link directly to specific feedback sources. This makes our work more strategic and enables our teams to create higher impact work.”

Read story

[Read story](https://claude.com/customers/sourcegraph-claude-for-work)

Read story

Justin Dorfman, Open Source Community Manager

“Since adopting the Claude Code + Claude for Enterprise bundle, we’ve rolled it out to hundreds of developers, and it has quickly become our go-to pair programmer. Its coding assistance consistently outperforms other agents, delivering superior results and value every day.”

Artem Pikulin, Sr. Manager of Machine Learning Operations

“Claude Code and Claude have accelerated Altana’s development velocity by 2-10x, transforming how we build sophisticated AI/ML systems that facilitate multi-party collaboration on large-scale knowledge graphs of global supply chains. These tools democratize development—engineers work across disciplines and non-technical members contribute to complex systems. We’re taking on significantly more ambitious projects as a result.”

Peter Swartz, Co-founder and Chief Science Officer

“We’re a global FinTech business with omnichannel touchpoints in marketing and communications. Our global growth requires our marketing resources to expand in capacity and language capability. Claude’s excellent writing and transcreation capabilities have been a big enabler for us to scale globally and achieve higher ROI.”

Olga Pirog, Global Head of Data and AI Transformation

“Claude offers our team members a tool that feels like an extension of their work and expertise, allowing us to take on more complex tasks and deliver greater impact while ensuring GitLab’s IP remains private and protected.”

Taylor McCaslin, Product Lead for AI and ML Tech

“Deloitte is leading the way in the trustworthy use of Generative AI within enterprises. Our exploration of Claude for Work will help us reveal how this transformative technology can empower our workforce.”

Gina Schaefer, AI Managing Director and Alliance Leader

“Claude Team is transforming our way of working at North Highland. Claude is a truly exceptional writer that has helped our team complete content creation and analysis tasks up to 5x faster than before—turning what was once two weeks of writing and research into minutes of work.”

Luka Anic, Senior Director of Technical AI Program and Product Manager

“Claude has been an incredible virtual collaborator for Midjourney. We use Claude for everything from summarizing research papers, to doing Q&A with user feedback notes, to iterating on our moderation policies. We’re excited to keep working alongside Claude as we grow and explore new domains.”

Caleb Kruse, Chief of Staff

“Launching our \$100M Anthology Fund with Anthropic, we received thousands of AI startup applications. Claude enabled a streamlined evaluation process, reducing time spent matching applications to partners and allowing more effective engagement with founders.”

Tim Tully, Partner

[Prev](#)

0/5

## Choose your Enterprise plan

Get started now or discuss more options. [Explore features](/pricing#team-enterprise-features)

### Enterprise\
(self-serve)

Get started today. Includes Enterprise security and compliance, chat, Claude Code, Cowork, connectors, SSO, SCIM, audit logs, and more.

\$20

Per seat / month, billed annually.\
Usage is billed as you go at API rates, based on what your team uses.

Get Enterprise plan

[Get Enterprise plan](https://claude.ai/create/enterprise)

Get Enterprise plan

### Enterprise\
(sales-assisted)

Work with Anthropic’s sales team on your Enterprise deployment. Tailored terms, usage commitments, invoicing, product bundling, and HIPAA-ready offering available.

[Contact sales](/contact-sales)

Quiz

Which plan is right for you?

Let's find out

\*Annual commitment required. Minimum 20 seats. [Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Prices shown don’t include applicable tax.

## FAQ

### What is the Claude Enterprise plan?

Claude is a trusted, secure, and collaborative AI expert that integrates with organizational knowledge and workflows to support high-quality work. Claude enhances productivity and creativity across various business functions within an organization. The Enterprise plan is designed for organizations that require large knowledge uploads, enhanced security and user management, and an AI solution that scales across cross-functional teams in support of deep work.

### What’s included in the Enterprise plan?

The Claude Enterprise plan supports deep, cross-functional workflows and includes everything in the Claude Team plan in addition to the following new features:

- Enterprise-grade security features to ensure the safety and compliance of your organization’s data including single-sign on (SSO) and domain capture, audit logs, System for Cross-domain Identity Management (SCIM), custom data retention controls and role-based permissioning for fine-grained user management.
- Expanded context window that enables users to upload hundreds of sales transcripts, dozens of 100+ page documents and 100K lines of code.
- Increased usage, which means more messages with Claude.
- Native integrations with data sources like GitHub provide the ability for engineering teams to brainstorm alongside your codebase, iterate on new features, onboard engineers and debug issues.

### What security is in place for the Enterprise plan?

By default, we will not use your inputs or outputs to train our models. To find out more, or if you would like to know how to contact us regarding a privacy related topic, see our [Trust Center](https://trust.anthropic.com/).

The Enterprise plan offers critical security and data management components including single sign-on (SSO) and domain capture for secure user access and centralized provisioning control, audit logs that trace system activities for security and compliance monitoring, system for Cross-domain Identity Management (SCIM) to automate user provisioning and access controls, and role-based permissioning that assigns a single primary owner of a workspace for security and information management.

### What's Claude for Work?

Claude for Work is a comprehensive solution for organizations to securely use Claude for business purposes. Within Claude for Work, organizations can choose between our Team plan and Enterprise plan, which offer a spectrum of features and capacity based on your usage and security needs.

### How can I integrate Claude into my own products or services?

If you’re a developer looking to create user-facing experiences and new products with Claude, the Anthropic API is right for you. To learn more about different API plans, contact our sales team. To get started, [explore our developer docs](https://docs.claude.com/en/home).

[Prev](#)

---
## extra-usage-for-max-20x-plans.md

# Extra usage for paid Claude plans

This article explains how to enable and use extra usage on your paid Claude plan (Pro, Max 5x, or Max 20x), allowing you to continue working with Claude after reaching your plan’s usage limits by switching to pay-as-you-go pricing.

## What is extra usage?

Extra usage allows individuals subscribed to paid Claude plans (Pro, Max 5x, and Max 20x) to continue using Claude seamlessly after reaching their included usage limits. Instead of being blocked when you hit your session limits, you can switch to consumption-based pricing at standard API rates and continue your work without interruption.

**Note:** If you subscribed through one of the Claude mobile apps, you can only enable extra usage on the web version of Claude. You will need to add your payment method before enabling and purchasing extra usage on the web.

------------------------------------------------------------------------

## How extra usage works

When you reach your plan’s usage limit with extra usage enabled:

- You’ll see a notification that you’ve reached your session usage limit.

- If extra usage is enabled and you have funds available, you can choose to continue working.

- Your subsequent usage will be billed at standard API pricing rates.

- Your session limits reset every five hours as usual.

**Note:** Extra usage is charged separately from your paid Claude subscription and appears as additional charges on your bill.

------------------------------------------------------------------------

## Enabling extra usage

To enable extra usage on your paid Claude plan:

1. Navigate to [Settings \> Usage](https://claude.ai/settings/usage) in your Claude account.

2. Locate the **Extra usage** section.

3. Click "Enable" to turn on extra usage.

4. Set up your payment method if not already configured.

5. Configure your spending preferences.

6. Click “Adjust limit” to control costs with a monthly spending cap. You can also select “Set to unlimited” if you prefer no spending restrictions:

7. You’ll then need to prepay to cover usage beyond your plan limits. Click “Add funds,” enter the amount you want to purchase in the modal, then click “Purchase.”

8. You can also enable auto-reload to automatically make a purchase when your balance falls below a threshold you set:

**Note:** There is a daily redemption limit of \$2000.

------------------------------------------------------------------------

## Setting spending controls

Control your extra usage spending with:

- **Monthly spending cap:** Set a maximum amount you're willing to spend on extra usage each month.

- **Auto-reload settings:** Automatically purchase credits when your balance drops below a threshold.

- **Usage alerts:** Receive notifications when approaching your spending limits.

------------------------------------------------------------------------

## Extra usage pricing

Extra usage is billed at standard API rates; see our [pricing page](https://claude.com/pricing#api) for details.

------------------------------------------------------------------------

## Managing your extra usage

### Monitoring usage and costs

Track your extra usage through:

- **Usage dashboard:** View real-time consumption in [Settings \> Usage](https://claude.ai/settings/usage).

- **Current spending:** Monitor your month-to-date extra usage costs.

- **Usage history:** Review past consumption patterns to optimize future usage.

### Tips for cost-effective usage

To manage extra usage costs while maintaining productivity:

- **Choose efficient models:** Use our most efficient model - Haiku 4.5, or Sonnet 4.5 for most tasks. These provide excellent performance at lower token costs than Opus models.

- **Leverage your included usage first:** Plan intensive work sessions around your five-hour usage windows.

- **Start new conversations:** Begin fresh chats for new topics to minimize the size of your context window.

- **Use projects effectively:** Store frequently referenced documents in project knowledge instead of re-uploading.

- **Set appropriate limits:** Start with conservative spending caps and adjust based on your needs.

------------------------------------------------------------------------

## How extra usage works with other features

### Claude Code

Extra usage applies to both Claude conversations and Claude Code terminal usage. Your combined usage across both interfaces counts toward your limits.

### Research mode

When using Research mode, extra usage rates apply once you exceed your included Max 20X limits. Research sessions may consume tokens more quickly due to multiple searches and comprehensive analysis.

### Projects and files

Documents stored in project files count toward your context when used in conversations. Extra usage pricing applies to all tokens processed, including project content.

------------------------------------------------------------------------

## Frequently Asked Questions

### Can I disable extra usage after enabling it?

Yes, you can disable extra usage at any time through [Settings \> Usage](https://claude.ai/settings/usage). Once disabled, you'll only have access to your plan's included usage.

### How quickly do my regular usage limits reset?

Your plan’s included usage limit will reset every five hours once you reach it. Extra usage doesn’t affect this reset timing.

### I subscribed to a paid Claude plan on the App or Play store; how can I access extra usage?

If you purchased your paid plan through one of the Claude mobile apps, extra usage is only available if you enable and purchase it on the Claude web app. You will not be able to set up extra usage on the mobile app.

### Is extra usage available for all paid plan tiers?

Yes, extra usage is now available for all paid Claude plans, including Pro, Max 5x, and Max 20x plans.

### Can I track extra usage separately from my included usage?

Yes, the usage dashboard clearly distinguishes between your included plan usage limits and any extra usage consumption.

### Will I get a warning before switching to extra usage?

Yes, you’ll see a clear notification when approaching and reaching your included usage limits, with a confirmation that you’ll continue with extra usage.

### Why was I able to exceed my extra usage limit?

It's possible to slightly exceed your defined usage limit. Our system checks if you're within your limit before you're allowed to make a single request or send a message. Once the request is processed, we calculate your token consumption, which means you may bypass your limit with that request. Once this happens, any subsequent requests will be blocked.

### Does extra usage pricing differ from API pricing?

No, extra usage is billed at the same [standard API rates](https://claude.com/pricing#api) shown in the pricing table above.

---
## extra-usage-for-paid-claude-plans-32418755be.md

# Manage usage credits for paid Claude plans

May 18, 2026

This article explains how usage credits work on your paid Claude plan (Pro, Max 5x, or Max 20x), allowing you to continue working with Claude after reaching your plan's usage limits by switching to pay-as-you-go pricing.

## What are usage credits?

Usage credits allow individuals subscribed to paid Claude plans (Pro, Max 5x, and Max 20x) to continue using Claude seamlessly after reaching their included usage limits. Instead of being blocked when you hit your session limits, you can switch to consumption-based pricing at standard API rates and continue your work without interruption.

**Note:** If you subscribed through one of the Claude mobile apps, you can only enable usage credits on the web version of Claude. You will need to add your payment method before enabling and purchasing usage credits on the web.

------------------------------------------------------------------------

## How usage credits work

When you reach your plan’s usage limit with usage credits enabled:

- You’ll see a notification that you’ve reached your session usage limit.

- If usage credits are enabled and you have funds available, you can choose to continue working.

- Your subsequent usage will be billed at standard API pricing rates.

- Your session limits reset every five hours as usual.

**Note:** Usage credits are charged separately from your paid Claude subscription and appear as additional charges on your bill.

------------------------------------------------------------------------

## Enabling usage credits

To enable usage credits on your paid Claude plan:

1. Navigate to [**Settings \> Usage**](https://claude.ai/settings/usage) in your Claude account.

2. Locate the **Usage credits** section.

3. Click "Enable" to turn on usage credits.

4. Set up your payment method if not already configured.

5. Configure your spending preferences.

6. Click “Adjust limit” to control costs with a monthly spend limit. You can also select “Set to unlimited” if you prefer no spending restrictions.

7. You’ll then need to prepay to cover usage beyond your plan limits. Click “Add funds,” enter the amount you want to purchase in the modal, then click “Purchase.”

8. You can also enable auto-reload to automatically make a purchase when your balance falls below a threshold you set:

**Note:** There is a daily redemption limit of \$2000.

------------------------------------------------------------------------

## Set spend limits

Control your usage credit spending with:

- **Monthly spending cap:** Set a maximum amount you're willing to spend on usage credits each month.

- **Auto-reload settings:** Automatically add funds when your balance drops below a threshold.

- **Usage alerts:** Receive notifications when approaching your spend limits.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Managing your usage credits

### Monitoring usage and costs

Track your usage credits through:

- **Usage dashboard:** View real-time consumption in **[Settings \> Usage](https://claude.ai/settings/usage)**.

- **Current spending:** Monitor your month-to-date usage credit costs.

- **Usage history:** Review past consumption patterns to optimize future usage.

## Tips for cost-effective usage

To manage usage credit costs while maintaining productivity:

- **Choose efficient models:** Use our most efficient Haiku model, or the most recent Sonnet model for most tasks. These provide excellent performance at lower token costs than Opus models.

- **Use your plan’s included usage first:** Plan intensive work sessions around your five-hour usage windows.

- **Start new conversations:** Begin fresh chats for new topics to minimize the size of your context window.

- **Use projects effectively:** Store frequently referenced documents in project knowledge instead of re-uploading.

- **Set appropriate limits:** Start with conservative spending caps and adjust based on your needs.

------------------------------------------------------------------------

## How usage credits work with other features

### Claude Code

Usage credits apply to both Claude conversations and Claude Code terminal usage. Your combined usage across both interfaces counts toward your limits.

### Research mode

When using Research mode, usage credits apply once you exceed your plan's included limits. Research sessions may consume tokens more quickly due to multiple searches and comprehensive analysis.

### Projects and files

Documents stored in project files count toward your context when used in conversations. Usage credits apply to all tokens processed, including project content.

------------------------------------------------------------------------

## Frequently asked questions

### Can I disable usage credits after enabling them?

Yes, you can disable usage credits at any time through **[Settings \> Usage](https://claude.ai/settings/usage)**. Once disabled, you'll only have access to your plan's included usage.

### How quickly do my regular usage limits reset?

Your plan’s included usage limit will reset every five hours once you reach it. Usage credits don’t affect this reset timing.

### I subscribed to a paid Claude plan on the App or Play store; how can I access usage credits?

If you purchased your paid plan through one of the Claude mobile apps, usage credits are only available if you enable and purchase them on the Claude web app. You will not be able to set up usage credits on the mobile app.

### Can I track usage credits separately from my included usage?

Yes, the usage dashboard clearly distinguishes between your included plan usage limits and any usage credit consumption.

### Will I get a warning before switching to usage credits?

Yes, you’ll see a clear notification when approaching and reaching your included usage limits, with a confirmation that you’ll continue with usage credits.

---
## extra-usage-for-paid-claude-plans.md

# Extra usage for paid Claude plans

## What is extra usage?

------------------------------------------------------------------------

## How extra usage works

When you reach your plan’s usage limit with extra usage enabled:

- You’ll see a notification that you’ve reached your session usage limit.

- If extra usage is enabled and you have funds available, you can choose to continue working.

- Your subsequent usage will be billed at standard API pricing rates.

- Your session limits reset every five hours as usual.

**Note:** Extra usage is charged separately from your paid Claude subscription and appears as additional charges on your bill.

------------------------------------------------------------------------

## Enabling extra usage

To enable extra usage on your paid Claude plan:

1. Navigate to [Settings \> Usage](https://claude.ai/settings/usage) in your Claude account.

2. Locate the **Extra usage** section.

3. Click "Enable" to turn on extra usage.

4. Set up your payment method if not already configured.

5. Configure your spending preferences.

6. Click “Adjust limit” to control costs with a monthly spending cap. You can also select “Set to unlimited” if you prefer no spending restrictions:

7. You’ll then need to prepay to cover usage beyond your plan limits. Click “Add funds,” enter the amount you want to purchase in the modal, then click “Purchase.”

8. You can also enable auto-reload to automatically make a purchase when your balance falls below a threshold you set:

**Note:** There is a daily redemption limit of \$2000.

------------------------------------------------------------------------

## Setting spending controls

Control your extra usage spending with:

- **Monthly spending cap:** Set a maximum amount you're willing to spend on extra usage each month.

- **Auto-reload settings:** Automatically purchase credits when your balance drops below a threshold.

- **Usage alerts:** Receive notifications when approaching your spending limits.

------------------------------------------------------------------------

## Extra usage pricing

Extra usage is billed at standard API rates; see our [pricing page](https://claude.com/pricing#api) for details.

------------------------------------------------------------------------

## Managing your extra usage

### Monitoring usage and costs

Track your extra usage through:

- **Usage dashboard:** View real-time consumption in [Settings \> Usage](https://claude.ai/settings/usage).

- **Current spending:** Monitor your month-to-date extra usage costs.

- **Usage history:** Review past consumption patterns to optimize future usage.

### Tips for cost-effective usage

To manage extra usage costs while maintaining productivity:

- **Choose efficient models:** Use our most efficient model - Haiku 4.5, or Sonnet 4.5 for most tasks. These provide excellent performance at lower token costs than Opus models.

- **Leverage your included usage first:** Plan intensive work sessions around your five-hour usage windows.

- **Start new conversations:** Begin fresh chats for new topics to minimize the size of your context window.

- **Use projects effectively:** Store frequently referenced documents in project knowledge instead of re-uploading.

- **Set appropriate limits:** Start with conservative spending caps and adjust based on your needs.

------------------------------------------------------------------------

## How extra usage works with other features

### Claude Code

Extra usage applies to both Claude conversations and Claude Code terminal usage. Your combined usage across both interfaces counts toward your limits.

### Research mode

When using Research mode, extra usage rates apply once you exceed your included Max 20X limits. Research sessions may consume tokens more quickly due to multiple searches and comprehensive analysis.

### Projects and files

Documents stored in project files count toward your context when used in conversations. Extra usage pricing applies to all tokens processed, including project content.

------------------------------------------------------------------------

## Frequently Asked Questions

### Can I disable extra usage after enabling it?

Yes, you can disable extra usage at any time through [Settings \> Usage](https://claude.ai/settings/usage). Once disabled, you'll only have access to your plan's included usage.

### How quickly do my regular usage limits reset?

Your plan’s included usage limit will reset every five hours once you reach it. Extra usage doesn’t affect this reset timing.

### I subscribed to a paid Claude plan on the App or Play store; how can I access extra usage?

### Is extra usage available for all paid plan tiers?

Yes, extra usage is now available for all paid Claude plans, including Pro, Max 5x, and Max 20x plans.

### Can I track extra usage separately from my included usage?

Yes, the usage dashboard clearly distinguishes between your included plan usage limits and any extra usage consumption.

### Will I get a warning before switching to extra usage?

Yes, you’ll see a clear notification when approaching and reaching your included usage limits, with a confirmation that you’ll continue with extra usage.

### Why was I able to exceed my extra usage limit?

### Does extra usage pricing differ from API pricing?

No, extra usage is billed at the same [standard API rates](https://claude.com/pricing#api) shown in the pricing table above.

---
## extra-usage-for-team-and-enterprise-plans-a7d190dd65.md

# Manage usage credits for Team and seat-based Enterprise plans

May 18, 2026

This article explains how Team and seat-based Enterprise plan Owners and Primary Owners can purchase usage credits, allowing members to continue using Claude, Claude Cowork, and Claude Code after reaching usage limits for their assigned seat.

## What are usage credits?

Usage credits allow Team and seat-based Enterprise plan members on Standard and Premium seats to continue working with Claude, Cowork, and Claude Code after reaching their included usage limits. Instead of being blocked upon hitting limits, members can keep working without interruption.

**Important:** Usage credits don't apply to current usage-based Enterprise plans. On those plans, there's no included usage allowance to run out of—all usage is billed at API rates from the first token. For details on how usage and spend limits work on usage-based plans, see **[How am I billed for my Enterprise plan?](https://support.claude.com/en/articles/11526368-how-am-i-billed-for-my-enterprise-plan)**

------------------------------------------------------------------------

## How usage credits work

After an organization Owner or Primary Owner configures your account for usage credits, you'll start using them as soon as you reach your seat's usage limit. Your subsequent usage will be billed at standard API pricing rates as you continue working.

**For Team plans:** Owners can pre-purchase usage credits that they can control using spend limits.

**For seat-based Enterprise plans:** Usage credits are billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable usage credits

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to pay for usage credits.

5. Next, you'll see the option to enable auto-reload; choose "Reload when balance reaches" and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable usage credits for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to usage credits once they're enabled?

Once an organization owner has enabled usage credits:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your usage credit consumption will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

**Note:** If you're on an Enterprise plan, you can also set spend limits at the group level. See **[Manage groups and group spend limits on Enterprise plans](https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans)**.

### Spend limits

After navigating to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)** and enabling this feature, Owners can set a monthly spend limit on the entire organization's usage credits. Setting a limit here controls total usage credit spend across your whole organization, regardless of individual or seat limits.

The **Usage and spend limits** section will show the current limit (if any) or **Unlimited**. Clicking on "Adjust limit" opens a modal where you can either input an amount and click "Set spend limit," or click "Set to unlimited" to remove the organization-wide monthly spend limit.

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Owners and Primary Owners on **seat-based Enterprise plans only** can set spend limits that apply to all users within a specific seat tier.

Select the "By group" tab to see **Standard seats** and **Premium seats** groups. Click the "..." icon next to the current limit, then "Edit limit." This opens a modal where you can either select "Set dollar amount" and input an amount, or click "Unlimited" to remove the limit for that seat type. Click "Set limit" to save your changes.

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the "..." button next to the user, then "Edit limit."

Enter the amount and click "Set limit." Alternatively, selecting "Set to unlimited" will remove that member's monthly spend limit (they will still be subject to any organization or seat-level spend limits).

This allows owners fine control over usage credits, so you can set limits for different members based on their roles or individual needs. Once a user reaches their defined spend limit, this will automatically pause their usage credits until the end of the month. They will need to wait for their usage limits to reset before using Claude again.

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members' usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Request usage credits for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request usage credits" link upon hitting their included usage limit.

Click this to send a request to organization Admins to either switch you to a Premium seat (if you're currently assigned to a Standard seat) or enable usage credits for your user account. This will change to **Request sent to admin** after clicking it, indicating that you submitted a request for a seat tier increase or usage credits to an organization Admin.

Admins and Owners can review these requests in **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**. Clicking into "Review requests" will open a modal where each requester is listed, along with their current seat, and the time they asked for more usage. Click "Increase limit" next to each request you want to approve. Admins and above will also receive a daily email including all your organization's outstanding requests.

### Disable usage credit requests

If you want to prevent users from submitting requests for usage credits, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Usage credit requests**.

3. Toggle it off.

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my spend limit?

If your account is configured for usage credits and you exceed your set spend limit, you won't be able to use Claude, Cowork, or Claude Code again until the next billing period, or until your limits are adjusted.

### Why was I able to exceed my spend limit?

It's possible to slightly exceed your defined spend limit. Our system checks if you're within your limit before you're allowed to make a single request or send a message. Once the request is processed, we calculate your token consumption, which means you may bypass your limit with that request. Once this happens, any subsequent requests will be blocked.

### Can usage credits be disabled completely?

Yes, Owners and Primary Owners can choose to disable usage credits entirely, which means that members of the organization will be unable to continue working once they reach their usage limits and will need to wait for them to reset.

---
## extra-usage-for-team-and-enterprise-plans.md

4. Manage extra usage for Team and seat-based Enterprise plans

# Manage extra usage for Team and seat-based Enterprise plans

This article explains how Team and seat-based Enterprise plan Owners and Primary Owners can purchase extra usage, allowing members to continue using Claude, Cowork, and Claude Code after reaching usage limits for their assigned seat.

## What is extra usage?

Enabling extra usage allows Team and seat-based Enterprise plan members on Standard and Premium seats to continue working with Claude, Cowork, and Claude Code after reaching their included usage limits. Instead of being blocked upon hitting limits, members can keep working without interruption by purchasing extra usage.

**Important:** Extra usage doesn't apply to current usage-based Enterprise plans. On those plans, there's no included usage allowance to run out of—all usage is billed at API rates from the first token. For details on how usage and spend limits work on usage-based plans, see **[How am I billed for my Enterprise plan?](how-am-i-billed-for-my-enterprise-plan.md)**

------------------------------------------------------------------------

## How extra usage works

After an organization Owner or Primary Owner configures your account for extra usage, you’ll start using this as soon as you reach your seat's usage limit. Your subsequent usage will be billed at standard API pricing rates as you continue working.

**For Team plans:** Owners can pre-purchase extra usage that they can control using spend limits.

**For seat-based Enterprise plans:** Extra usage is billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable extra usage

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click “Enable” in **Extra usage** to turn this on for your organization.

4. You’ll be prompted to pay for extra usage.

5. Next, you’ll see the option to enable auto-reload; choose “Reload when balance reaches” and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable extra usage for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click “Enable” in **Extra usage** to turn this on for your organization.

4. You’ll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to extra usage once it's enabled?

Once an organization owner has enabled extra usage:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your extra usage will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

### Spend limits

After navigating to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)** and enabling this feature, Owners can set a monthly spend limit on the entire organization's extra usage. Setting a limit here controls total extra usage spend across your whole organization, regardless of individual or seat limits.

The **Usage and spend limits** section will show the current limit (if any) or **Unlimited**. Clicking on “Adjust limit” opens a modal where you can either input an amount and click “Set spend limit,” or click “Set to unlimited” to remove the organization-wide monthly spend limit:

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Owners and Primary Owners on **seat-based Enterprise plans only** can set spend limits that apply to all users within a specific seat tier. Clicking the pencil icon next to the current limit for either Standard or Premium users allows you to edit this:

Clicking that icon opens a modal where you can either input an amount and click “Set limit,” or click “Set to unlimited” to remove the limit for that seat type:

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the “...” button next to the user, then “Edit limit”:

Enter the amount and click “Set limit.” Alternatively, selecting “Set to unlimited” will remove that member’s monthly spend limit (they will still be subject to any organization or seat-level spend limits).

This allows owners fine control over extra usage, so you can set limits for different members based on their roles or individual needs. Once a user reaches their defined spend limit, this will automatically pause their extra usage until the end of the month. They will need to wait for their usage limits to reset before using Claude again.

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members’ usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Extra usage pricing

Extra usage is billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

------------------------------------------------------------------------

## Request extra usage for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request extra usage" link upon hitting their included usage limit:

Click this to send a request to organization Admins to either switch you to a Premium seat (if you're currently assigned to a Standard seat) or enable extra usage for your user account. This will change to **Request sent to admin** after clicking it, indicating that you submitted a request for a seat tier increase or extra usage to an organization Admin.

Admins and Owners can review these requests in **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**. Clicking into "Review requests" will open a modal where each requester is listed, along with their current seat, and the time they asked for more usage. Click "Increase limit" next to each request you want to approve. Admins and above will also receive a daily email including all your organization's outstanding requests.

### Disable extra usage requests

If you want to prevent users from submitting requests for extra usage, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Extra usage requests**.

3. Toggle it off:

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my extra usage limit?

If your account is configured for extra usage and you exceed your set spend limit, you won’t be able to use Claude, Cowork, or Claude Code again until the next billing period, or until your limits are adjusted.

### Why was I able to exceed my extra usage limit?

### Does extra usage apply to Claude, Cowork, and Claude Code?

Yes, extra usage applies to Claude, Cowork, and Claude Code.

### Can extra usage be disabled completely?

Yes, Owners and Primary Owners can choose to disable extra usage entirely, which means that members of the organization will be unable to continue working once they reach their usage limits and will need to wait for them to reset.\

---
## extra-usage-for-team-and-seat-based-enterprise-plans-9f8655d599.md

# Manage usage credits for Team and seat-based Enterprise plans

May 18, 2026

## What are usage credits?

------------------------------------------------------------------------

## How usage credits work

**For Team plans:** Owners can pre-purchase usage credits that they can control using spend limits.

**For seat-based Enterprise plans:** Usage credits are billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable usage credits

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to pay for usage credits.

5. Next, you'll see the option to enable auto-reload; choose "Reload when balance reaches" and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable usage credits for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to usage credits once they're enabled?

Once an organization owner has enabled usage credits:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your usage credit consumption will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

### Spend limits

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Owners and Primary Owners on **seat-based Enterprise plans only** can set spend limits that apply to all users within a specific seat tier.

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the "..." button next to the user, then "Edit limit."

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members' usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Request usage credits for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request usage credits" link upon hitting their included usage limit.

### Disable usage credit requests

If you want to prevent users from submitting requests for usage credits, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Usage credit requests**.

3. Toggle it off.

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my spend limit?

### Why was I able to exceed my spend limit?

### Can usage credits be disabled completely?

---
## extra-usage-for-team-and-seat-based-enterprise-plans.md

4. Manage extra usage for Team and seat-based Enterprise plans

# Manage extra usage for Team and seat-based Enterprise plans

## What is extra usage?

------------------------------------------------------------------------

## How extra usage works

**For Team plans:** Owners can pre-purchase extra usage that they can control using spend limits.

**For seat-based Enterprise plans:** Extra usage is billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable extra usage

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click “Enable” in **Extra usage** to turn this on for your organization.

4. You’ll be prompted to pay for extra usage.

5. Next, you’ll see the option to enable auto-reload; choose “Reload when balance reaches” and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable extra usage for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click “Enable” in **Extra usage** to turn this on for your organization.

4. You’ll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to extra usage once it's enabled?

Once an organization owner has enabled extra usage:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your extra usage will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

### Spend limits

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Clicking that icon opens a modal where you can either input an amount and click “Set limit,” or click “Set to unlimited” to remove the limit for that seat type:

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the “...” button next to the user, then “Edit limit”:

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members’ usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Extra usage pricing

Extra usage is billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

------------------------------------------------------------------------

## Request extra usage for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request extra usage" link upon hitting their included usage limit:

### Disable extra usage requests

If you want to prevent users from submitting requests for extra usage, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Extra usage requests**.

3. Toggle it off:

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my extra usage limit?

### Why was I able to exceed my extra usage limit?

### Does extra usage apply to Claude, Cowork, and Claude Code?

Yes, extra usage applies to Claude, Cowork, and Claude Code.

### Can extra usage be disabled completely?

---
## get-started-with-the-team-plan-e4a445d9ae.md

# Get started with the Team plan

## Requirements to sign up for a Team plan

- The account creator must use a business email address. Public domains like @gmail.com, @yahoo.com, and @hotmail.com aren't allowed—but you can **[add them as permitted domains](https://support.claude.com/en/articles/13325567-account-management-faqs#h_b54c41c86c)** for other members of your organization.

- All team members must have an email address with one of your organization's allowed email domains to be invited to the account.

- During sign-up, you can choose between monthly or annual billing options.

- Refer to this article for more information: **[How is my Team plan bill calculated?](https://support.claude.com/en/articles/9267289-how-is-my-team-plan-bill-calculated)**

- Team plans require a minimum of two members and are not intended for individual use.

## Create a new Team organization

To get started with the Team plan, navigate to **[claude.ai/login](http://claude.ai/login)** and enter your work email address. Follow the onboarding prompts and select the Team plan.

## Upgrade from an individual plan to the Team plan

If you already have an individual Free, Pro, or Max account associated with your work email and wish to create a Team plan, sign into your individual account, then visit **[claude.ai/upgrade](http://claude.ai/upgrade)**. Follow the steps to create your Team.

Upgrading to the Team plan creates a new Claude organization. Your individual Free, Pro, or Max account remains separate, and you can toggle between the two by clicking your initials or name in the lower left and selecting the account you'd like to access.

If you'd rather use a single account, you can migrate your personal account into your Team organization. Migration moves your chats, projects, files, and memory into the organization's workspace, and your paid individual subscription is canceled automatically as part of the migration (subscriptions purchased through the Apple App Store must be canceled separately first). To get started, go to **[Settings \> Account](https://claude.ai/settings/account)**, or see **[Move your personal Claude account to a Team or Enterprise organization](https://support.claude.com/en/articles/9267400-move-your-personal-claude-account-to-a-team-or-enterprise-organization)** for details.

**Note:** Once content has been moved into an organization, it can't be moved back to a personal account.

---
## get-started-with-the-team-plan.md

# Get started with the Team plan

## Requirements to sign up for a Team plan

- The account creator must use a business email address. Public domains like @gmail.com, @yahoo.com, and @hotmail.com aren't allowed—but you can **[add them as permitted domains](../21-Account-Support/account-management-faqs.md#h_b54c41c86c)** for other members of your organization.

- All team members must have an email address with one of your organization's allowed email domains to be invited to the account.

- During sign-up, you can choose between monthly or annual billing options.

- Refer to this article for more information: **[How is my Team plan bill calculated?](how-is-my-team-plan-bill-calculated.md)**

- Team plans require a minimum of five members and are not intended for individual use.

## Create a new Team organization

To get started with the Team plan, navigate to **[claude.ai/login](http://claude.ai/login)** and enter your work email address. Follow the onboarding prompts and select the Team plan.

## Upgrade from an individual plan to the Team plan

If you already have a free or paid Claude account associated with your work email and wish to create a Team plan, sign into your account, then visit **[claude.ai/upgrade](http://claude.ai/upgrade)**. Follow the steps to create your Team.

- Upgrading to the Team plan will create a new Claude organization, and your individual free or paid account (Pro or Max) will remain separate. You can toggle between them by clicking your initials or name in the lower left, then selecting the account you'd like to access.

- Team plan organizations are separate from free and paid individual Claude accounts. Data cannot be transferred between the separate instances.

- If you only want to use your Team plan after upgrading, you'll need to cancel your paid subscription and/or delete your free or paid individual Claude account separately.

- **[How do I cancel my paid Claude subscription?](https://support.claude.com/en/articles/8325617-how-do-i-cancel-my-paid-claude-subscription)**

- **[How can I delete my Claude account?](../21-Account-Support/how-can-i-delete-my-claude-account.md)**

---
## hipaa-ready-enterprise-plans-3abc9d3ee3.md

# HIPAA-ready Enterprise plans

This feature is available for Enterprise plans only (both self-serve and sales-assisted).

We offer a HIPAA-ready version of Claude that is available for organizations on Enterprise plans that choose to process protected health information (PHI) through Claude. This article explains what the offering includes, which features are available, and how to get started.

## Overview

The HIPAA-ready Enterprise offering is designed for healthcare providers, health plans, healthcare data processors, and their business associates who are subject to HIPAA requirements. This offering includes a Business Associate Agreement (BAA), functionality, and safeguards designed to support an organization's HIPAA compliance requirements.

## Who is this for?

This offering is designed for HIPAA-covered entities and their business associates, including:

- Healthcare providers (e.g., hospitals, clinics, physicians)

- Health plans and insurers

- Healthcare data processors

- Business associates that handle PHI on behalf of covered entities

- Other HIPAA regulated entities

If you're unsure whether your organization benefits from a HIPAA-ready product, ask yourself: will you be processing protected health information through Claude? If yes, you need the HIPAA-ready offering with a BAA.

## Feature availability

The HIPAA-ready Enterprise offering includes many of the features available on **[standard Enterprise plans](https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan)**—but enabling HIPAA doesn't bring every feature under your BAA. Features fall into three categories: covered by your BAA, available but not covered, and disabled. PHI should only be processed through covered features, so it's important for administrators to know which features fall in which category and to configure their workspace accordingly. The **[Implementation Guide for HIPAA Entities](https://trust.anthropic.com/resources?s=rgirr4qe8u7ek8c2igx3&name=claude-for-enterprise-hipaa-ready-offering-implementation-guide)** on the Anthropic Trust Center lists every feature's status and is the authoritative source.

**Important:** Enabling HIPAA readiness alone doesn't bring Claude Code under your BAA. Claude Code is covered under your BAA only with zero data retention (ZDR) enabled, and only on qualified accounts. Without ZDR, Claude Code remains available to use but isn't covered—including when Claude Code access is bundled into your Enterprise seats. To explore Claude Code coverage, contact your Anthropic account team or our **[Sales team](https://www.anthropic.com/contact-sales)**.

Additionally, Cowork is not yet covered under Anthropic’s BAA.

## Additional resources

For detailed implementation requirements and technical specifications, review the **[Implementation Guide for HIPAA Entities](https://trust.anthropic.com/resources?s=rgirr4qe8u7ek8c2igx3&name=claude-for-enterprise-hipaa-ready-offering-implementation-guide)** on the Anthropic Trust Center. You can download the Implementation Guide directly during the setup flow.

**Note:** You'll need to request access to view the Implementation Guide. Requests from domains matching existing customer accounts are approved automatically.

------------------------------------------------------------------------

## Get started

Eligible Enterprise organizations can enable HIPAA-ready configuration directly from organization settings—no sales or legal cycle required. The Business Associate Agreement (BAA) is included in the flow as click-to-accept, so there's no separate document to sign and return. Clicking “Accept and Enable HIPAA” constitutes acceptance of the BAA.

### Eligibility

You can enable the HIPAA configuration from organization settings if your organization is on an Enterprise plan. Team plans and individual plans (Free, Pro, and Max) can't enable HIPAA.

Only the **Primary Owner** of the organization can accept the BAA and enable HIPAA. Other Owners or Admins can't complete this flow on the org's behalf. If you're an admin but not the Primary Owner of the Enterprise organization, ask your Primary Owner to sign in and complete enablement.

### Before you begin

Two things to know up front:

- **Enabling HIPAA resets certain settings across your organization.** Some configurations return to defaults as part of the transition to a HIPAA-ready state. The onboarding modal and the Implementation Guide (downloadable during the flow) detail what changes.

- **This is a one-way decision.** Once HIPAA is enabled and the BAA is accepted, the change can't be reversed from organization settings.

You must review the BAA and the Implementation Guide before accepting, as this is an irreversible organization transition.

**Note:** The BAA offered through the self-serve flow is a standard agreement and can't be modified.

### Enable HIPAA

1. Sign in to Claude as the Primary Owner and go to **[Organization settings \> Data and privacy](https://claude.ai/admin-settings/data-privacy-controls)**.

2. Go to **HIPAA Compliance.**

3. Click “Enable” to open the consent flow.

4. Download the Business Associate Agreement, review it, then click “Next.”

5. Download the Implementation Guide, review it, then click “Next.”

6. Click “Accept and enable HIPAA.”

### Confirmation

Once enabled, you'll see a checkmark in the **HIPAA Compliance** section of organization settings, confirming your organization has been configured to process PHI through Claude in accordance with HIPAA. If you don't see this checkmark, your organization isn't enabled.

The onboarding modal will guide you through next steps for your team.

For help with the BAA, the Implementation Guide, or post-enablement questions, reach out to your Anthropic account team or **[our support team](https://support.claude.com/en/articles/9015913-how-to-get-support)**.

------------------------------------------------------------------------

## If you have an existing API BAA

If your organization signed a BAA for Claude API usage before December 2, 2025, that agreement only covers API usage—it does not extend to the HIPAA-ready Enterprise plan. To add this Enterprise plan access, you'll need to sign a new BAA with your account team.

BAAs signed after December 2, 2025 can cover both API usage and the Enterprise plan under a single agreement.

If you use the Claude API, learn more about **[HIPAA-ready Claude API access and how to set it up](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness)**.

---
## hipaa-ready-enterprise-plans.md

# HIPAA-ready Enterprise plans

This feature is available for Enterprise plans only.

We now offer a HIPAA-ready version of Claude that is available for organizations with Enterprise plans that choose to process protected health information (PHI) through Claude. This article explains what the offering includes, which features are available, and how to get started.

## Overview

## Who is this for?

This offering is designed for HIPAA-covered entities and their business associates, including:

- Healthcare providers (e.g., hospitals, clinics, physicians)

- Health plans and insurers

- Healthcare data processors

- Business associates that handle PHI on behalf of covered entities

- Other HIPAA regulated entities

## Feature availability

The HIPAA-ready Enterprise offering includes access to most of the features available on **[standard Enterprise plans](what-is-the-enterprise-plan.md)**. For example, users can chat with Claude, create projects and artifacts, and use voice mode. Depending on what functions are enabled by the organization’s plan administrator, users can also leverage connectors, enterprise search, file creation and code execution, web search, research, and skills. More information about the specific features, functionality, and administrator controls are included in the **[Implementation Guide for HIPAA Entities](https://trust.anthropic.com/resources?s=rgirr4qe8u7ek8c2igx3&name=claude-for-enterprise-hipaa-ready-offering-implementation-guide)**.

**Important:** Claude Code bundled seats are not currently covered as part of the HIPAA-ready offering. If you purchase Enterprise seats that include Claude Code access, only the chat functionality is covered. Claude Code usage is not covered, even when purchased as part of a bundled seat. If your organization wants to have Claude Code usage covered as part of HIPAA-related services, contact your account team to discuss available options.

Additionally, Cowork is not yet available for any HIPAA-ready Enterprise plans.

## Additional resources

**Note:** You'll need to request access to view the Implementation Guide. Requests from domains matching existing customer accounts are approved automatically.

## Getting started

The HIPAA-ready offering requires a sales-assisted Enterprise plan and is not available on self-serve Enterprise plans. To get started, your organization must execute a BAA with our Sales team.

1. **[Contact our Sales team](http://claude.com/contact-sales)** to discuss your organization's needs.

2. Review the Business Associate Agreement and the Implementation Guide.

3. Execute the Business Associate Agreement.

4. Work with your account team to appropriately set up and configure your HIPAA-ready Enterprise plan.

## If you have an existing API BAA

BAAs signed after December 2, 2025 can cover both API usage and the Enterprise plan under a single agreement.

---
## how-am-i-billed-for-my-enterprise-plan-0f7f190634.md

# How am I billed for my Enterprise plan?

Enterprise plan billing has two parts: a fixed seat fee and separate usage charges. The seat fee covers platform access. Usage is billed on top of that, based on what your team actually consumes.

How billing works depends on whether your organization is on a self-serve or sales-assisted Enterprise plan, and whether you're using the current single Enterprise seat or a legacy seat type. The sections below are organized by plan type—make sure you're reading the section that matches your setup. If you're unsure which plan type you're on, check with the person who set up your Enterprise account or contact your Anthropic account manager. Price and plans are subject to change at Anthropic's discretion.

**Important:** The main sections of this article describe the current Enterprise seat billing model, which applies to all new Enterprise plans.

- If your organization was provisioned before the transition to the single Enterprise seat and you see **Chat** and **Chat + Claude Code** seat types in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, skip to the **[Chat and Chat + Claude Code seats section](#h_f6aa4f4dd2)**.

- If your organization is on a seat-based plan with **Standard** and **Premium** seats, skip to the **[seat-based plans section](#h_3b87de90bd)**.

- Chat-only seats and Standard/Premium seats are no longer available for new contracts—both legacy plan types are transitioning to the single Enterprise seat at their next renewal.

------------------------------------------------------------------------

## Seat fees

All usage-based Enterprise plans (self-serve and sales-assisted) use the same seat pricing: **priced per user per month and billed annually**.

The seat fee gives each person access to Claude on web, desktop, and mobile, plus Claude Code and Cowork, but doesn't include any usage. Every token your team consumes is billed separately at standard API rates.

You're charged for the number of seats on your plan at the start of your annual billing cycle. If you add seats during your term, you're charged the prorated amount immediately for the remainder of the year.

**Example:** Your annual plan starts January 1 with 50 seats. You are charged upfront for the seats. On April 1, you add 10 seats. You'll be charged immediately for the remaining months.

**Note:** Seats cannot be removed mid-term on self-serve Enterprise plans. For step-by-step instructions on purchasing, adding, and managing seats, see **[Purchase and manage seats on Enterprise plans](https://support.claude.com/en/articles/13393991-purchasing-and-managing-seats-on-enterprise-plans)**.

------------------------------------------------------------------------

## Usage billing and payment methods

On usage-based Enterprise plans, usage is charged separately from your seat fee and is based on actual token consumption at standard API rates. For current per-model pricing, see our **[API pricing page](https://www.anthropic.com/pricing#api)**.

**Important:** If your organization has the US-only inference setting turned on, usage is billed at 1.1x standard API rates for Claude Opus 4.6, Claude Sonnet 4.6, and later models. This applies to both self-serve and sales-assisted plans. Learn more about **[enabling US-only inference for your organization](https://support.claude.com/en/articles/15422948)**.

How and when you're billed for usage depends on your plan type:

### Self-serve Enterprise

**Usage billing**

Usage is purchased **upfront in credits**. Your credits draw down as your team uses Claude and Claude Code. When your credits run out, usage stops until an Owner, Primary Owner, or custom role with the **Billing** permission set to "Can manage" purchases more. Self-serve Enterprise plans are billed in USD only. If your organization needs to pay in another currency, **[contact our Sales team](https://claude.com/contact-sales)** to set up a sales-assisted plan.

- After setup, Owners, Primary Owners, and custom roles with the **Billing** permission set to "Can manage" can purchase additional credits at any time from **[Organization](https://claude.ai/admin-settings/organization) [settings \> Usage](https://claude.ai/admin-settings/usage)**.

- All credits are shared across your organization—any team member can draw from the same pool.

**Note:** If you purchased your Enterprise plan through AWS Marketplace, billing works like sales-assisted plans. You're billed monthly in arrears based on your organization's consumption rather than purchasing credits upfront.

**Payment methods**

Self-serve Enterprise organizations can pay by credit card, debit card, or ACH bank transfer. Owners, Primary Owners, and custom roles with the **Billing** permission set to "Can manage" can switch between payment methods at any time in **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**.

For details on ACH, including activation timing and auto-reload, see **[What is the Enterprise plan?](https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan)**

### Sales-assisted Enterprise

**Usage billing**

Usage is **billed monthly in arrears** based on your organization's actual consumption during each billing period. You'll receive a monthly invoice reflecting usage for that period. Speak with your account manager for questions about your usage invoices.

**Payment methods**

Sales-assisted Enterprise organizations can pay by bank transfer (ACH or wire) or, for smaller invoices, by credit card. Invoices of \$50,000 or more can only be paid by bank transfer (ACH or wire). The credit card option won't appear on the payment page for invoices at or above this amount. To pay a specific invoice by card, reach out to your Anthropic Contact to request an exception.

------------------------------------------------------------------------

## How usage works across your team

Enterprise seats don't come with an individual token allowance. All usage across your organization is billed together at API rates, regardless of who consumed it.

What this looks like in practice depends on your plan type:

### Self-serve Enterprise

Everyone's usage draws from the same credit balance. One person's heavy usage depletes credits faster for everyone, so monitoring and spend limits matter here. When the balance hits zero, usage stops for the whole organization until an Owner purchases more.

### Sales-assisted Enterprise

There's no balance to deplete. Everyone's usage is metered and added to the same monthly invoice. One person's heavy usage doesn't block anyone else — it just increases what shows up on the bill. If you want a ceiling, set spend limits.

------------------------------------------------------------------------

## Spend limits

Owners, Primary Owners, and custom roles with the **Billing** permission set to "Can manage" can set spend limits to manage your organization's consumption. This applies to both self-serve and sales-assisted plans.

To configure spend limits, navigate to **[Organization](https://claude.ai/admin-settings/organization) [settings \> Usage](https://claude.ai/admin-settings/usage)**.

You can set limits at two levels:

- **Organization level:** Maximum spend for all usage across your organization.

- **Individual level:** Maximum spend for a specific user.

These limits work hierarchically, so a user cannot exceed their individual limit or the organization limit, whichever is lower.

On **self-serve plans**, spend limits work alongside your credit balance. If a user hits their individual limit or the organization limit, their usage will stop even if credits remain. Owners can adjust limits at any time.

On **sales-assisted plans**, spend limits prevent usage from continuing past the limit threshold. If a limit is reached, usage stops until the next billing period begins or an owner raises the limit.

**Owners can set limits to "unlimited,"** but consumption will still be billed. You cannot disable billing for usage—usage-based pricing is a core part of the Enterprise plan.

------------------------------------------------------------------------

## Monitoring usage and spend

You can track your organization's usage and spending in a few places:

- **Organization** **settings \> Usage:** View month-to-date spending for each member, current spend limit status, and credit balance (self-serve plans).

- **Monthly invoices:** Detailed usage per user for the billing period (sales-assisted plans).

- **Spend limit notifications:** Alerts when users or your organization approach configured spending thresholds.

------------------------------------------------------------------------

## What happens when usage stops

If usage stops on your Enterprise plan, here's how Owners, Primary Owners, and custom roles with the **Billing** permission set to "Can manage" can resume:

- **Self-serve plans:** If credits run out or a spend limit is reached, purchase additional credits or raise the spend limit from **[Organization](https://claude.ai/admin-settings/organization) [settings \> Usage](https://claude.ai/admin-settings/usage)**.

- **Sales-assisted plans:** If a spend limit is reached, you can raise the limit, or usage will resume at the start of the next billing period. Contact your account manager with questions.

------------------------------------------------------------------------

## Chat and Chat + Claude Code seats

**Important:** Chat and Chat + Claude Code are legacy seat types that are no longer available for new Enterprise contracts. This section only applies to organizations that were provisioned with these seat types before the transition to the single Enterprise seat. If you recently signed a new Enterprise contract, the main sections of this article apply to you—your plan uses the single Enterprise seat.

Some existing usage-based Enterprise organizations currently have two seat types with different pricing. If you see **Chat** and **Chat + Claude Code** seats in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you.

Seat fees are billed annually. Usage billing works the same way as described in the **[Usage billing section](#h_540cbc3861)** above: separately from seat fees, at API rates, and in arrears on sales-assisted plans.

### Transition to the single Enterprise seat

At your next contract renewal, your plan will automatically transition to the single Enterprise seat model. When that happens, all users — regardless of their current seat type — will move to the **Enterprise seat**. This seat includes Claude Code, Cowork, Chat and more.

If you have questions about your upcoming renewal, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

------------------------------------------------------------------------

## Seat-based plans

**Important:** Standard and Premium are legacy seat types that are no longer available for new Enterprise contracts. This section only applies to organizations that were provisioned with these seat types before the transition to usage-based billing. If you recently signed a new Enterprise contract, the main sections of this article apply to you.

Some Enterprise organizations are on older seat-based plans with **Standard** and **Premium** seats. These plans charge a flat monthly fee per seat that includes a usage allowance, which is a different model than the usage-based billing described above.

If you see "Standard" and "Premium" seats in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you.

On seat-based plans, usage credits are available to allow team members to continue working after reaching their seat's included limits. For details on how usage credits work and how they're billed on your plan, see **[Manage usage credits for Team and seat-based Enterprise plans](https://support.claude.com/en/articles/12005970-)**.

### Transitioning to usage-based Enterprise

At your next contract renewal, your plan will transition to the usage-based single Enterprise seat model described in this article. If you'd like to migrate before your renewal, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

---
## how-am-i-billed-for-my-enterprise-plan.md

4. How am I billed for my Enterprise plan?

# How am I billed for my Enterprise plan?

Enterprise plan billing has two parts: a fixed seat fee and separate usage charges. The seat fee covers platform access. Usage is billed on top of that, based on what your team actually consumes. How and when usage is billed depends on whether your organization purchased self-serve or sales-assisted.

**Important:** If your organization is on a seat-based plan with Standard and Premium seats, skip to the **[seat-based plans section](#h_3b87de90bd)** at the bottom. If your organization currently has Chat and Chat + Claude Code seats, skip to the **[Chat and Chat + Claude Code seats section](#h_f6aa4f4dd2)**.

------------------------------------------------------------------------

## Seat fees

All usage-based Enterprise plans (self-serve and sales-assisted) use the same seat pricing: **priced per user per month and billed annually**.

**Example:** Your annual plan starts January 1 with 50 seats. You are charged upfront for the seats. On April 1, you add 10 seats. You'll be charged immediately for the remaining months.

**Note:** Seats cannot be removed mid-term on self-serve Enterprise plans. For step-by-step instructions on purchasing, adding, and managing seats, see **[Purchase and manage seats on Enterprise plans](purchasing-and-managing-seats-on-enterprise-plans.md)**.

------------------------------------------------------------------------

## Usage billing

How and when you're billed for usage depends on your plan type:

### Self-serve Enterprise

Usage is purchased **upfront in credits**. Your credits draw down as your team uses Claude and Claude Code. When your credits run out, usage stops until an Owner or Primary Owner purchases more. Self-serve Enterprise plans are billed in USD only. If your organization needs to pay in another currency, **[contact our Sales team](https://claude.com/contact-sales)** to set up a sales-assisted plan.

- After setup, Owners and Primary Owners can purchase additional credits at any time from **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

- All credits are shared across your organization — any team member can draw from the same pool.

### Sales-assisted Enterprise

------------------------------------------------------------------------

## How usage works across your team

Enterprise seats don't come with an individual token allowance. All usage across your organization is billed together at API rates, regardless of who consumed it.

What this looks like in practice depends on your plan type:

### Self-serve Enterprise

### Sales-assisted Enterprise

------------------------------------------------------------------------

## Spend controls

Owners and Primary Owners can set spending caps to manage your organization's consumption. This applies to both self-serve and sales-assisted plans.

To configure spend controls, sign in as an Owner or Primary Owner and navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

You can set caps at two levels:

- **Organization level:** Maximum spend for all usage across your organization.

- **Individual level:** Maximum spend for a specific user.

These limits work hierarchically — a user cannot exceed their individual limit or the organization limit, whichever is lower.

On **self-serve plans**, spend caps work alongside your credit balance. If a user hits their individual cap or the organization cap, their usage will stop even if credits remain. Owners can adjust caps at any time.

On **sales-assisted plans**, spend caps prevent usage from continuing past the cap threshold. If a cap is reached, usage stops until the next billing period begins or an owner raises the limit.

**Owners can set limits to "unlimited,"** but consumption will still be billed. You cannot disable billing for usage — usage-based pricing is a core part of the Enterprise plan.

------------------------------------------------------------------------

## Monitoring usage and spend

You can track your organization's usage and spending in a few places:

- **Organization** **settings \> Usage:** View month-to-date spending for each member, current spend cap status, and credit balance (self-serve plans).

- **Monthly invoices:** Detailed usage per user for the billing period (sales-assisted plans).

- **Spend limit notifications:** Alerts when users or your organization approach configured spending thresholds.

------------------------------------------------------------------------

## What happens when usage stops

If usage stops on your Enterprise plan, here's how to resume:

- **Self-serve plans:** If credits run out or a spend cap is reached, an Owner or Primary Owner can purchase additional credits or raise the spend cap from **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

- **Sales-assisted plans:** If a spend cap is reached, an Owner or Primary Owner can raise the cap, or usage will resume at the start of the next billing period. Contact your account manager with questions.

------------------------------------------------------------------------

## Chat and Chat + Claude Code seats

**Note:** Organizations currently using usage-based Enterprise plans with Chat and Chat + Claude Code seats will not be able to continue with this billing model past your next contract renewal.

### Transitioning to the single Enterprise seat

If you have questions about your upcoming renewal, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

------------------------------------------------------------------------

## Seat-based plans

**Note:** Organizations currently using seat-based Enterprise plans with Standard and Premium seats will not be able to continue with this billing model past your next contract renewal.

If you see "Standard" and "Premium" seats in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you.

On seat-based plans, extra usage is available to allow team members to continue working after reaching their seat’s included limits. See **[Manage extra usage for Team and seat-based Enterprise plans](extra-usage-for-team-and-seat-based-enterprise-plans.md)** for details on how extra usage works and how it's billed on your plan.

### Transitioning to usage-based Enterprise

---
## how-can-i-cancel-my-claude-pro-subscription-on-the-claude-app-for-ios.md

4. How can I cancel my Claude Pro subscription on the Claude app for iOS?

# How can I cancel my Claude Pro subscription on the Claude app for iOS?

If you signed up for Claude Pro via the iOS app, your subscription and payment will be handled directly on your iOS device.

To cancel your subscription, click on your initials in the top right corner of the Claude app for iOS, and then click “Billing” from the menu options. Select “manage subscription” and follow the prompts for cancellation. If you’ve already removed the app from your device, you can also follow the instructions located in the App Store resource [here](https://support.apple.com/en-us/118428) to unsubscribe.

You may cancel your Claude Pro subscription at any time from the platform you signed up on. To avoid being charged for your next billing period, cancel your subscription at least 24 hours before your next billing date.

---
## how-can-i-learn-more-about-claude-api-pricing-55059e836c.md

# How can I learn more about Claude API pricing?

March 16, 2026

For our most up-to-date prices, please consult our [pricing page](https://claude.com/pricing#api).

---
## how-can-i-learn-more-about-claude-api-pricing.md

4. How can I learn more about Claude API pricing?

# How can I learn more about Claude API pricing?

For our most up-to-date prices, please consult our [pricing page](https://claude.com/pricing#api).

---
## how-do-i-cancel-my-organization-s-team-plan-subscription-239ac7a68f.md

# Cancel your organization's Team plan subscription

---
## how-do-i-cancel-my-organization-s-team-plan-subscription.md

4. Cancel your organization's Team plan subscription

# Cancel your organization's Team plan subscription

---
## how-do-i-cancel-my-paid-claude-subscription-2a2e02e930.md

# Cancel your Pro or Max subscription

**Note:** To avoid being charged for your next billing period, cancel your subscription at least 24 hours before your next billing date.

## Cancel your Pro or Max subscription on Claude and Claude Desktop

## Cancel your Pro or Max subscription on Claude for iOS

If you subscribed to a Pro or Max plan via Claude for iOS, your subscription and payment will be handled directly on your iOS device.

## Cancel your Pro or Max subscription on Claude for Android

If you subscribed to a Pro or Max plan via Claude for Android, your subscription and payment will be handled directly on your Android device.

---
## how-do-i-get-started-with-the-team-plan-5bc832ab3b.md

# Get started with the Team plan

## Requirements to sign up for a Team plan

- All team members must have an email address with one of your organization's allowed email domains to be invited to the account.

- During sign-up, you can choose between monthly or annual billing options.

- Refer to this article for more information: **[How is my Team plan bill calculated?](https://support.claude.com/en/articles/9267289-how-is-my-team-plan-bill-calculated)**

- Team plans require a minimum of two members and are not intended for individual use.

## Create a new Team organization

To get started with the Team plan, navigate to **[claude.ai/login](http://claude.ai/login)** and enter your work email address. Follow the onboarding prompts and select the Team plan.

## Upgrade from an individual plan to the Team plan

**Note:** Once content has been moved into an organization, it can't be moved back to a personal account.

---
## how-do-i-get-started-with-the-team-plan.md

# Get started with the Team plan

## Requirements to sign up for a Team plan

- The account creator must use a business email address. Public domains like @gmail.com, @yahoo.com, and @hotmail.com aren't allowed—but you can **[add them as permitted domains](../21-Account-Support/account-management-faqs.md#h_b54c41c86c)** for other members of your organization.

- All team members must have an email address with one of your organization's allowed email domains to be invited to the account.

- During sign-up, you can choose between monthly or annual billing options.

- Refer to this article for more information: **[How is my Team plan bill calculated?](how-is-my-team-plan-bill-calculated.md)**

- Team plans require a minimum of five members and are not intended for individual use.

## Create a new Team organization

To get started with the Team plan, navigate to **[claude.ai/login](http://claude.ai/login)** and enter your work email address. Follow the onboarding prompts and select the Team plan.

## Upgrade from an individual plan to the Team plan

- Team plan organizations are separate from free and paid individual Claude accounts. Data cannot be transferred between the separate instances.

- If you only want to use your Team plan after upgrading, you'll need to cancel your paid subscription and/or delete your free or paid individual Claude account separately.

- **[How do I cancel my paid Claude subscription?](https://support.claude.com/en/articles/8325617-how-do-i-cancel-my-paid-claude-subscription)**

- **[How can I delete my Claude account?](../21-Account-Support/how-can-i-delete-my-claude-account.md)**

---
## how-is-my-team-plan-bill-calculated-7772627a23.md

# How is my Team plan bill calculated?

May 18, 2026

Prices shown are for US customers and exclude applicable taxes. Pricing, currency, and tax handling vary by region. Visit **[claude.ai/upgrade](http://claude.ai/upgrade)** to see current pricing for your location.

For current pricing by seat type and billing interval, see **[What is the Team plan?](https://support.claude.com/en/articles/9266767-what-is-the-team-plan)**

For information on seat types and what's included, see **[Purchasing and managing seats on Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)**.

------------------------------------------------------------------------

## How does adding or removing members affect my bill?

**Adding members or upgrading seats:** You will be charged the prorated amount immediately.

**Removing members:** You will not receive an immediate credit or refund. The seat becomes available to assign to another member.

For instructions to add and remove members, see **[Managing members on Team and Enterprise plans](https://support.claude.com/en/articles/13133750-managing-members-on-team-and-enterprise-plans)**.

------------------------------------------------------------------------

## Usage credits

If usage credits are enabled, your bill may include charges for usage beyond seat limits. For details on how usage credits work and how they're billed on your plan, see **[Manage usage credits for Team and seat-based Enterprise plans](https://support.claude.com/en/articles/12005970-)**.

------------------------------------------------------------------------

## Billing examples

### Annual plan example

On January 1 (the start date of your annual subscription), your annual plan has 10 standard seats. The amount charged would be \$2,400 (\$20 × 10 seats × 12 months) due on January 1st.

On April 1st, you decide to upgrade five of the existing standard seats to premium seats. Since there are 275 days remaining in your subscription year, the prorated cost for the seat upgrades would be: (\$80 × 5 seats × 12 months) × (275 days ÷ 365 days in the year) = \$3,616.44. Your payment method will be charged \$3,616.44 on April 1st for the seat upgrades for the remainder of the subscription year.

If you remove members during your subscription year, their seats will become available to assign to other team members.

Taxes are not included in this example.

### Monthly plan example

On January 1 (the first day of your billing cycle), your Team plan has 10 standard seats. The amount charged would be \$250 (\$25 × 10 seats) due on January 1st.

On January 15th, you decide to upgrade five standard seats to premium seats. Since there are 16 days remaining in January, the prorated cost for the seat upgrades would be: (\$100 × 5 seats × 16 days) ÷ 31 days in January = \$258.06. Your payment method will be charged \$258.06 on January 15th for the seat upgrades in January.

You will be charged for the number of members on your team at the beginning of each billing cycle. If you remove members in the middle of a billing cycle, their seats will become available to assign to other team members.

Taxes are not included in this example.

**Note:** The "Projected total" displayed on **[your organization’s Billing page](https://claude.ai/admin-settings/billing)** is not inclusive of taxes.

Price and plans are subject to change at Anthropic's discretion.

---
## how-is-my-team-plan-bill-calculated.md

# How is my Team plan bill calculated?

For current pricing by seat type and billing interval, see **[What is the Team plan?](what-is-the-team-plan.md)**

For information on seat types and what's included, see **[Purchasing and managing seats on Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)**.

------------------------------------------------------------------------

## How does adding or removing members affect my bill?

**Adding members or upgrading seats:** You will be charged the prorated amount immediately.

**Removing members:** You will not receive an immediate credit or refund. The seat becomes available to assign to another member.

For instructions to add and remove members, see **[Managing members on Team and Enterprise plans](managing-members-on-team-and-enterprise-plans.md)**.

------------------------------------------------------------------------

## Extra usage

If extra usage is enabled, your bill may include charges for usage beyond seat limits. See this article for more information: **[Extra usage for Team and seat-based Enterprise plans](extra-usage-for-team-and-seat-based-enterprise-plans.md)**.

------------------------------------------------------------------------

## Billing examples

### Annual plan example

On January 1 (the start date of your annual subscription), your annual plan has 10 standard seats. The amount charged would be \$2,400 (\$20 × 10 seats × 12 months) due on January 1st.

If you remove members during your subscription year, their seats will become available to assign to other team members.

Taxes are not included in this example.

### Monthly plan example

On January 1 (the first day of your billing cycle), your Team plan has 10 standard seats. The amount charged would be \$250 (\$25 × 10 seats) due on January 1st.

Taxes are not included in this example.

**Note:** The "Projected total" displayed on **[your organization’s Billing page](https://claude.ai/admin-settings/billing)** is not inclusive of taxes.

---
## how-large-is-the-context-window-on-paid-claude-plans-24df102877.md

# How large is the context window on paid Claude plans?

Claude Opus 5 and Sonnet 5 support a 1M token context window on all paid plans when chatting with Claude. Claude Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6 support a 500K token context window on all paid plans when chatting with Claude. Outside of these models, Claude’s context window size is 200K, meaning it can ingest 200K+ tokens (about 500 pages of text or more) when using a paid Claude plan.

When using Claude Code with a Pro, Max, Team, or Enterprise plan, Claude Sonnet 5, Fable 5, Opus 5, Opus 4.8, Opus 4.7, and Opus 4.6 support a 1M token context window. Pro users need to enable usage credits to access the 1M token context window for Opus models. Sonnet 4.6 also supports a 1M context window for all paid Claude plans on Claude Code, but usage credits must be enabled to access it (except for usage-based Enterprise plans).

## Automatic context management

For users on paid plans with code execution enabled, Claude automatically manages your conversation context. When your conversation approaches the context window limit, Claude summarizes earlier messages to make room for new content. This does not count towards your usage limit, and allows conversations to continue indefinitely in most cases.

Your full chat history is preserved so Claude can reference it, even after earlier portions have been summarized. You may occasionally notice Claude "organizing its thoughts" during long conversations—this is the automatic context management at work.

**Note:** Code execution must be enabled for automatic context management to work. In rare edge cases (such as very large first messages or system errors), you may still encounter context window limits.

## Maximizing your context window

While context is managed automatically for most conversations, you can still optimize how you use your available context space:

- **Utilize projects effectively:** Projects use retrieval-augmented generation (RAG), which allows Claude to work with larger amounts of information by only loading relevant content into the context window.

- **Keep project instructions concise:** Claude performs best when you use project instructions for general context around your project, key guidelines, and Claude's role.

- **Manage tools and connectors:** These features are token-intensive, so being mindful of how many you have active helps maximize your available context.

---
## how-large-is-the-context-window-on-paid-claude-plans.md

4. How large is the context window on paid Claude plans?

# How large is the context window on paid Claude plans?

Claude’s context window size is 200K, meaning it can ingest 200K+ tokens (about 500 pages of text or more) when using a paid Claude plan.

**Note:** Users on Enterprise plans have access to a 500K context window when using specific models. See **[What is the Enterprise plan?](what-is-the-enterprise-plan.md)** for more information.

## Automatic context management

## Maximizing your context window

While context is managed automatically for most conversations, you can still optimize how you use your available context space:

- **Keep project instructions concise:** Claude performs best when you use project instructions for general context around your project, key guidelines, and Claude's role.

- **Manage tools and connectors:** These features are token-intensive, so being mindful of how many you have active helps maximize your available context.

---
## how-long-do-you-store-personal-data.md

# How long do you store my organization’s data?

## Standard Retention Timeframe

For Anthropic API users, we automatically delete inputs and outputs on our backend within 30 days of receipt or generation, except:

- When you use a service with longer retention under your control (e.g. Files API)

- When you and we have agreed otherwise (e.g. [zero data retention agreement](https://privacy.anthropic.com/en/articles/8956058-i-have-a-zero-retention-agreement-with-anthropic-what-products-does-it-apply-to))

- If we need to retain them for longer to enforce our [Usage Policy (UP)](https://www.anthropic.com/legal/aup)

- In compliance with the law

If you use our other commercial products (e.g. Claude for Work, Claude for Enterprise, Anthropic Console, etc.) that allow you to save and continue conversations with Claude, we retain your chats and coding sessions in the product to provide you with a consistent product experience.

You control your conversations and can [delete your chats](https://privacy.anthropic.com/en/articles/8230524-how-can-i-delete-or-rename-a-conversation) anytime from your dashboard. When you delete a conversation it’s:

- Removed from your chat history immediately

- Deleted from our back-end storage systems within 30 days

Incognito chats are automatically deleted within 30 days unless flagged as a Usage Policy violation. [Learn more](https://support.anthropic.com/en/articles/12260368-using-incognito-chats) about Incognito chats for your organization.

## Usage Policy Violations

We retain inputs and outputs for up to 2 years and trust and safety classification scores for up to 7 years if your chat is flagged by our trust and safety classifiers as violating our [Usage Policy](https://www.anthropic.com/legal/aup).

## Feedback Data

Where you have provided feedback to us (e.g. by submitting feedback through our thumbs up/down button or sent bug reports), we retain data associated with that submission for 5 years. [Learn more](https://privacy.anthropic.com/en/articles/7996868-is-my-data-used-for-model-training).

In all cases, we may retain your chats or sessions as required by law or as necessary to combat violations of our [Usage Policy](https://www.anthropic.com/legal/aup). If permitted in your contract with us, we may anonymize your organization’s data for research or statistical purposes, in which case we may retain this information for longer.

For more information about our privacy practices, please see our [Trust Center](https://trust.anthropic.com/) and [Data Processing Addendum](https://anthropic.com/legal/data-processing-addendum).

---
## how-to-change-your-pro-plan-from-monthly-to-annual-billing-7bd9204afe.md

# How to change your Pro plan from monthly to annual billing

March 16, 2026

Save on your Pro plan subscription by switching from monthly to annual billing. When you upgrade, any remaining time on your current monthly subscription will be credited to your new annual plan invoice.

## To switch from monthly to annual billing

1. Navigate to [Settings \> Billing](https://claude.ai/settings/billing).

2. Click "Adjust plan" next to your Pro subscription details.

3. From [the upgrade page](https://claude.ai/upgrade), select "Get Pro annual plan"

4. Review the annual price on the next screen.

5. Click "Confirm subscription."

## What happens next?

- Your subscription billing period switches from monthly to annual immediately.

- Any unused time from your monthly subscription will be automatically credited to your first annual invoice. You’ll see this credit as a separate line item on your invoice.

- Your next billing date will be set to one year from the date you switch.

- You can cancel your subscription at any time from your billing settings. See [How do I cancel my paid Claude subscription?](https://support.anthropic.com/en/articles/8325617-how-do-i-cancel-my-paid-claude-subscription) for more information.

---
## how-to-change-your-pro-plan-from-monthly-to-annual-billing.md

4. How to change your Pro plan from monthly to annual billing

# How to change your Pro plan from monthly to annual billing

## To switch from monthly to annual billing

1. Navigate to [Settings \> Billing](https://claude.ai/settings/billing).

2. Click "Adjust plan" next to your Pro subscription details.

3. From [the upgrade page](https://claude.ai/upgrade), select "Get Pro annual plan"

4. Review the annual price on the next screen.

5. Click "Confirm subscription."

## What happens next?

- Your subscription billing period switches from monthly to annual immediately.

- Any unused time from your monthly subscription will be automatically credited to your first annual invoice. You’ll see this credit as a separate line item on your invoice.

- Your next billing date will be set to one year from the date you switch.

---
## how-to-change-your-team-plan-from-monthly-to-annual-billing-bcf1288298.md

# Change your Team plan from monthly to annual billing

March 16, 2026

Owners and Primary Owners of Team plans with monthly subscriptions can switch from the monthly plan to an annual plan by following these steps:

1. Navigate to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)** or **[claude.ai/upgrade](http://claude.ai/upgrade)**.

2. You’ll see a banner confirming your current monthly plan in your Billing settings; click the “Switch to Annual” button.

3. Or from /upgrade, click the “Switch to Annual plan” button:

4. The confirmation screen will display the total cost for your upgrade from monthly to annual billing:

5. Click “Confirm subscription.”

6. Your new annual Team plan will start immediately and you will be credited for any unused time on your previous monthly plan.

---
## how-to-change-your-team-plan-from-monthly-to-annual-billing.md

4. Change your Team plan from monthly to annual billing

# Change your Team plan from monthly to annual billing

Owners and Primary Owners of Team plans with monthly subscriptions can switch from the monthly plan to an annual plan by following these steps:

1. Navigate to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)** or **[claude.ai/upgrade](http://claude.ai/upgrade)**.

2. You’ll see a banner confirming your current monthly plan in your Billing settings; click the “Switch to Annual” button.

3. Or from /upgrade, click the “Switch to Annual plan” button:

4. The confirmation screen will display the total cost for your upgrade from monthly to annual billing:

5. Click “Confirm subscription.”

6. Your new annual Team plan will start immediately and you will be credited for any unused time on your previous monthly plan.

---
## how-to-gift-a-claude-subscription-1b2526ec96.md

# How to gift a Claude subscription

April 29, 2026

Give the gift of Claude to friends, family, or colleagues.

## What's included?

Gift subscriptions include full access to all features of the selected plan. Refer to the below articles for full details for each plan:

- **[What is the Pro plan?](https://support.claude.com/en/articles/8325606-what-is-the-pro-plan)**

- **[What is the Max plan?](https://support.claude.com/en/articles/11049741-what-is-the-max-plan)**

## Who can purchase gifts?

Gift subscriptions are available for most Pro and Max plan users to purchase. Free users and members of Team and Enterprise organizations can't purchase gift subscriptions at this time.

## How to purchase a gift

1. Log in to your Claude account and click your initials in the lower left corner.

2. Select “Gift Claude” from the menu, or visit claude.ai/gift.

3. Choose a plan (Pro, Max 5x, or Max 20x) and duration (1, 3, 6, or 12 months).

4. Personalize your gift:

- Pick a card color

- Add an optional message

- Choose to send via email or generate a shareable link

5. If sending by email, enter the recipient's name and email address.

6. Complete checkout with your payment information.

After purchase, you'll receive a confirmation email with your order details.

**Important:** The gift will expire 365 days after the purchase date. Recipients cannot redeem multiple gifts at one time or stack redemptions.

## Delivery options

**Email delivery:** The recipient receives the gift directly in their inbox. The email includes your personalized message and a redemption button.

**Shareable link:** You receive a link that you can share however you'd like—in a card, text message, or in person.

## Good to know

- Gift subscriptions are available globally.

- Recipients redeem gifts on the web at **[claude.ai/gift/redeem](https://claude.ai/gift/redeem)**. For more information, see **[How to redeem a Claude gift subscription](https://support.claude.com/en/articles/12938695-how-to-redeem-a-claude-gift-subscription)**.

- Recipients with active mobile (iOS or Android) subscriptions will need to wait until their mobile subscription ends before redeeming.

- No credit card is required for the recipient to redeem.

---
## how-to-gift-a-claude-subscription.md

# How to gift a Claude subscription

Give the gift of Claude to friends, family, or colleagues. Gift subscriptions are available for Pro, Max 5x, and Max 20x plans, and can be purchased for 1, 3, 6, or 12 months.

## What's included?

Gift subscriptions include full access to all features of the selected plan. Refer to the below articles for full details for each plan:

- [What is the Pro plan?](what-is-the-pro-plan.md)

- [What is the Max plan?](what-is-the-max-plan.md)

## Who can purchase gifts?

Anyone can purchase a gift subscription, so you don’t need to have a Claude account to give a subscription to someone else.

## How to purchase a gift

1. Log in to your Claude account and click your initials in the lower left corner.

2. Select “Gift Claude” from the menu, or visit claude.ai/gift.

3. Choose a plan (Pro, Max 5x, or Max 20x) and duration (1, 3, 6, or 12 months).

4. Personalize your gift:

- Pick a card color

- Add an optional message

- Choose to send via email or generate a shareable link

5. If sending by email, enter the recipient's name and email address.

6. Complete checkout with your payment information.

After purchase, you'll receive a confirmation email with your order details.

**Important:** The gift will expire 365 days after the purchase date. Recipients cannot redeem multiple gifts at one time or stack redemptions.

## Delivery Options

**Email delivery:** The recipient receives the gift directly in their inbox. The email includes your personalized message and a redemption button.

**Shareable link:** You receive a link that you can share however you'd like—in a card, text message, or in person.

## Good to Know

- Gift subscriptions are available globally.

- Recipients redeem gifts on the web at [claude.ai/gift/redeem](https://claude.ai/gift/redeem).

- Recipients with active mobile (iOS or Android) subscriptions will need to wait until their mobile subscription ends before redeeming.

- No credit card is required for the recipient to redeem.

---
## how-to-redeem-a-claude-gift-subscription-97f49e6fcf.md

# How to redeem a Claude gift subscription

March 16, 2026

Someone sent you a Claude gift subscription—here's how to redeem it and start using Claude.

## How to redeem your gift

1. Open the gift email or link you received.

2. Click “Redeem your gift.”

3. Sign in to your Claude account, or create a new account if you don't have one.

4. Confirm redemption.

5. You can also redeem directly at [claude.ai/gift/redeem](https://claude.ai/gift/redeem) and enter your gift code.

**Important:** Your gift will expire 365 days after the purchase date. It’s not possible to redeem multiple gifts at one time or stack redemptions.

## What happens when you redeem

Your experience depends on your current subscription status:

**If you're a new or free user:** Your account is upgraded to the gifted plan immediately. You'll have full access for the duration of the gift.

**If you're a Pro subscriber (web) and receive a Pro gift:** Your Pro subscription is extended by the gift duration.

**If you're a Pro subscriber (web) and receive a Max gift:** You're upgraded to the Max plan for the gift duration. When the gift ends, your Pro subscription resumes. Any unused time from your Pro billing cycle is added as account credit.

**If you're a Max subscriber (web) and receive a lower-tier gift:** The gift value is converted to account credit, which is automatically applied to your future invoices.

**If you're a Max subscriber (web) and receive the same or higher Max tier:** Your Max subscription is extended or upgraded accordingly.

## Mobile Subscribers

If you have an active subscription through the iOS App Store or Google Play Store, you'll need to wait until that subscription ends before you can redeem a gift subscription. Gift subscriptions can only be redeemed on the web.

Your gift won't expire while you wait—you can redeem it once your mobile subscription ends.

## Troubleshooting

### I don't see the redemption email

Check your spam or junk folder. If you still can't find it, ask the person who sent the gift to confirm your email address or resend the gift link.

### I'm getting an error when trying to redeem

Make sure you're signed in to Claude on the web (not the mobile app).

### Can I use the gift on a different email address?

The gift can be redeemed by any Claude account, regardless of which email received the gift.

---
## how-to-redeem-a-claude-gift-subscription.md

4. How to redeem a Claude gift subscription

# How to redeem a Claude gift subscription

Someone sent you a Claude gift subscription—here's how to redeem it and start using Claude.

## How to redeem your gift

1. Open the gift email or link you received.

2. Click “Redeem your gift.”

3. Sign in to your Claude account, or create a new account if you don't have one.

4. Confirm redemption.

5. You can also redeem directly at [claude.ai/gift/redeem](https://claude.ai/gift/redeem) and enter your gift code.

**Important:** Your gift will expire 365 days after the purchase date. It’s not possible to redeem multiple gifts at one time or stack redemptions.

## What happens when you redeem

Your experience depends on your current subscription status:

**If you're a new or free user:** Your account is upgraded to the gifted plan immediately. You'll have full access for the duration of the gift.

**If you're a Pro subscriber (web) and receive a Pro gift:** Your Pro subscription is extended by the gift duration.

**If you're a Max subscriber (web) and receive a lower-tier gift:** The gift value is converted to account credit, which is automatically applied to your future invoices.

**If you're a Max subscriber (web) and receive the same or higher Max tier:** Your Max subscription is extended or upgraded accordingly.

## Mobile Subscribers

Your gift won't expire while you wait—you can redeem it once your mobile subscription ends.

## Troubleshooting

### I don't see the redemption email

Check your spam or junk folder. If you still can't find it, ask the person who sent the gift to confirm your email address or resend the gift link.

### I'm getting an error when trying to redeem

Make sure you're signed in to Claude on the web (not the mobile app).

### Can I use the gift on a different email address?

The gift can be redeemed by any Claude account, regardless of which email received the gift.

---
## i-have-a-paid-claude-subscription-pro-max-team-or-enterprise-plans-why-do-i-have-5b192918a7.md

# I have a paid Claude subscription (Pro, Max, Team, or Enterprise plans). Why do I have to pay separately to use the Claude API and Console?

March 16, 2026

Claude paid plans and the Claude Console are separate products designed for different purposes:

- Claude paid plans give subscribers access to Claude on the web, desktop, and mobile, and offer enhanced features like more usage and priority access during high-traffic periods.

- The Claude Console is our developer platform providing API keys and access to Claude models for building applications and integrations.

A paid Claude subscription enhances your chat experience but doesn't include access to the Claude API or Console.

If you're interested in both enhanced chat features and API access, you'll need to sign up for a paid Claude plan and separately [set up Console access](https://support.claude.com/en/articles/8114521-how-can-i-access-the-anthropic-api) for API usage. This allows you to benefit from both offerings based on your specific needs.

Refer to this article to learn more about Claude Console billing: [How do I pay for my API usage?](https://support.claude.com/en/articles/8977456-how-do-i-pay-for-my-api-usage)

---
## i-have-a-paid-claude-subscription-pro-max-team-or-enterprise-plans-why-do-i-have.md

4. I have a paid Claude subscription (Pro, Max, Team, or Enterprise plans). Why do I have to pay separately to use the Claude API and Console?

# I have a paid Claude subscription (Pro, Max, Team, or Enterprise plans). Why do I have to pay separately to use the Claude API and Console?

Claude paid plans and the Claude Console are separate products designed for different purposes:

- Claude paid plans give subscribers access to Claude on the web, desktop, and mobile, and offer enhanced features like more usage and priority access during high-traffic periods.

- The Claude Console is our developer platform providing API keys and access to Claude models for building applications and integrations.

A paid Claude subscription enhances your chat experience but doesn't include access to the Claude API or Console.

If you're interested in both enhanced chat features and API access, you'll need to sign up for a paid Claude plan and separately [set up Console access](../04-API-Reference/Other/how-can-i-access-the-anthropic-api.md) for API usage. This allows you to benefit from both offerings based on your specific needs.

Refer to this article to learn more about Claude Console billing: [How do I pay for my API usage?](../22-Safety-Policy/how-do-i-pay-for-my-api-usage.md)

---
## i-m-planning-to-launch-a-product-using-the-claude-api-what-steps-should-i-take-t-d354484757.md

# I’m planning to launch a product using the Claude API. What steps should I take to ensure I’m not violating Anthropic’s Usage Policy?

March 16, 2026

We founded Anthropic to put safety at the frontier of AI research and AI products. Our research informs our commercial products, and our models are some of the most reliably safe and resistant to abuse available today. We are working to improve our safety filters based on user feedback - and we expect our commercial customers will hold us accountable when our safety features are failing.

But we believe safety is a shared responsibility. Our features are not failsafe, and committed partners are a second line of defense. Depending on your use case, moderation steps will look different, but here are some additional safety recommendations:

- [Use Claude as a content moderation filter](https://docs.claude.com/en/docs/about-claude/use-case-guides/content-moderation) to identify and prevent violations.

- For external-facing products, disclose to your users that they are interacting with an AI system.

- For sensitive information and decision making, have a qualified professional review content prior to dissemination to consumers.

We encourage you to send us feedback or specific proposals to [\[email protected\]](/cdn-cgi/l/email-protection#f88d8b9d8a8b999e9d8c81b899968c908a9788919bd69b9795). For existing commercial partners, we’d recommend [joining our Discord server](https://discord.com/invite/6PPFFzqPDZ) and exchanging ideas with fellow developers as well.

---
## i-m-planning-to-launch-a-product-using-the-claude-api-what-steps-should-i-take-t.md

4. I’m planning to launch a product using the Claude API. What steps should I take to ensure I’m not violating Anthropic’s Usage Policy?

# I’m planning to launch a product using the Claude API. What steps should I take to ensure I’m not violating Anthropic’s Usage Policy?

- [Use Claude as a content moderation filter](https://docs.claude.com/en/docs/about-claude/use-case-guides/content-moderation) to identify and prevent violations.

- For external-facing products, disclose to your users that they are interacting with an AI system.

- For sensitive information and decision making, have a qualified professional review content prior to dissemination to consumers.

We encourage you to send us feedback or specific proposals to [\[email protected\]](/cdn-cgi/l/email-protection#176264726564767172636e577679637f6578677e743974787a). For existing commercial partners, we’d recommend [joining our Discord server](https://discord.com/invite/6PPFFzqPDZ) and exchanging ideas with fellow developers as well.

---
## i-need-to-add-or-update-my-team-plan-s-tax-or-vat-id-db9d66de41.md

# Add or update your Team plan's tax or VAT ID

March 16, 2026

## Add your tax or VAT ID during signup

When you sign up for a Team plan, you may have the option to enter your Tax or VAT ID depending on your location:

1. During the signup process, enter your address information.

2. If your address is eligible for tax purposes, an optional field for your Tax or VAT ID will appear.

3. Enter your Tax or VAT ID in the provided field.

4. If the ID is entered correctly, you'll be able to proceed with your signup.

## Update your tax or VAT ID after signup

**Note**: Updates to your billing details will only apply to future billing cycles. Previously completed invoices cannot be updated retroactively.

If you need to add or update your Tax or VAT ID after you've already signed up, follow these steps:

1. Navigate to your **[Billing Settings](https://claude.ai/settings/billing)**.

2. Click on the "Update" button next to your payment method.

3. In the payment update form, you should see a field to enter or update your Tax or VAT ID.

4. Enter or modify your Tax or VAT ID as needed.

5. Save your changes.

---
## i-need-to-add-or-update-my-team-plan-s-tax-or-vat-id.md

4. Add or update your Team plan's tax or VAT ID

# Add or update your Team plan's tax or VAT ID

## Add your tax or VAT ID during signup

When you sign up for a Team plan, you may have the option to enter your Tax or VAT ID depending on your location:

1. During the signup process, enter your address information.

2. If your address is eligible for tax purposes, an optional field for your Tax or VAT ID will appear.

3. Enter your Tax or VAT ID in the provided field.

4. If the ID is entered correctly, you'll be able to proceed with your signup.

## Update your tax or VAT ID after signup

**Note**: Updates to your billing details will only apply to future billing cycles. Previously completed invoices cannot be updated retroactively.

If you need to add or update your Tax or VAT ID after you've already signed up, follow these steps:

1. Navigate to your **[Billing Settings](https://claude.ai/settings/billing)**.

2. Click on the "Update" button next to your payment method.

3. In the payment update form, you should see a field to enter or update your Tax or VAT ID.

4. Enter or modify your Tax or VAT ID as needed.

5. Save your changes.

---
## manage-costs-effectively-claude-code-docs-7c26178a4f.md

# Manage costs effectively

Track token usage, set team spend limits, and reduce Claude Code costs with context management, model selection, extended thinking settings, and preprocessing hooks.

> ## Documentation Index
>
> Fetch the complete documentation index at: <https://code.claude.com/docs/llms.txt>
>
> Use this file to discover all available pages before exploring further.

Claude Code charges by API token consumption. For subscription plan pricing (Pro, Max, Team, Enterprise), see [claude.com/pricing](https://claude.com/pricing). Per-developer costs vary widely based on model selection, codebase size, and usage patterns such as running multiple instances or automation. Across enterprise deployments, the average cost is around \$13 per developer per active day and \$150-250 per developer per month, with costs remaining below \$30 per active day for 90% of users. To estimate spend for your own team, start with a small pilot group and use the tracking tools below to establish a baseline before wider rollout. This page covers how to [track your costs](#track-your-costs), [manage costs for teams](#managing-costs-for-teams), and [reduce token usage](#reduce-token-usage).

Track your costs

Using the `/usage` command

The Session block in `/usage` shows API token usage and is intended for API users. Claude Max and Pro subscribers have usage included in their subscription, so the session cost figure isn’t relevant for billing purposes. Subscribers see plan usage bars and activity stats on the same screen.

The `/usage` command provides detailed token usage statistics for your current session. The dollar figure is an estimate computed locally from token counts and may differ from your actual bill. For authoritative billing, see the Usage page in the [Claude Console](https://platform.claude.com/usage).

```python
Total cost: $0.55
Total duration (API): 6m 19.7s
Total duration (wall): 6h 33m 10.2s
Total code changes: 0 lines added, 0 lines removed
```

Managing costs for teams

When you first authenticate Claude Code with your Claude Console account, a workspace called “Claude Code” is automatically created for you. This workspace provides centralized cost tracking and management for all Claude Code usage in your organization. You cannot create API keys for this workspace; it is exclusively for Claude Code authentication and usage.For organizations with custom rate limits, Claude Code traffic in this workspace counts toward your organization’s overall API rate limits. You can set a [workspace rate limit](../04-API-Reference/Other/api-rate-limits-28d3302987.md#setting-lower-limits-for-workspaces) on this workspace’s Limits page in the Claude Console to cap Claude Code’s share and protect other production workloads.

On Bedrock, Vertex, and Foundry, Claude Code does not send metrics from your cloud. To get cost metrics, several large enterprises reported using [LiteLLM](/docs/en/llm-gateway#litellm-configuration), which is an open-source tool that helps companies [track spend by key](https://docs.litellm.ai/docs/proxy/virtual_keys#tracking-spend). This project is unaffiliated with Anthropic and has not been audited for security.

Rate limit recommendations

When setting up Claude Code for teams, consider these Token Per Minute (TPM) and Request Per Minute (RPM) per-user recommendations based on your organization size:

| Team size | TPM per user | RPM per user |
|---------------|--------------|--------------|
| 1-5 users | 200k-300k | 5-7 |
| 5-20 users | 100k-150k | 2.5-3.5 |
| 20-50 users | 50k-75k | 1.25-1.75 |
| 50-100 users | 25k-35k | 0.62-0.87 |
| 100-500 users | 15k-20k | 0.37-0.47 |
| 500+ users | 10k-15k | 0.25-0.35 |

For example, if you have 200 users, you might request 20k TPM for each user, or 4 million total TPM (200\*20,000 = 4 million). The TPM per user decreases as team size grows because fewer users tend to use Claude Code concurrently in larger organizations. These rate limits apply at the organization level, not per individual user, which means individual users can temporarily consume more than their calculated share when others aren’t actively using the service.

If you anticipate scenarios with unusually high concurrent usage (such as live training sessions with large groups), you may need higher TPM allocations per user.

Agent team token costs

[Agent teams](/docs/en/agent-teams) spawn multiple Claude Code instances, each with its own context window. Token usage scales with the number of active teammates and how long each one runs. To keep agent team costs manageable:

- Use Sonnet for teammates. It balances capability and cost for coordination tasks.
- Keep teams small. Each teammate runs its own context window, so token usage is roughly proportional to team size.
- Keep spawn prompts focused. Teammates load CLAUDE.md, MCP servers, and skills automatically, but everything in the spawn prompt adds to their context from the start.
- Clean up teams when work is done. Active teammates continue consuming tokens even if idle.
- Agent teams are disabled by default. Set `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in your [settings.json](/docs/en/settings) or environment to enable them. See [enable agent teams](/docs/en/agent-teams#enable-agent-teams).

Reduce token usage

Token costs scale with context size: the more context Claude processes, the more tokens you use. Claude Code automatically optimizes costs through [prompt caching](/docs/en/prompt-caching), which reduces costs for repeated content like system prompts, and auto-compaction, which summarizes conversation history when approaching context limits. The following strategies help you keep context small and reduce per-message costs.

Manage context proactively

Use `/usage` to check your current token usage, or [configure your status line](/docs/en/statusline#context-window-usage) to display it continuously.

- **Clear between tasks**: Use `/clear` to start fresh when switching to unrelated work. Stale context wastes tokens on every subsequent message. Use `/rename` before clearing so you can easily find the session later, then `/resume` to return to it.
- **Add custom compaction instructions**: `/compact Focus on code samples and API usage` tells Claude what to preserve during summarization.

You can also customize compaction behavior in your CLAUDE.md:

```python
# Compact instructions

When you are using compact, please focus on test output and code changes
```

Choose the right model

Reduce MCP server overhead

MCP tool definitions are [deferred by default](/docs/en/mcp#scale-with-mcp-tool-search), so only tool names enter context until Claude uses a specific tool. Run `/context` to see what’s consuming space.

- **Prefer CLI tools when available**: Tools like `gh`, `aws`, `gcloud`, and `sentry-cli` are still more context-efficient than MCP servers because they don’t add any per-tool listing. Claude can run CLI commands directly.
- **Disable unused servers**: Run `/mcp` to see configured servers and disable any you’re not actively using.

Install code intelligence plugins for typed languages

[Code intelligence plugins](/docs/en/discover-plugins#code-intelligence) give Claude precise symbol navigation instead of text-based search, reducing unnecessary file reads when exploring unfamiliar code. A single “go to definition” call replaces what might otherwise be a grep followed by reading multiple candidate files. Installed language servers also report type errors automatically after edits, so Claude catches mistakes without running a compiler.

Offload processing to hooks and skills

Custom [hooks](/docs/en/hooks) can preprocess data before Claude sees it. Instead of Claude reading a 10,000-line log file to find errors, a hook can grep for `ERROR` and return only matching lines, reducing context from tens of thousands of tokens to hundreds. A [skill](/docs/en/skills) can give Claude domain knowledge so it doesn’t have to explore. For example, a “codebase-overview” skill could describe your project’s architecture, key directories, and naming conventions. When Claude invokes the skill, it gets this context immediately instead of spending tokens reading multiple files to understand the structure. For example, this PreToolUse hook filters test output to show only failures:

- settings.json

- filter-test-output.sh

Add this to your [settings.json](/docs/en/settings#settings-files) to run the hook before every Bash command:

```python
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/filter-test-output.sh"
}
]
}
]
}
}
```

The hook calls this script, which checks if the command is a test runner and modifies it to show only failures:

```python
#!/bin/bash
input=$(cat)
cmd=$(echo "$input" | jq -r '.tool_input.command')

Move instructions from CLAUDE.md to skills

Your [CLAUDE.md](/docs/en/memory) file is loaded into context at session start. If it contains detailed instructions for specific workflows (like PR reviews or database migrations), those tokens are present even when you’re doing unrelated work. [Skills](/docs/en/skills) load on-demand only when invoked, so moving specialized instructions into skills keeps your base context smaller. Aim to keep CLAUDE.md under 200 lines by including only essentials.

Adjust extended thinking

Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model. For simpler tasks where deep reasoning isn’t needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, disabling thinking in `/config`, or lowering the budget with `MAX_THINKING_TOKENS=8000`.

Delegate verbose operations to subagents

Running tests, fetching documentation, or processing log files can consume significant context. Delegate these to [subagents](/docs/en/sub-agents#isolate-high-volume-operations) so the verbose output stays in the subagent’s context while only a summary returns to your main conversation.

Manage agent team costs

Agent teams use approximately 7x more tokens than standard sessions when teammates run in plan mode, because each teammate maintains its own context window and runs as a separate Claude instance. Keep team tasks small and self-contained to limit per-teammate token usage. See [agent teams](/docs/en/agent-teams) for details.

Write specific prompts

Vague requests like “improve this codebase” trigger broad scanning. Specific requests like “add input validation to the login function in auth.ts” let Claude work efficiently with minimal file reads.

Work efficiently on complex tasks

For longer or more complex work, these habits help avoid wasted tokens from going down the wrong path:

- **Use plan mode for complex tasks**: Press Shift+Tab to enter [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) before implementation. Claude explores the codebase and proposes an approach for your approval, preventing expensive re-work when the initial direction is wrong.
- **Course-correct early**: If Claude starts heading the wrong direction, press Escape to stop immediately. Use `/rewind` or double-tap Escape to restore conversation and code to a previous checkpoint.
- **Give verification targets**: Include test cases, paste screenshots, or define expected output in your prompt. When Claude can verify its own work, it catches issues before you need to request fixes.
- **Test incrementally**: Write one file, test it, then continue. This catches issues early when they’re cheap to fix.

Background token usage

Claude Code uses tokens for some background functionality even when idle:

- **Conversation summarization**: Background jobs that summarize previous conversations for the `claude --resume` feature
- **Command processing**: Some commands like `/usage` may generate requests to check status

These background processes consume a small amount of tokens (typically under \$0.04 per session) even without active interaction.

Understanding changes in Claude Code behavior

---
## manage-custom-roles-on-enterprise-plans-f8a1b3dabf.md

# Manage custom roles on Enterprise plans

Custom roles are available for Enterprise plan organizations. Owners, Primary Owners, and custom roles with the **Identity & Access** permission set to "Can manage" can go to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)** to manage custom roles.

## What are custom roles?

Custom roles let you define which features your members can access. Each custom role contains a set of permissions that grant or restrict access to specific capabilities like chat, Claude Cowork, Claude Code, and web search, plus the connectors your organization has added, such as Slack or Google Drive. Custom roles can also grant admin permissions, which give members access to specific administrative areas like billing, identity, or privacy without making them Owners.

Custom roles work alongside groups. The typical workflow is: create custom roles, assign them to groups, and then set members' roles to “Custom” so their access is governed entirely by the custom roles assigned to their groups.

**Note:** Custom roles only affect members whose role is set to “Custom.” Members with the User, Admin, or Owner roles get their permissions from those roles directly, not from custom roles.

------------------------------------------------------------------------

## How feature access works

Feature access is determined by a four-level precedence chain, where the most restrictive level wins:

1. **Platform-level overrides**: Some features may be force-enabled or force-disabled for your organization by Anthropic as part of your contract. These can't be changed in organization settings.

2. **Organization-level setting**: An Owner or Primary Owner can toggle a feature on or off for the entire organization. If a feature is disabled at the organization level, no custom role can grant access to it.

3. **Custom role permissions**: If the feature is enabled at the organization level, the member's custom roles determine whether they can access it. If any of the member's custom roles grant the feature, they have it.

4. **User-level setting**: If the feature is granted at the role level, it's available unless the member has disabled it in their own settings.

The key takeaway: the organization-level toggle is a main switch. Custom roles are the per-member switches underneath it. A feature must be enabled at the organization level before custom roles can control who gets access.

**Note:** This precedence chain applies to capabilities. Admin permissions aren't gated by an organization-level toggle or a member's own settings. If a member's custom role grants an admin permission, they have that access.

------------------------------------------------------------------------

## Available capabilities

Each custom role can grant or restrict access to the following capabilities:

[TABLE]

\*Claude Code dynamic workflows are on for your whole organization by default. Because a single run can last for hours and use more tokens than a typical session, decide which roles should have access. For members on custom roles, this capability follows the additive model like any other—a role must grant it for those members to use it. To restrict a specific group, leave this capability off in their role.

This can be disabled organization-wide via `managed-settings.json` by adding `"disableWorkflows": true` to your managed settings.

An owner can turn it off across your entire organization by going to **[Organization settings \> Claude Code](https://claude.ai/admin-settings/claude-code)** and toggling **Workflows** off.

Custom roles also govern admin permissions, connectors, and model access, which are configured on separate **Permissions**, **Connectors**, and **Models** tabs in the role editor. See **[Admin permissions](#h_fde60b08bd)**, **[Connector permissions](#h_979e558d00)**, and **[Model access](#h_fca0f9a6b5)** below.

**Note:** Chat is enabled by default for all custom roles, including ones created before this capability was added. If you want to restrict chat for a specific role, toggle it off when editing the role.

### Grant all capabilities at once

Instead of toggling capabilities individually, you can grant a role every capability. When creating or editing a role, choose an option on the **Capabilities** tab for **Capability access**:

- **All capabilities:** Grants the role every capability, including capabilities in beta and research preview.

- **All generally available:** Grants the role every generally available capability.

Roles set to either option pick up new capabilities automatically as they launch. Roles set to “Only selected” only include the capabilities you select.

------------------------------------------------------------------------

## Create a custom role

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Click “Add role.”

3. Enter a name for the role (for example, “Developer,” “Standard Access,” or “Restricted”).

4. Select the groups you want to assign to the role.

5. Toggle each capability on or off to define what this role grants, or choose "All capabilities" or "All generally available" to grant every capability at once.

6. Configure permissions. You can choose No access, Can view, and Can manage for each admin setting.

7. Configure connectors. You can choose Always allow, Needs approval, or Blocked for all connectors, or customize per connector or connector tool.

8. Configure models. Select which models this role can use, optionally set a maximum effort level per model, and optionally choose a default model for the role.

9. Click “Save role.”

## Edit a custom role

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Click the role you want to edit.

3. Update the name and groups, or toggle capabilities, permissions, connectors, and models as needed.

4. Click “Save role” to save your changes.

Role changes may take up to 15 minutes to take effect, and members may need to refresh their browser. All members in groups assigned to this role are affected.

## Delete a custom role

Click the menu button on any custom role and select “Delete role.” Deleting a role removes its permissions from all groups it was assigned to. Members in those groups lose the permissions the role granted, unless another role in their chain also grants them.

------------------------------------------------------------------------

## Assign groups to custom roles

Custom roles are assigned to groups, not directly to individual members. To assign a group to a role:

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Click the role you want to assign.

3. In the groups selector, select one or more groups.

4. Click "Save role."

You can also assign custom roles when creating or editing a group in **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)**. See **[Manage groups and group spend limits on Enterprise plans](https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans)**.

------------------------------------------------------------------------

## How permissions combine across multiple roles

If a member belongs to multiple groups with different custom roles, their permissions are **additive**—they get the union of all permissions from all roles in their chain. If any role grants a feature, the member has access to it.

This means you can't use one role to remove a permission granted by another role. This is by design — it enables a layered approach where a base role covers common features and additional roles layer on specific capabilities and admin permissions.

**Example:** A member is in two groups. The "All Users" group is assigned a "Standard Access" role with web search and memory. The "Engineering" group is assigned a "Developer" role with Cowork and Claude Code. The member gets all four: web search, memory, Cowork, and Claude Code.

------------------------------------------------------------------------

## See a member or group's effective role

When a member belongs to several groups whose roles grant different capabilities, it can be hard to tell what they can actually do. The "View effective role" option shows the combined result: every capability, admin permission, and connector the member has, with the role that grants each one.

1. Navigate to **[Organization settings \> Members](https://claude.ai/admin-settings/members)** (or **[Organization settings \> Groups](https://claude.ai/admin-settings/groups)**).

2. Find the member or group and open the "⋮" menu on the right side of their row.

3. Select "View effective role."

The modal lists the member's assigned roles and three tabs:

- **Capabilities:** each capability with a "Granted by *\[role name\]*" label showing which role turned it on.

- **Permissions:** each admin permission area with its effective level (No access, Can view, or Can manage) and which role grants it.

- **Connectors:** each connector's effective permission level and which role grants it.

This view is read-only. To change what a member can do, edit the roles assigned to their groups.

**Note:** "View effective role" appears only for members whose role is set to "Custom" and who have at least one custom role assigned through a group. Members with a built-in role (User, Admin, Owner, or Primary Owner) get their permissions from that role directly, so there's nothing to compute.

------------------------------------------------------------------------

## Admin permissions

Custom roles can grant admin permissions in addition to capabilities and connector permissions. Admin permissions give members access to specific administrative areas, like billing or privacy, without making them Owners. You can configure admin permissions in the **Permissions** tab of the role editor.

**Note:** Admin permissions only apply to members whose role is set to "Custom." Members with the User, Admin, Owner, or Primary Owner roles keep the access those roles grant.

### Admin permission levels

On the **Permissions** tab, you set each permission area to one of three levels:

- **No access:** The member doesn't see this area in their organization settings.

- **Can view:** View grants read-only access. The member sees the same pages and settings as someone who can manage that area, but every control is disabled or shown as read-only. Use this permission level for compliance reviewers, finance auditors, security teams, or anyone who needs to see the configuration without changing it.

- **Can manage:** Manage grants full read and write access to the area and includes view access.

Within an area, you grant all of View or all of Manage. You can't grant or restrict individual pages or settings.

### Available admin permissions

There are seven admin permission areas:

[TABLE]

**Note:** A role with **Identity & Access** set to "Can manage" can create and edit groups and roles, including its own role definition. Members with this permission can expand their own access, so reserve it for trusted security and IT administrators.

### Available organization settings pages for each permission

[TABLE]

### What admin permissions don't cover

The following remain available only to Owners and Primary Owners, even for members with admin permissions:

- **Managing Owners and Admins.** Admin permissions can't grant or revoke the Owner, Admin, or Primary Owner built-in roles. Only Owners can manage other Owners.

- **API keys and workspaces.** API key management, workspace settings, and Claude Console administration aren't covered by admin permissions.

- **Compliance and security keys.** Compliance API settings and security-key administration remain Owner-only.

- **Organization-level capability settings.** Which capabilities are enabled at the organization level is governed separately and isn't part of admin permissions.

### What members see when admin permissions are restricted

If a member doesn’t have access to a specific admin permission, the section doesn't appear in their organization settings. Only sections their permissions cover are shown.

------------------------------------------------------------------------

## Connector permissions

Custom roles also control which connectors, and which tools on those connectors, a role can use. Where capabilities cover Claude’s built-in features, connector permissions cover the apps and services you’ve connected to your organization, such as Slack, Google Drive, or Jira. You set them on the **Connectors** tab of the role editor, next to the **Capabilities** and **Permissions** tabs.

**Note:** Connector permissions apply only to members whose role is set to “Custom.” Members with the User, Admin, or Owner roles see every connector enabled for your organization, subject to your organization-wide tool policies per connector. Owners and Admins always see every connector so they can configure it, regardless of any role’s connector permissions.

### Permission levels

On the **Connectors** tab, you set all connectors, each connector, or each tool on a connector, to one of three levels:

- **Always allow:** Every tool on the connector is available, and members can set their own approval to “Always allow” to skip the per-call confirmation.

- **Needs approval:** Every tool is available, but members confirm each call. The “Always allow” option is removed from their personal approval menu for these tools.

- **Blocked:** The connector or tool is hidden. Claude can’t see it or call it.

A connector can also be set to **Custom**, which lets you set each of its tools individually. For the full setup, see **[Set up role-based permissions on Enterprise plans](https://support.claude.com/en/articles/13930458-)**.

### How connector access is determined

A connector or tool passes through several layers before a member can use it, evaluated in this order:

1. **Role grant.** Each connector or tool on a role is set to “Always allow,” “Needs approval,” or “Blocked.”

2. **Across the member’s roles.** If a member’s groups give them more than one role, the most permissive grant for each tool applies. Connector permissions are additive across roles, the same as capabilities.

3. **Organization-wide tool policy.** The per-tool policy you set under **[Organization settings \> Connectors](https://claude.ai/admin-settings/connectors)** per connector is the ceiling. For each tool, Claude compares the member’s role grant to this policy and applies the stricter of the two. Role grants narrow access within the policy; they can’t widen past it. Learn more about setting tool access in **[Use connectors to extend Claude’s capabilities](https://support.claude.com/en/articles/11176164-use-connectors-to-extend-claude-s-capabilities)**.

4. **The member’s own setting.** The result of the steps above is the member’s effective ceiling. It limits the options in their personal per-tool approval menu (“Always allow,” “Ask,” or “Never”). A ceiling of “Needs approval” removes “Always allow.” A ceiling of “Blocked” grays the tool out.

For members using Claude Code, one more layer applies: Managed Settings policies and connector permissions compose by most-restrictive. A tool is callable without a prompt only when both allow it. For more information, see **[Claude Code settings](https://code.claude.com/docs/en/settings#settings-files)**.

For members using Claude Cowork, write-capable connector tools pass through one more gate. See **[Cowork approval setting for write tools](#h_85bd7c30e9)** below.

This table shows how the organization-wide tool policy and a member’s role grant combine:

[TABLE]

### Cowork approval setting for write tools

Claude Cowork has a separate organization setting, **Allow "Always allow" for connector tools**, that gates write-capable connector tools. It's off by default, and custom role grants can't override it: even when the organization-wide tool policy and every role grant are set to "Always allow," members approve these tools per task in Cowork until the setting is turned on. Learn more about **[connector tool approvals in Cowork](https://support.claude.com/en/articles/13455879-use-claude-cowork-on-team-and-enterprise-plans#h_1bd1fa754d)**.

### Where connector permissions apply

Connector permissions are enforced on Anthropic’s servers, so they apply across every Claude surface that routes connector traffic through Anthropic:

[TABLE]

Connector permissions govern connectors your organization has added under **[Organization settings \> Connectors](https://claude.ai/admin-settings/connectors)**. They don’t govern connectors a member runs locally on their own machine, and they don’t govern Claude Cowork when it’s deployed on a third-party platform. For third-party Cowork deployments, use MDM instead. See **[Cowork on 3P: MCP, plugins, skills, and hooks](https://claude.com/docs/cowork/3p/extensions).**

### What members see when a connector is restricted

[TABLE]

Members can’t tell which layer restricted a tool. The message is the same whether the limit comes from the organization-wide tool policy, a role grant, or both. To find the source, compare the organization-wide policy with the member’s role grants.

------------------------------------------------------------------------

## Model access

Custom roles also control which Claude models a role can use and the maximum effort level members can select on each one. You set these on the **Models** tab of the role editor, alongside the role's default model.

The organization-level model setting is the ceiling. A role can't grant a model that's disabled at the organization level. Across a member's roles, model access is additive and effort limits take the highest cap any role allows. Haiku models are always available and can't be disabled.

For setup steps and what members see, see **[Manage model access for your organization](https://support.claude.com/en/articles/15694740)**. For default model behavior, see **[Set a default model for your organization](https://support.claude.com/en/articles/15330088)**.

------------------------------------------------------------------------

## What members see when capability access is restricted

When a capability is restricted, here’s what members see. For connector and tool restrictions, see **[Connector permissions](#h_979e558d00)** above.

[TABLE]

---
## manage-extra-usage-for-paid-claude-plans-f6c37e2de4.md

# Manage usage credits for paid Claude plans

May 18, 2026

## What are usage credits?

------------------------------------------------------------------------

## How usage credits work

When you reach your plan’s usage limit with usage credits enabled:

- You’ll see a notification that you’ve reached your session usage limit.

- If usage credits are enabled and you have funds available, you can choose to continue working.

- Your subsequent usage will be billed at standard API pricing rates.

- Your session limits reset every five hours as usual.

**Note:** Usage credits are charged separately from your paid Claude subscription and appear as additional charges on your bill.

------------------------------------------------------------------------

## Enabling usage credits

To enable usage credits on your paid Claude plan:

1. Navigate to [**Settings \> Usage**](https://claude.ai/settings/usage) in your Claude account.

2. Locate the **Usage credits** section.

3. Click "Enable" to turn on usage credits.

4. Set up your payment method if not already configured.

5. Configure your spending preferences.

6. Click “Adjust limit” to control costs with a monthly spend limit. You can also select “Set to unlimited” if you prefer no spending restrictions.

7. You’ll then need to prepay to cover usage beyond your plan limits. Click “Add funds,” enter the amount you want to purchase in the modal, then click “Purchase.”

8. You can also enable auto-reload to automatically make a purchase when your balance falls below a threshold you set:

**Note:** There is a daily redemption limit of \$2000.

------------------------------------------------------------------------

## Set spend limits

Control your usage credit spending with:

- **Monthly spending cap:** Set a maximum amount you're willing to spend on usage credits each month.

- **Auto-reload settings:** Automatically add funds when your balance drops below a threshold.

- **Usage alerts:** Receive notifications when approaching your spend limits.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Managing your usage credits

### Monitoring usage and costs

Track your usage credits through:

- **Usage dashboard:** View real-time consumption in **[Settings \> Usage](https://claude.ai/settings/usage)**.

- **Current spending:** Monitor your month-to-date usage credit costs.

- **Usage history:** Review past consumption patterns to optimize future usage.

## Tips for cost-effective usage

To manage usage credit costs while maintaining productivity:

- **Choose efficient models:** Use our most efficient Haiku model, or the most recent Sonnet model for most tasks. These provide excellent performance at lower token costs than Opus models.

- **Use your plan’s included usage first:** Plan intensive work sessions around your five-hour usage windows.

- **Start new conversations:** Begin fresh chats for new topics to minimize the size of your context window.

- **Use projects effectively:** Store frequently referenced documents in project knowledge instead of re-uploading.

- **Set appropriate limits:** Start with conservative spending caps and adjust based on your needs.

------------------------------------------------------------------------

## How usage credits work with other features

### Claude Code

Usage credits apply to both Claude conversations and Claude Code terminal usage. Your combined usage across both interfaces counts toward your limits.

### Research mode

When using Research mode, usage credits apply once you exceed your plan's included limits. Research sessions may consume tokens more quickly due to multiple searches and comprehensive analysis.

### Projects and files

Documents stored in project files count toward your context when used in conversations. Usage credits apply to all tokens processed, including project content.

------------------------------------------------------------------------

## Frequently asked questions

### Can I disable usage credits after enabling them?

Yes, you can disable usage credits at any time through **[Settings \> Usage](https://claude.ai/settings/usage)**. Once disabled, you'll only have access to your plan's included usage.

### How quickly do my regular usage limits reset?

Your plan’s included usage limit will reset every five hours once you reach it. Usage credits don’t affect this reset timing.

### I subscribed to a paid Claude plan on the App or Play store; how can I access usage credits?

### Can I track usage credits separately from my included usage?

Yes, the usage dashboard clearly distinguishes between your included plan usage limits and any usage credit consumption.

### Will I get a warning before switching to usage credits?

Yes, you’ll see a clear notification when approaching and reaching your included usage limits, with a confirmation that you’ll continue with usage credits.

---
## manage-extra-usage-for-team-and-seat-based-enterprise-plans-dff5902d37.md

# Manage usage credits for Team and seat-based Enterprise plans

May 18, 2026

## What are usage credits?

------------------------------------------------------------------------

## How usage credits work

**For Team plans:** Owners can pre-purchase usage credits that they can control using spend limits.

**For seat-based Enterprise plans:** Usage credits are billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable usage credits

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to pay for usage credits.

5. Next, you'll see the option to enable auto-reload; choose "Reload when balance reaches" and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable usage credits for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to usage credits once they're enabled?

Once an organization owner has enabled usage credits:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your usage credit consumption will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

### Spend limits

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Owners and Primary Owners on **seat-based Enterprise plans only** can set spend limits that apply to all users within a specific seat tier.

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the "..." button next to the user, then "Edit limit."

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members' usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Request usage credits for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request usage credits" link upon hitting their included usage limit.

### Disable usage credit requests

If you want to prevent users from submitting requests for usage credits, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Usage credit requests**.

3. Toggle it off.

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my spend limit?

### Why was I able to exceed my spend limit?

### Can usage credits be disabled completely?

---
## manage-extra-usage-for-team-and-seat-based-enterprise-plans.md

4. Manage extra usage for Team and seat-based Enterprise plans

# Manage extra usage for Team and seat-based Enterprise plans

## What is extra usage?

------------------------------------------------------------------------

## How extra usage works

**For Team plans:** Owners can pre-purchase extra usage that they can control using spend limits.

**For seat-based Enterprise plans:** Extra usage is billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable extra usage

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click “Enable” in **Extra usage** to turn this on for your organization.

4. You’ll be prompted to pay for extra usage.

5. Next, you’ll see the option to enable auto-reload; choose “Reload when balance reaches” and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable extra usage for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click “Enable” in **Extra usage** to turn this on for your organization.

4. You’ll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to extra usage once it's enabled?

Once an organization owner has enabled extra usage:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your extra usage will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

### Spend limits

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Clicking that icon opens a modal where you can either input an amount and click “Set limit,” or click “Set to unlimited” to remove the limit for that seat type:

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the “...” button next to the user, then “Edit limit”:

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members’ usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Extra usage pricing

Extra usage is billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

------------------------------------------------------------------------

## Request extra usage for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request extra usage" link upon hitting their included usage limit:

### Disable extra usage requests

If you want to prevent users from submitting requests for extra usage, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Extra usage requests**.

3. Toggle it off:

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my extra usage limit?

### Why was I able to exceed my extra usage limit?

### Does extra usage apply to Claude, Cowork, and Claude Code?

Yes, extra usage applies to Claude, Cowork, and Claude Code.

### Can extra usage be disabled completely?

---
## manage-groups-and-group-spend-limits-on-enterprise-plans-fd3f391cc6.md

# Manage groups and group spend limits on Enterprise plans

Groups and group spend limits are available for Enterprise plan organizations. Owners, Primary Owners, and custom roles with the **Identity & Access** permission set to "Can manage" can go to **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)** to manage groups. Owners, Primary Owners, and custom roles with the **Billing** permission set to "Can manage" can go to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)** to manage group spend limits. Group visibility settings are currently in beta.

## What are groups?

Groups let you organize members into logical collections—by team, department, or any other grouping that fits your organization. Once groups are set up, you can:

- **Set spend limits for groups**, so all members of a group share a per-user spend limit.

- **Control member access through group memberships and custom roles**, so their capabilities and permissions are determined entirely by the groups they belong to. For additional details, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)**.

- **Let members share projects with a group**, so a project shared with the group is available to everyone in it, and access follows membership as it changes. For details, see [**Manage project visibility and sharing**](https://support.claude.com/en/articles/9519189-manage-project-visibility-and-sharing).

Groups can be created manually or synced automatically from your identity provider via SCIM. Each organization can have up to 100 groups. There's no limit on how many groups a member can belong to, though belonging to more than 250 can slow performance.

In addition to spend limits, Enterprise admins can use groups to control plugin access in Cowork. Each plugin in your organization's marketplace can have group-level overrides that determine whether it's available, pre-installed, required, or hidden for members of a specific group. For details, see **[Manage Cowork plugins for your organization](https://support.claude.com/en/articles/13837433-manage-cowork-plugins-for-your-organization)**.

------------------------------------------------------------------------

## Create a group

1. Navigate to **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)**.

2. Click "Add group."

3. Enter a **Group name**.

4. Optionally enter a **Display name**. The display name replaces the group name on in-product surfaces, like the project sharing picker. Leave it blank to use the group name.

5. Select which custom roles to assign to this group (optional).

6. Under **Visibility settings**, choose who can discover the group, share resources like projects with it, and see its members (optional).

7. Search for and add members, or click "Add all members" to add everyone in your organization.

8. Click "Add group."

**Note:** If SCIM directory sync is enabled, you’ll see a “SCIM Sync” button next to "Add group." Clicking this will manually refresh groups from your identity provider.

## Edit a group

Click any group in the list to open its edit form. You can change the group name and display name, update custom role assignments, change visibility settings, and add or remove members.

To change settings for several groups at once, select them with the checkboxes in the groups list, then click the "Edit settings" button that appears.

**Note:** Groups synced from your identity provider via SCIM can't be renamed or deleted in Claude, and their members are managed in your identity provider.

## Delete a group

Click the menu button to the right of any group and select "Delete." Deleting a group doesn't affect the custom roles that were assigned to it and doesn't remove any members from your organization. Deleting a group also removes its access to any projects shared with it. Members lose access to those projects unless they have access another way.

------------------------------------------------------------------------

## SCIM group sync

If your organization uses SCIM directory sync, groups from your identity provider are automatically synced to Claude. SCIM groups appear with a sync indicator in the groups list.

SCIM groups support custom role assignments and spend limits the same way as manually created groups.

To manually trigger a sync, click “SCIM Sync."

**Note:** Claude supports direct group memberships only. If your identity provider nests groups inside other groups, those relationships are ignored when memberships are pushed via SCIM, and only direct members appear in Claude. Some providers flatten nested memberships before pushing them, which makes members of child groups appear as direct members. Check your provider's SCIM behavior to confirm.

------------------------------------------------------------------------

## Group visibility

Group visibility settings are currently in beta.

By default, groups appear only on admin surfaces. Visibility settings let you make a group discoverable to members so they can share resources (like projects) with it. You set them in the **Visibility settings** section when creating or editing a group.

There are three settings:

- **Discover this group:** Members can find the group by name. This doesn't expose group members, spend limits, or role assignments.

- **Share projects with this group:** Members can share resources, such as projects, with the group.

- **See group members:** Members can see who belongs to the group, by name and email address.

For each setting, select **Group members** to grant it to members of that group, or **Everyone** to grant it to everyone in your organization. Leave both unchecked to keep the setting off.

Visibility settings don't affect admin access. Owners, Primary Owners, and custom roles with **Identity & Access** access always see every group.

The **Visibility** column in the groups list shows each group's current state. New visibility settings can take a few minutes to appear in-app.

**Important:** Visibility settings are configured per organization. Groups, group membership, and SCIM sync are managed at the parent organization level and shared across child organizations, but visibility settings aren't. An admin changing visibility settings in one organization doesn't affect any other organization.

### Remove a group's access to shared projects

Turning off **Share projects with this group** blocks new shares. It doesn't revoke projects already shared with the group. To revoke those:

1. Open the group's edit form.

2. Under **Visibility settings**, select "Remove this group's access to all \[number\] projects."

3. Save the group.

This revokes existing shares only. It doesn't block future sharing, so turn off **Share projects with this group** as well if you want both.

**Note:** Removing a group's access runs in the background. For groups with more than 1000 shared projects, it can take several minutes or longer.

------------------------------------------------------------------------

## Control member access with custom roles

You can control individual members' feature access entirely through groups and custom roles. When a member's role is set to **Custom**, they have no default capabilities or permissions—their access is determined entirely by the custom roles assigned to their groups. This is different from the User, Admin, or Owner roles, which include built-in permissions.

### Set a member's role to Custom

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Find the member and click their role dropdown.

3. Select "Custom."

Owners, Primary Owners, and custom roles with the **User Management** permission set to "Can manage" can change member roles. You can also assign “Custom” at scale by mapping an IdP group using **[group mappings](https://support.claude.com/en/articles/13133195-set-up-jit-or-scim-provisioning)**.

### Recommended setup

1. Create custom roles with the desired permissions in **[Organization settings \> Roles](http://claude.ai/admin-settings/roles)**. For details, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452)**.

2. Create groups in **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)** (or sync them from your identity provider).

3. Assign custom roles to groups.

4. Add members to the appropriate groups.

1. **Note:** If a member set to a Custom role isn't in any groups, or their groups have no custom roles assigned, they have no permissions and can't access any products. They'll land on their settings page when they sign in.

5. Set each member's organization role to **Custom**.

6. Enable any features at the organization level that you want to control per-group.

The member's effective permissions are now determined by their group memberships and the custom roles assigned to those groups.

**Important:** Always complete steps 1–5 before enabling features at the organization level (step 6). If you enable a feature before changing members' roles to Custom and assigning appropriate custom roles, there's a brief window where some members could access the feature through their previous role. For a detailed walkthrough, see **[Set up role-based permissions on Enterprise plans](https://support.claude.com/en/articles/13930458-set-up-role-based-entitlements-on-enterprise-plans)**.

### Invite new members

When inviting a new member, Owners, Primary Owners, and custom roles with the **User Management** permission set to "Can manage" can select "Custom” as the role.The new member's access is determined by their group memberships after they join.

------------------------------------------------------------------------

## Group spend limits

Group spend limits let you control spending across your organization by assigning per-user monthly spend limits to groups. Instead of setting spend limits for each member individually, you can set a limit on a group and have it apply to every member of that group.

Group spend limits work alongside individual spend limits. If a member has an individual spend limit set, their individual limit takes precedence over any group limit.

## Set a group spend limit

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Select the “By group” tab.

3. Find the group and click the menu button to the right, then “Edit limit”

4. Select “Unlimited,” or “Set dollar amount” and enter a dollar amount for the spend limit.

5. Click "Set limit."

The spend limit applies to all members of the group. Members who also have an individual spend limit set are governed by their individual limit instead.

## Choose how multi-group spend limits resolve

If a member belongs to more than one group with a spend limit, the **Multi-group spend limit** setting controls which limit applies.

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Find **Multi-group spend limit** in the **Spending defaults** section.

3. Select "Higher group limit" or "Lower group limit" from the dropdown.

Select "Lower group limit" to set a broad limit on a large group and create subgroups with tighter budgets. Select "Higher group limit" to set a conservative baseline on a large group and grant more headroom to specific teams.

## How spend limits are resolved

When determining a member's effective spend limit, the system evaluates in this order:

1. **Individual limit**—if the member has an individual spend limit set, that limit applies regardless of group membership.

2. **Group limit**—if the member has no individual limit, the system checks their group memberships. If the member belongs to multiple groups with spend limits, your **Multi-group spend limit** setting determines whether the higher or lower limit applies.

3. **No limit**—if the member has no individual limit and belongs to no groups with spend limits, no spend limit is applied.

---
## manage-members-on-team-and-enterprise-plans-ae927760ef.md

# Manage members on Team and Enterprise plans

This guide covers how to add, remove, and manage the people on your Team or Enterprise plan.

**Permissions note:** Organization Admins can manage members in **[Organization settings \> Members](http://claude.ai/admin-settings/members)**, but only Owners and Primary Owners can access **[Organization](https://claude.ai/admin-settings/organization) [settings \> Billing](https://claude.ai/admin-settings/billing)**. For more information, see our article about **[roles and permissions](https://support.claude.com/en/articles/9267276-roles-and-permissions)**.

For information on purchasing seats or adjusting your plan's seat allocation, see our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](https://support.claude.com/en/articles/13393991-purchasing-and-managing-seats-on-enterprise-plans)**.

------------------------------------------------------------------------

## Add members

### Add members by invitation

**Note:** Pending invitations occupy your available seats immediately; a new member does not need to accept the invite to take up a seat.

Admins and above can add members by following these steps:

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)** and click “Add member.”

2. Enter the person's email address (it must use one of your organization's **[allowed email domains](https://support.claude.com/en/articles/13325567-account-management-faqs#h_b54c41c86c)**).

3. Select the appropriate seat type.

4. Set the role and permissions for the member.

1. **Note:** On Enterprise plans, you can also select “Custom” as a member’s role. Members set to this role have their access controlled through group memberships and custom roles. To see exactly what a custom role member can access, open the “**⋮**” menu on the right side of their row and select "View effective role." For details, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)**.

5. Click “Add members.”

This sends an email invitation to the person. The invitation expires after 21 days, so you'll need to re-invite them if they don't accept within that time period.

**Add multiple members at once:** You can invite multiple members by clicking "Bulk add" and typing or pasting email addresses separated by commas or new lines.

**Note:** The seat type selector only shows seat types your plan already owns. If all seats of the selected type are assigned, you'll be prompted to purchase one. See our guides for **[Team plans](https://support.claude.com/en/articles/12004354)** and **[Enterprise plans](https://support.claude.com/en/articles/13393991)** for more information.

### Add members via organization discovery

Members can also join your organization on their own through organization discovery. When you enable discoverability, colleagues with a matching email domain can find your organization during signup and request to join—no invitation needed. You can configure whether they're added automatically or require your approval. See **[Find and join a Team or Enterprise organization](https://support.claude.com/en/articles/13566435-organization-discovery)** for details.

### Share an invite link

Admins and above can generate a shareable invite link and distribute it to teammates—for example, by posting it in a Slack channel, email thread, or team wiki—without needing to enter individual email addresses.

**Availability:**

- **Team plans:** Invite links are enabled by default for new organizations.

- **Enterprise plans (non-SSO):** Invite links are disabled by default. Admins can enable them in **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

- **SSO organizations:** Invite links are not available. Member provisioning is managed through your Identity Provider.

To find and copy your invite link, navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**. New members who join via link are assigned to the lowest available seat tier, defaulting to a standard seat if none are available.

Admins can disable the link at any time—this immediately invalidates all existing links. Regenerating the link also invalidates the previous one.

For more details on how the joining flow works, see **[Join an organization via invite link](https://support.claude.com/en/articles/13776697-join-an-organization-via-invite-link)**.

### Automated provisioning with SSO

Organizations with single sign-on (SSO) configured can automate member provisioning. Learn more about **[setting up SSO](https://support.claude.com/en/articles/13132885-setting-up-single-sign-on-sso-for-claude-and-claude-console)**.

- **Just-in-time (JIT) provisioning:** Members assigned to the Anthropic app in your Identity Provider will have accounts created automatically the first time they log in. On plans with multiple seat types, users are assigned to the highest-available seat type upon first login. On single-seat Enterprise plans, users are automatically assigned the Enterprise seat. Admins and above can manually reassign seat types afterward in **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

- **SCIM provisioning (Enterprise plan only):** With SCIM directory sync enabled, members assigned to the Anthropic app in your Identity Provider are provisioned automatically, up to the number of total seats on your plan. On plans with multiple seat types, seat types are distributed from highest to lowest available. On single-seat Enterprise plans, all users are automatically assigned the Enterprise seat. Primary Owners and Owners can reassign seat types afterward in **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

**Important:** An Owner or Primary Owner must ensure seats are available before new users can be provisioned. We recommend monitoring your seat usage and adding seats proactively to ensure uninterrupted access for your team. You can **[enable group mappings with JIT or SCIM](https://support.claude.com/en/articles/13133195-setting-up-jit-or-scim-provisioning#h_adee31eeba) to provision users directly to a specific role and seat tier**.

------------------------------------------------------------------------

## Member-to-member invites

Organization members can invite teammates by email, even if they aren't admins. This makes it easier for your team to grow organically without requiring admin involvement for every new member.

### How it works

Any member can access the invite flow from the account selector in Claude. They enter a teammate's email address and submit the invite. What happens next depends on your organization's new member approval setting:

- **Approve one-by-one (default):** The invite request goes to an admin for review. The invite is only sent to the teammate after an admin approves it.

- **Approve automatically:** The invite is sent right away and the invitee can join immediately.

Invites sent by members follow the same domain restrictions as other join methods — the invitee's email must match one of your organization's allowed domains.

### Availability

- **Team plans:** Member-to-member invites are enabled by default for new organizations.

- **Enterprise plans:** Member-to-member invites are disabled by default. Admins can enable them from Admin settings.

### Admin controls

Admins can enable or disable member-to-member invites from the admin settings. When disabled, only admins can send invitations. Invitees added through member invites are assigned the default member role and placed in the lowest available seat tier.

------------------------------------------------------------------------

## Remove members

You can remove a member by navigating to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**, clicking the menu button to the right of the member, then selecting "Remove from team."

For Enterprise organizations using SCIM provisioning, members are automatically removed from Claude when they are removed from your Identity Provider.

When a member is removed:

- They lose access to the organization immediately.

- The seat they occupied becomes available to assign to another user.

- If you re-add the member later using the same email address, their account history will be maintained.

Removing a member frees up their seat for reassignment, but does not automatically reduce your plan's total seat count. See our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](https://support.claude.com/en/articles/13393991-purchasing-and-managing-seats-on-enterprise-plans)** for information on reducing seats.

**Note:** You cannot remove yourself as a Primary Owner or Owner. Another Primary Owner or Owner must remove you from the team.

------------------------------------------------------------------------

## Export member data

Admins and above can export a CSV of your organization's current member list from your organization settings.

The export includes member details such as name, email address, role, and seat type. This is useful for auditing membership, reconciling seat usage, or maintaining an external record of your team.

To export:

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Click the "Export CSV" button at the top of the **Members** section.

3. A CSV file will download to your device.

------------------------------------------------------------------------

## Manage invitations

### Resend an expired invitation

You can resend an invite from **[Organization settings \> Members](http://claude.ai/admin-settings/members)**. Click the “Pending” tab, find the member, and select to resend the invite.

### Revoke a pending invitation

You can revoke a pending invite from **[Organization settings \> Members](http://claude.ai/admin-settings/members)**. Click the “Pending” tab, find the member, and select "Remove from team."

------------------------------------------------------------------------

## Frequently asked questions

### Can I invite someone who already uses Claude personally with their work email?

Yes. Once they join your team, they'll have both a personal account and a Team or Enterprise plan account. They can toggle between accounts through the menu by clicking their initials or name in the lower left corner.

### How do I add a member that I previously removed?

To add a member that you previously removed, follow the same steps as adding a new member. Their account history will be maintained.

### How do I change the Primary Owner?

The current Primary Owner can transfer ownership by:

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Click the Role dropdown next to the new user and select "Primary Owner."

3. Type the new Primary Owner's email address in the modal to confirm and transfer ownership.

**Important:** There can only be one Primary Owner per organization. Following these steps transfers the role to a different user.

### What happens to the initial invitation for a new Enterprise organization?

When Anthropic provides a new Enterprise organization and invites the Primary Owner, the same 21-day expiration period applies to that initial invitation. If your invitation has expired, please reach out to your account manager.

---
## manage-members-on-team-and-enterprise-plans.md

4. Manage members on Team and Enterprise plans

# Manage members on Team and Enterprise plans

This guide covers how to add, remove, and manage the people on your Team or Enterprise plan.

**Permissions note:** Organization Admins can manage members in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, but only Owners and Primary Owners can access **[Organization](https://claude.ai/admin-settings/organization)** **[settings \> Billing](https://claude.ai/admin-settings/billing)**. For more information, see our article about **[roles and permissions](https://support.claude.com/en/articles/9267276-roles-and-permissions)**.

For information on purchasing seats or adjusting your plan's seat allocation, see our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](purchasing-and-managing-seats-on-enterprise-plans.md)**.

------------------------------------------------------------------------

## Add members

### Add members by invitation

**Note:** Pending invitations occupy your available seats immediately; a new member does not need to accept the invite to take up a seat.

Admins and above can add members by following these steps:

1. Navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)** and click “Add member.”

2. Enter the person's email address (it must use one of your organization's **[allowed email domains](../21-Account-Support/account-management-faqs.md#h_b54c41c86c)**).

3. Select the appropriate seat type.

4. Set the role and permissions for the member.

5. Click “Add members.”

This sends an email invitation to the person. The invitation expires after 21 days, so you'll need to re-invite them if they don't accept within that time period.

**Add multiple members at once:** You can invite multiple members by clicking "Bulk add" and typing or pasting email addresses separated by commas or new lines.

**Note:** If you don't have an available seat of the selected type, you'll be prompted to purchase one. See our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](purchasing-and-managing-seats-on-enterprise-plans.md)** for more information.

### Add members via organization discovery

Members can also join your organization on their own through organization discovery. When you enable discoverability, colleagues with a matching email domain can find your organization during signup and request to join—no invitation needed. You can configure whether they're added automatically or require your approval. See **[Find and join a Team or Enterprise organization](../13-Enterprise-Admin/organization-discovery.md)** for details.

### Share an invite link

**Availability:**

- **Team plans:** Invite links are enabled by default for new organizations.

- **Enterprise plans (non-SSO):** Invite links are disabled by default. Admins can enable them in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

- **SSO organizations:** Invite links are not available. Member provisioning is managed through your Identity Provider.

To find and copy your invite link, navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**. New members who join via link are assigned to the lowest available seat tier, defaulting to a standard seat if none are available.

Admins can disable the link at any time—this immediately invalidates all existing links. Regenerating the link also invalidates the previous one.

For more details on how the joining flow works, see **[Join an organization via invite link](https://support.claude.com/en/articles/13776697-join-an-organization-via-invite-link)**.

### Automated provisioning with SSO

Organizations with single sign-on (SSO) configured can automate member provisioning. Learn more about **[setting up SSO](../21-Account-Support/setting-up-single-sign-on-sso-for-claude-and-claude-console.md)**.

- **Just-in-time (JIT) provisioning:** Members assigned to the Anthropic app in your Identity Provider will have accounts created automatically the first time they log in. On plans with multiple seat types, users are assigned to the highest-available seat type upon first login. On single-seat Enterprise plans, users are automatically assigned the Enterprise seat. Admins and above can manually reassign seat types afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

- **SCIM provisioning (Enterprise plan only):** With SCIM directory sync enabled, members assigned to the Anthropic app in your Identity Provider are provisioned automatically, up to the number of total seats on your plan. On plans with multiple seat types, seat types are distributed from highest to lowest available. On single-seat Enterprise plans, all users are automatically assigned the Enterprise seat. Primary Owners and Owners can reassign seat types afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

**Important:** An Owner or Primary Owner must ensure seats are available before new users can be provisioned. We recommend monitoring your seat usage and adding seats proactively to ensure uninterrupted access for your team. You can **[enable group mappings with JIT or SCIM](../13-Enterprise-Admin/setting-up-jit-or-scim-provisioning.md#h_adee31eeba) to provision users directly to a specific role and seat tier**.

------------------------------------------------------------------------

## Member-to-member invites

Organization members can invite teammates by email, even if they aren't admins. This makes it easier for your team to grow organically without requiring admin involvement for every new member.

### How it works

- **Approve one-by-one (default):** The invite request goes to an admin for review. The invite is only sent to the teammate after an admin approves it.

- **Approve automatically:** The invite is sent right away and the invitee can join immediately.

Invites sent by members follow the same domain restrictions as other join methods — the invitee's email must match one of your organization's allowed domains.

### Availability

- **Team plans:** Member-to-member invites are enabled by default for new organizations.

- **Enterprise plans:** Member-to-member invites are disabled by default. Admins can enable them from Admin settings.

### Admin controls

------------------------------------------------------------------------

## Remove members

You can remove a member by navigating to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, clicking the menu button to the right of the member, then selecting "Remove from team."

For Enterprise organizations using SCIM provisioning, members are automatically removed from Claude when they are removed from your Identity Provider.

When a member is removed:

- They lose access to the organization immediately.

- The seat they occupied becomes available to assign to another user.

- If you re-add the member later using the same email address, their account history will be maintained.

Removing a member frees up their seat for reassignment, but does not automatically reduce your plan's total seat count. See our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](purchasing-and-managing-seats-on-enterprise-plans.md)** for information on reducing seats.

**Note:** You cannot remove yourself as a Primary Owner or Owner. Another Primary Owner or Owner must remove you from the team.

------------------------------------------------------------------------

## Export member data

Admins and above can export a CSV of your organization's current member list from your organization settings.

The export includes member details such as name, email address, role, and seat type. This is useful for auditing membership, reconciling seat usage, or maintaining an external record of your team.

To export:

1. Navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Find the **Members** section.

3. Click the "Export CSV" button.

4. A CSV file will download to your device.

------------------------------------------------------------------------

## Manage invitations

### Resend an expired invitation

You can resend an invite from **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**. Find the member and select to resend the invite.

### Revoke a pending invitation

You can revoke a pending invite from **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**. Find the member and select "Remove from team."

------------------------------------------------------------------------

## Frequently asked questions

### Can I invite someone who already uses Claude personally with their work email?

### How do I add a member that I previously removed?

To add a member that you previously removed, follow the same steps as adding a new member. Their account history will be maintained.

### How do I change the Primary Owner?

The current Primary Owner can transfer ownership by:

1. Navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Click the Role dropdown next to the new user and select "Primary Owner."

3. Type the new Primary Owner's email address in the modal to confirm and transfer ownership.

**Important:** There can only be one Primary Owner per organization. Following these steps transfers the role to a different user.

### What happens to the initial invitation for a new Enterprise organization?

---
## manage-usage-credits-for-paid-claude-plans-3682360a70.md

# Manage usage credits for paid Claude plans

May 18, 2026

## What are usage credits?

------------------------------------------------------------------------

## How usage credits work

When you reach your plan’s usage limit with usage credits enabled:

- You’ll see a notification that you’ve reached your session usage limit.

- If usage credits are enabled and you have funds available, you can choose to continue working.

- Your subsequent usage will be billed at standard API pricing rates.

- Your session limits reset every five hours as usual.

**Note:** Usage credits are charged separately from your paid Claude subscription and appear as additional charges on your bill.

------------------------------------------------------------------------

## Enabling usage credits

To enable usage credits on your paid Claude plan:

1. Navigate to [**Settings \> Usage**](https://claude.ai/settings/usage) in your Claude account.

2. Locate the **Usage credits** section.

3. Click "Enable" to turn on usage credits.

4. Set up your payment method if not already configured.

5. Configure your spending preferences.

6. Click “Adjust limit” to control costs with a monthly spend limit. You can also select “Set to unlimited” if you prefer no spending restrictions.

7. You’ll then need to prepay to cover usage beyond your plan limits. Click “Add funds,” enter the amount you want to purchase in the modal, then click “Purchase.”

8. You can also enable auto-reload to automatically make a purchase when your balance falls below a threshold you set:

**Note:** There is a daily redemption limit of \$2000.

------------------------------------------------------------------------

## Set spend limits

Control your usage credit spending with:

- **Monthly spending cap:** Set a maximum amount you're willing to spend on usage credits each month.

- **Auto-reload settings:** Automatically add funds when your balance drops below a threshold.

- **Usage alerts:** Receive notifications when approaching your spend limits.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Managing your usage credits

### Monitoring usage and costs

Track your usage credits through:

- **Usage dashboard:** View real-time consumption in **[Settings \> Usage](https://claude.ai/settings/usage)**.

- **Current spending:** Monitor your month-to-date usage credit costs.

- **Usage history:** Review past consumption patterns to optimize future usage.

## Tips for cost-effective usage

To manage usage credit costs while maintaining productivity:

- **Choose efficient models:** Use our most efficient Haiku model, or the most recent Sonnet model for most tasks. These provide excellent performance at lower token costs than Opus models.

- **Use your plan’s included usage first:** Plan intensive work sessions around your five-hour usage windows.

- **Start new conversations:** Begin fresh chats for new topics to minimize the size of your context window.

- **Use projects effectively:** Store frequently referenced documents in project knowledge instead of re-uploading.

- **Set appropriate limits:** Start with conservative spending caps and adjust based on your needs.

------------------------------------------------------------------------

## How usage credits work with other features

### Claude Code

Usage credits apply to both Claude conversations and Claude Code terminal usage. Your combined usage across both interfaces counts toward your limits.

### Research mode

When using Research mode, usage credits apply once you exceed your plan's included limits. Research sessions may consume tokens more quickly due to multiple searches and comprehensive analysis.

### Projects and files

Documents stored in project files count toward your context when used in conversations. Usage credits apply to all tokens processed, including project content.

------------------------------------------------------------------------

## Frequently asked questions

### Can I disable usage credits after enabling them?

Yes, you can disable usage credits at any time through **[Settings \> Usage](https://claude.ai/settings/usage)**. Once disabled, you'll only have access to your plan's included usage.

### How quickly do my regular usage limits reset?

Your plan’s included usage limit will reset every five hours once you reach it. Usage credits don’t affect this reset timing.

### I subscribed to a paid Claude plan on the App or Play store; how can I access usage credits?

### Can I track usage credits separately from my included usage?

Yes, the usage dashboard clearly distinguishes between your included plan usage limits and any usage credit consumption.

### Will I get a warning before switching to usage credits?

Yes, you’ll see a clear notification when approaching and reaching your included usage limits, with a confirmation that you’ll continue with usage credits.

---
## manage-usage-credits-for-team-and-seat-based-enterprise-plans-c4a8f47459.md

# Manage usage credits for Team and seat-based Enterprise plans

May 18, 2026

## What are usage credits?

------------------------------------------------------------------------

## How usage credits work

**For Team plans:** Owners can pre-purchase usage credits that they can control using spend limits.

**For seat-based Enterprise plans:** Usage credits are billed at the end of each month based on your actual usage during the billing period.

------------------------------------------------------------------------

## Enable usage credits

### For Team owners

1. Log in to your Team organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to pay for usage credits.

5. Next, you'll see the option to enable auto-reload; choose "Reload when balance reaches" and enter the amount to reload.

6. Set a monthly spend limit to apply organization-wide.

7. Enable usage credits for specific users or the entire organization.

### For seat-based Enterprise owners

1. Log in to your seat-based Enterprise organization as an Owner or Primary Owner.

2. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

3. Click "Enable" in **Usage credits** to turn this on for your organization.

4. You'll be prompted to set monthly spend limits for the organization as a whole, by seat tier, or for individual members.

### How can members switch to usage credits once they're enabled?

Once an organization owner has enabled usage credits:

1. Continue using Claude or Claude Code normally.

2. When you reach your usage limit and choose to continue working, your usage credit consumption will be tracked and billed according to your plan type.

------------------------------------------------------------------------

## Organization-wide spend limits

Owners and Primary Owners of Team and seat-based Enterprise plans can set organization-wide spend limits to ensure predictable costs while providing flexibility for critical work.

### Spend limits

Changes to your organization’s overall spend limit go into effect immediately.

### Seat spend limits for seat-based Enterprise plans

Owners and Primary Owners on **seat-based Enterprise plans only** can set spend limits that apply to all users within a specific seat tier.

------------------------------------------------------------------------

## User-level spend limits

Owners and Primary Owners can also set individual monthly spend limits for each member by finding **Spend limits by user** and clicking the "..." button next to the user, then "Edit limit."

Note that the **Spend limits by user** section has a **MTD Spend** column, so you can track members' usage patterns and optimize seat assignments.

------------------------------------------------------------------------

## Usage credit pricing

Usage credits are billed at standard API rates; see our **[pricing page](https://claude.com/pricing#api)** for details.

Price and plans are subject to change at Anthropic's discretion.

------------------------------------------------------------------------

## Request usage credits for seat-based Enterprise plans

Members of seat-based Enterprise plans will see a "Request usage credits" link upon hitting their included usage limit.

### Disable usage credit requests

If you want to prevent users from submitting requests for usage credits, an organization owner can follow these steps:

1. Navigate to **[Organization settings \> Usage](https://claude.ai/admin-settings/usage)**.

2. Scroll to the bottom of the page and find **Usage credit requests**.

3. Toggle it off.

------------------------------------------------------------------------

## Frequently asked questions

### What happens when I reach my spend limit?

### Why was I able to exceed my spend limit?

### Can usage credits be disabled completely?

---
## manage-user-feedback-settings-on-team-and-enterprise-plans-19d51c778b.md

# Manage user feedback settings on Team and Enterprise plans

March 16, 2026

As a Primary Owner or Owner of a Team or Enterprise plan, you can manage the ability for members of your organization to submit feedback to Anthropic via thumbs up / thumbs down.

1. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls).**

2. Use the toggle to change the **Rate chats** setting for your organization:

More information on how Anthropic collects, uses, and stores feedback data can be found in our Privacy Center: **[How long do you store my organization’s data?](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data)**

---
## manage-user-feedback-settings-on-team-and-enterprise-plans.md

4. Manage user feedback settings on Team and Enterprise plans

# Manage user feedback settings on Team and Enterprise plans

As a Primary Owner or Owner of a Team or Enterprise plan, you can manage the ability for members of your organization to submit feedback to Anthropic via thumbs up / thumbs down.

1. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls).**

2. Use the toggle to change the **Rate chats** setting for your organization:

---
## managing-members-on-team-and-enterprise-plans-08b3821afb.md

# Manage members on Team and Enterprise plans

This guide covers how to add, remove, and manage the people on your Team or Enterprise plan.

------------------------------------------------------------------------

## Add members

### Add members by invitation

**Note:** Pending invitations occupy your available seats immediately; a new member does not need to accept the invite to take up a seat.

Admins and above can add members by following these steps:

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)** and click “Add member.”

2. Enter the person's email address (it must use one of your organization's **[allowed email domains](https://support.claude.com/en/articles/13325567-account-management-faqs#h_b54c41c86c)**).

3. Select the appropriate seat type.

4. Set the role and permissions for the member.

5. Click “Add members.”

This sends an email invitation to the person. The invitation expires after 21 days, so you'll need to re-invite them if they don't accept within that time period.

**Add multiple members at once:** You can invite multiple members by clicking "Bulk add" and typing or pasting email addresses separated by commas or new lines.

### Add members via organization discovery

### Share an invite link

**Availability:**

- **Team plans:** Invite links are enabled by default for new organizations.

- **SSO organizations:** Invite links are not available. Member provisioning is managed through your Identity Provider.

Admins can disable the link at any time—this immediately invalidates all existing links. Regenerating the link also invalidates the previous one.

For more details on how the joining flow works, see **[Join an organization via invite link](https://support.claude.com/en/articles/13776697-join-an-organization-via-invite-link)**.

### Automated provisioning with SSO

------------------------------------------------------------------------

## Member-to-member invites

Organization members can invite teammates by email, even if they aren't admins. This makes it easier for your team to grow organically without requiring admin involvement for every new member.

### How it works

- **Approve one-by-one (default):** The invite request goes to an admin for review. The invite is only sent to the teammate after an admin approves it.

- **Approve automatically:** The invite is sent right away and the invitee can join immediately.

Invites sent by members follow the same domain restrictions as other join methods — the invitee's email must match one of your organization's allowed domains.

### Availability

- **Team plans:** Member-to-member invites are enabled by default for new organizations.

- **Enterprise plans:** Member-to-member invites are disabled by default. Admins can enable them from Admin settings.

### Admin controls

------------------------------------------------------------------------

## Remove members

For Enterprise organizations using SCIM provisioning, members are automatically removed from Claude when they are removed from your Identity Provider.

When a member is removed:

- They lose access to the organization immediately.

- The seat they occupied becomes available to assign to another user.

- If you re-add the member later using the same email address, their account history will be maintained.

**Note:** You cannot remove yourself as a Primary Owner or Owner. Another Primary Owner or Owner must remove you from the team.

------------------------------------------------------------------------

## Export member data

Admins and above can export a CSV of your organization's current member list from your organization settings.

The export includes member details such as name, email address, role, and seat type. This is useful for auditing membership, reconciling seat usage, or maintaining an external record of your team.

To export:

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Click the "Export CSV" button at the top of the **Members** section.

3. A CSV file will download to your device.

------------------------------------------------------------------------

## Manage invitations

### Resend an expired invitation

You can resend an invite from **[Organization settings \> Members](http://claude.ai/admin-settings/members)**. Click the “Pending” tab, find the member, and select to resend the invite.

### Revoke a pending invitation

You can revoke a pending invite from **[Organization settings \> Members](http://claude.ai/admin-settings/members)**. Click the “Pending” tab, find the member, and select "Remove from team."

------------------------------------------------------------------------

## Frequently asked questions

### Can I invite someone who already uses Claude personally with their work email?

### How do I add a member that I previously removed?

To add a member that you previously removed, follow the same steps as adding a new member. Their account history will be maintained.

### How do I change the Primary Owner?

The current Primary Owner can transfer ownership by:

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Click the Role dropdown next to the new user and select "Primary Owner."

3. Type the new Primary Owner's email address in the modal to confirm and transfer ownership.

**Important:** There can only be one Primary Owner per organization. Following these steps transfers the role to a different user.

### What happens to the initial invitation for a new Enterprise organization?

---
## managing-members-on-team-and-enterprise-plans.md

4. Manage members on Team and Enterprise plans

# Manage members on Team and Enterprise plans

This guide covers how to add, remove, and manage the people on your Team or Enterprise plan.

For information on purchasing seats or adjusting your plan's seat allocation, see our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](purchasing-and-managing-seats-on-enterprise-plans.md)**.

------------------------------------------------------------------------

## Add members

### Add members by invitation

**Note:** Pending invitations occupy your available seats immediately; a new member does not need to accept the invite to take up a seat.

Admins and above can add members by following these steps:

1. Navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)** and click “Add member.”

2. Enter the person's email address (it must use one of your organization's **[allowed email domains](../21-Account-Support/account-management-faqs.md#h_b54c41c86c)**).

3. Select the appropriate seat type.

4. Set the role and permissions for the member.

5. Click “Add members.”

This sends an email invitation to the person. The invitation expires after 21 days, so you'll need to re-invite them if they don't accept within that time period.

**Add multiple members at once:** You can invite multiple members by clicking "Bulk add" and typing or pasting email addresses separated by commas or new lines.

### Add members via organization discovery

Members can also join your organization on their own through organization discovery. When you enable discoverability, colleagues with a matching email domain can find your organization during signup and request to join—no invitation needed. You can configure whether they're added automatically or require your approval. See **[Find and join a Team or Enterprise organization](../13-Enterprise-Admin/organization-discovery.md)** for details.

### Share an invite link

**Availability:**

- **Team plans:** Invite links are enabled by default for new organizations.

- **Enterprise plans (non-SSO):** Invite links are disabled by default. Admins can enable them in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

- **SSO organizations:** Invite links are not available. Member provisioning is managed through your Identity Provider.

Admins can disable the link at any time—this immediately invalidates all existing links. Regenerating the link also invalidates the previous one.

For more details on how the joining flow works, see **[Join an organization via invite link](https://support.claude.com/en/articles/13776697-join-an-organization-via-invite-link)**.

### Automated provisioning with SSO

- **Just-in-time (JIT) provisioning:** Members assigned to the Anthropic app in your Identity Provider will have accounts created automatically the first time they log in. On plans with multiple seat types, users are assigned to the highest-available seat type upon first login. On single-seat Enterprise plans, users are automatically assigned the Enterprise seat. Admins and above can manually reassign seat types afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

- **SCIM provisioning (Enterprise plan only):** With SCIM directory sync enabled, members assigned to the Anthropic app in your Identity Provider are provisioned automatically, up to the number of total seats on your plan. On plans with multiple seat types, seat types are distributed from highest to lowest available. On single-seat Enterprise plans, all users are automatically assigned the Enterprise seat. Primary Owners and Owners can reassign seat types afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

**Important:** An Owner or Primary Owner must ensure seats are available before new users can be provisioned. We recommend monitoring your seat usage and adding seats proactively to ensure uninterrupted access for your team. You can **[enable group mappings with JIT or SCIM](../13-Enterprise-Admin/setting-up-jit-or-scim-provisioning.md#h_adee31eeba) to provision users directly to a specific role and seat tier**.

------------------------------------------------------------------------

## Member-to-member invites

Organization members can invite teammates by email, even if they aren't admins. This makes it easier for your team to grow organically without requiring admin involvement for every new member.

### How it works

- **Approve one-by-one (default):** The invite request goes to an admin for review. The invite is only sent to the teammate after an admin approves it.

- **Approve automatically:** The invite is sent right away and the invitee can join immediately.

Invites sent by members follow the same domain restrictions as other join methods — the invitee's email must match one of your organization's allowed domains.

### Availability

- **Team plans:** Member-to-member invites are enabled by default for new organizations.

- **Enterprise plans:** Member-to-member invites are disabled by default. Admins can enable them from Admin settings.

### Admin controls

------------------------------------------------------------------------

## Remove members

For Enterprise organizations using SCIM provisioning, members are automatically removed from Claude when they are removed from your Identity Provider.

When a member is removed:

- They lose access to the organization immediately.

- The seat they occupied becomes available to assign to another user.

- If you re-add the member later using the same email address, their account history will be maintained.

Removing a member frees up their seat for reassignment, but does not automatically reduce your plan's total seat count. See our guides for **[Team plans](https://support.claude.com/en/articles/12004354-purchasing-and-managing-seats)** and **[Enterprise plans](purchasing-and-managing-seats-on-enterprise-plans.md)** for information on reducing seats.

**Note:** You cannot remove yourself as a Primary Owner or Owner. Another Primary Owner or Owner must remove you from the team.

------------------------------------------------------------------------

## Export member data

Admins and above can export a CSV of your organization's current member list from your organization settings.

The export includes member details such as name, email address, role, and seat type. This is useful for auditing membership, reconciling seat usage, or maintaining an external record of your team.

To export:

1. Navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Find the **Members** section.

3. Click the "Export CSV" button.

4. A CSV file will download to your device.

------------------------------------------------------------------------

## Manage invitations

### Resend an expired invitation

You can resend an invite from **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**. Find the member and select to resend the invite.

### Revoke a pending invitation

You can revoke a pending invite from **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**. Find the member and select "Remove from team."

------------------------------------------------------------------------

## Frequently asked questions

### Can I invite someone who already uses Claude personally with their work email?

### How do I add a member that I previously removed?

To add a member that you previously removed, follow the same steps as adding a new member. Their account history will be maintained.

### How do I change the Primary Owner?

The current Primary Owner can transfer ownership by:

1. Navigate to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Click the Role dropdown next to the new user and select "Primary Owner."

3. Type the new Primary Owner's email address in the modal to confirm and transfer ownership.

**Important:** There can only be one Primary Owner per organization. Following these steps transfers the role to a different user.

### What happens to the initial invitation for a new Enterprise organization?

---
## managing-user-feedback-settings-on-team-and-enterprise-plans-61d37da327.md

# Manage user feedback settings on Team and Enterprise plans

March 16, 2026

As a Primary Owner or Owner of a Team or Enterprise plan, you can manage the ability for members of your organization to submit feedback to Anthropic via thumbs up / thumbs down.

1. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls).**

2. Use the toggle to change the **Rate chats** setting for your organization:

---
## managing-user-feedback-settings-on-team-and-enterprise-plans.md

4. Manage user feedback settings on Team and Enterprise plans

# Manage user feedback settings on Team and Enterprise plans

As a Primary Owner or Owner of a Team or Enterprise plan, you can manage the ability for members of your organization to submit feedback to Anthropic via thumbs up / thumbs down.

1. Navigate to **[Organization settings \> Data and Privacy](https://claude.ai/admin-settings/data-privacy-controls).**

2. Use the toggle to change the **Rate chats** setting for your organization:

---
## max-plan-claude.md

The Max plan combines Claude desktop and mobile apps and Claude Code in one subscription, with up to 20x more usage per session than Pro. That’s a lot of deep work potential.

Get started

[Get started](http://claude.ai/)

Get started

People are using Claude to develop Amazon ad testing strategies

Download the desktop app:

macOS

[macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect)

macOS

Windows

[Windows](https://downloads.claude.ai/releases/win32/ClaudeSetup.exe)

Windows

Windows (arm64)

[Windows (arm64)](https://claude.ai/api/desktop/win32/arm64/exe/latest/redirect)

Windows (arm64)

Try Claude on mobile:

Apple

[Apple](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684)

Apple

Google Play

[Google Play](https://play.google.com/store/apps/details?id=com.anthropic.claude)

Google Play

A thought partner for your most ambitious work

Enable every team to spark new ideas, achieve more, and collaborate better.

### Tackle complex projects

Handle sophisticated, multi-dimensional challenges—the kind that require a true thinking partner.

### Do real work well

Launch features, complete analyses, publish content, and more with Claude.

### Claude works alongside you

Claude shows its thinking, seeks clarification, and collaborates thoughtfully.

One plan for all your work

Analysts

Marketers

Developers

Sales

Founders

Creators

Active

Note

Interact with the data—hover and toggle views to uncover patterns

Prompt

Attachments

Quarterly Performance

977 lines

csv

Strategic Metrics

92 kb

json

Content is user-generated and unverified.

Customize

Content is user-generated and unverified.

### Analysts

Research in Claude apps, then build data pipelines and query data with Claude Code.

Note

Interact with the data—hover and toggle views to uncover patterns

Prompt

Attachments

Quarterly Performance

1,283 lines

csv

Market Analysis

921 kb

json

Content is user-generated and unverified.

Customize

Content is user-generated and unverified.

### Marketers

Create compelling content and build campaign dashboards in Claude apps.

Prompt

\> claude fix the authentication error in our login flow

I'll investigate the auth error. Let me look at the relevant files.

Examining auth-related files...

\* src/services/authService.js

\* src/components/Login.jsx

\* src/store/authSlice.js

Running the login flow...

Error detected: "401 Unauthorized: Token expired"

Root cause:

\* Token refresh mechanism not handling expired tokens correctly

\* Refresh token missing from request header

\* Improper error handling for 401 responses

Updating authService.js with proper refresh logic...

Updating request interceptor for 401 handling...

Testing the fix...

\* Login successful ✓

\* Token refresh working ✓

\* Proper redirection on expired tokens ✓

Authentication error fixed! The login flow now properly handles token expiration.

### Developers

Plan project implementation with Claude apps, then execute with Claude Code in the terminal.

Prompt

Conduct a comprehensive win/loss analysis of the Q4 2024 enterprise sales pipeline using the attached CRM data, sales call transcripts, and win/loss interview summaries. I need a strategic business report.

Attachments

CRM Data

7,126 lines

csv

Sales Calls Transcripts

479 kb

txt

### Q4 2025 Enterprise Deal Win/Loss Analysis

#### Executive Summary

**Overall Performance:**

- **Win Rate:** 54.5% (6 wins out of 11 completed deals)
- **Total Pipeline Value:** \$8.27M across 20 deals
- **Won Deal Value:** \$1.97M (average \$328K per win)
- **Lost Deal Value:** \$1.44M (average \$288K per loss)
- **Active Pipeline:** \$4.86M across 9 in-progress deals

#### Key Findings

##### What’s Working: Primary Win Drivers

1. **Industry-Specific Expertise**
- **Compliance Leadership:** Won deals consistently highlighted superior compliance capabilities (TechCorp security, AutoManuf automotive certs, EnergyPlus sustainability)
- **Technical Fit:** All wins featured strong technical alignment with existing infrastructure
- **Industry References:** Successful deals leveraged relevant customer case studies effectively
2. **Speed to Value**
- **Fast Implementation:** Won deals averaged 75 days vs 121 days for lost deals
- **Quick ROI:** Winners showed immediate business impact (RetailMax Black Friday readiness, CloudFirst rapid scaling)
3. **Sales Team Performance**
- **Sarah Johnson:** 3 wins, 3 in-progress (50% of total wins)
- **David Rodriguez:** 3 wins, 2 in-progress (strong enterprise focus)
- Top performers brought in technical experts and leveraged references effectively

##### Critical Loss Factors

1. **Pricing Competitiveness**
- **60% of losses** cited cost as primary factor
- **Total Cost of Ownership:** Competitors offered 20-40% lower TCO
- **Budget Constraints:** Especially impactful in education and government sectors
2. **Implementation Timeline**
- **Seasonal Deadlines:** FoodChain and EduTech lost due to timing misalignment
- **Resource Constraints:** Lost deals averaged 40% longer implementation times
3. **Industry-Specific Gaps**
- **Feature Deficits:** Food safety (FoodChain), government compliance (GovServices), consulting templates (ConsultPro)
- **Reference Shortage:** Lacked sufficient industry-specific case studies

#### Detailed Analysis

##### Industry Performance

**High-Performing Industries** achieved perfect win rates across the board. Technology deals (100% win rate across 2 deals) succeeded through superior technical fit and security-focused positioning. Retail and Sports sectors also delivered 100% success rates, with scalability and real-time performance capabilities driving wins. Energy and Automotive industries maintained perfect records through industry-specific compliance expertise and sustainability-focused solutions.

**Struggling Industries** present significant challenges requiring strategic intervention. Manufacturing deals failed due to cost sensitivity and ERP integration complexities. Education sector losses stemmed from budget constraints and seasonal timing misalignment. Consulting industry struggles centered on ROI timeline concerns and extensive customization requirements. Food & Beverage deals were lost primarily due to industry-specific compliance gaps. Government sector challenges included complex procurement processes and vendor pre-approval requirements.

##### Deal Size Impact

Enterprise deals over \$300K delivered a 50% win rate with 5 wins out of 10 completed opportunities, while mid-market deals under \$300K achieved a perfect 100% win rate though represented only 1 completed deal. The average won deal value reached \$328K compared to \$288K for lost deals, indicating that higher-value opportunities are actually slightly more likely to close successfully despite their complexity.

##### Competitor Analysis

**Uncontested deals** represent the strongest opportunity with 6 total encounters resulting in 5 wins for an 83% success rate, demonstrating clear market fit when not facing direct competition.

**Competitor A** appeared in 4 deals with only 1 win achieved against them (25% win rate). Their primary strengths include lower cost positioning and faster implementation timelines that appeal to budget-conscious and time-sensitive prospects.

**Competitor B** proved most challenging with 5 encounters resulting in zero wins (0% win rate). They excel through industry-specific feature sets and superior integration capabilities with existing customer systems.

**Competitor C** also maintained a perfect defensive record with 4 encounters and zero losses to our solution (0% win rate). Their key advantages center on significant cost advantages and strong compliance capabilities that resonate particularly well in regulated industries.

#### Pipeline Risk Assessment

##### High-Risk Deals (Likely to be Lost)

1. **FinanceFirst Bank (D003) - \$680K**
- **Risk Level:** 🔴 HIGH
- **Issues:** Security audit delays, complex approval process, integration concerns
- **Timeline:** 125+ days in cycle
2. **LogiCorp International (D007) - \$750K**
- **Risk Level:** 🔴 HIGH
- **Issues:** Resource constraints, quarterly decision cycles, competitive evaluation
- **Timeline:** 134+ days in cycle
3. **BioPharm Research (D011) - \$610K**
- **Risk Level:** 🔴 HIGH
- **Issues:** FDA validation needs, merger uncertainty, 90-day regulatory review
- **Timeline:** 143+ days in cycle

##### Medium-Risk Deals

4. **TelecomMax Inc (D017) - \$690K**
- **Risk Level:** 🟡 MEDIUM
- **Issues:** Acquisition talks pausing decisions, architecture review delays
- **Action:** Provide technical POC to advance architecture review
5. **InsureTech Ltd (D013) - \$480K**
- **Risk Level:** 🟡 MEDIUM
- **Issues:** Q2 regulatory deadlines, build vs buy decision pending
- **Action:** Accelerate sandbox testing, provide regulatory compliance package

##### Promising Deals

6. **MediaWorks Global (D009) - \$380K**
- **Risk Level:** 🟢 LOW
- **Issues:** Change management concerns, timing with Q1 workflow changes
- **Action:** Provide training timeline, phase implementation approach

#### Strategic Recommendations

##### Immediate Actions (Next 30 Days)

1. **Pricing Strategy Review**
- Develop competitive pricing tiers for education, government, and manufacturing
- Create TCO calculators showing long-term value proposition
- Consider flexible payment terms for budget-constrained sectors
2. **Implementation Acceleration**
- Create phased implementation options to reduce resource burden
- Develop rapid deployment packages for time-sensitive industries
- Build seasonal implementation calendars for education and retail
3. **Industry Specialization**
- Develop food safety compliance package for F&B sector
- Create government-specific security documentation and pre-approval materials
- Build manufacturing-specific ERP integration templates

##### Medium-Term Initiatives (Next Quarter)

1. **Reference Program Enhancement**
- Recruit case study participants from each target industry
- Develop industry-specific ROI calculators and business cases
- Create peer reference networks for prospects
2. **Sales Team Optimization**
- Replicate Sarah Johnson and David Rodriguez's best practices
- Provide industry-specific training for underperforming reps
- Develop technical expert engagement playbooks
3. **Competitive Intelligence**
- Deep-dive analysis of Competitor B and C's industry-specific advantages
- Develop competitive battle cards for each major competitor
- Create differentiation messaging for key competitive scenarios

##### Long-Term Strategic Shifts

1. **Product Development Priorities**
- Food safety and traceability features for F&B market
- Government compliance and security certifications
- Manufacturing-specific ERP integration capabilities
2. **Market Focus Refinement**
- Double down on high-win-rate industries (Technology, Energy, Automotive)
- Develop specialized go-to-market strategies for challenging sectors
- Consider partnership strategies for government market entry

#### Success Metrics to Track

- **Win rate improvement:** Target 65% win rate by Q1 2025
- **Sales cycle reduction:** Target 15% decrease in average cycle time
- **Competitive win rate:** Improve win rate against top competitors to 40%
- **Pipeline conversion:** Focus on advancing high-value, high-probability deals

—

Analysis based on Q4 2024 CRM data, sales call transcripts, and win/loss interviews. Last updated: December 2024

### Sales

Write personalized outreach and analyze customer feedback in Claude apps.

Note

Interact with the data—hover and toggle views to uncover patterns

Prompt

Create an interactive time series chart showing performance trends over time from my uploaded data. Include:\
– Multiple metrics as different colored trend areas\
– Hover details showing exact values and dates\
– Legend to toggle metrics on/off\
– Trend analysis summary below the chartMake it visually clear which metrics are improving or declining.

Attachments

Industry Trends

522 lines

csv

Growth Analysis

442 kb

xlsx

Content is user-generated and unverified.

Customize

Content is user-generated and unverified.

Founders

Use Claude apps for strategic planning, then prototype with Claude Code—even without coding experience.

Prompt

Analyze my content performance and audience data. What patterns should guide my content strategy?

Attachments

Audience Insights Report

8.10 kb

txt

### Content strategy analysis: Performance patterns and strategic recommendations

#### Key performance patterns

##### Top performing content types

###### Case studies dominate conversions

- Customer success stories achieve 15.4-16.8% conversion rates
- Generate highest revenue attribution (\$4,560-\$5,240 per piece)
- Strong engagement across all audience segments
- **Pattern:** Real-world proof points resonate universally

###### Product tools and resources excel

- ROI calculator achieved 25.3% conversion rate (highest overall)
- Templates and guides average 21.4% conversion
- **Technical tutorials:** 24.6% conversion with engaged audiences
- **Pattern:** Actionable, practical content drives decisions

###### Video content shows mixed performance

- **Technical tutorials:** 24.6% conversion rate
- **Product demos:** 18.9% conversion rate
- **General webinars:** 6.8% conversion rate
- **Pattern:** Specific, educational video content outperforms general presentations

#### Channel performance insights

##### Website content drives revenue

- Averages 13.2% conversion rate across content types
- Captures high-intent audiences seeking solutions
- Long-form content performs best (8.9-15.6 minutes average time)

##### LinkedIn balances reach and conversion

- Professional audience aligns with your segments
- Moderate conversion rates (4.2-7.4%) but consistent performance
- Strong sharing behavior supports organic reach

##### YouTube technical content opportunity

- Advanced tutorials achieve exceptional conversion (24.6%)
- Currently underutilized for your technical audience segment
- Long-form educational content shows promise

##### Instagram and Twitter underperform

- Company culture content generates minimal business impact
- Low conversion rates (0.9-3.1%) for business goals
- Resource reallocation opportunity identified

#### Audience alignment analysis

##### Content gaps vs. audience needs

###### Marketing practitioners (42% of audience)

- **Need:** Campaign optimization, ROI proof, workflow efficiency
- **Gap:** Insufficient how-to guides and process optimization content
- **Opportunity:** Your templates perform well (21.4% conversion) but production volume low

###### Business leadership (28% of audience)

- **Need:** Competitive advantage, revenue impact, strategic planning
- **Strength:** Case studies and industry reports perform well
- **Gap:** Limited executive-focused content formats

###### Technical implementers (8% of audience)

- **Need:** Implementation guides, security considerations, troubleshooting
- **Major opportunity:** 24.6% conversion rate but minimal content volume
- **Gap:** Only 2 technical pieces in sample vs. high demand

#### Content consumption patterns

##### Peak engagement alignment

- Tuesday-Thursday content performs best
- Morning publication (9-11 AM) drives higher engagement
- Video content optimal on Wednesdays

##### Format preferences match performance

- Marketing practitioners prefer actionable guides → templates convert at 21.4%
- Business leaders prefer case studies → convert at 15.4-16.8%
- Technical implementers prefer detailed guides → convert at 24.6%

#### Strategic recommendations

##### Immediate content optimization (next 90 days)

###### Expand high-converting formats

- Double case study production (currently 2/month, target 4/month)
- Create monthly interactive tool or calculator
- Develop technical implementation guide series

###### Channel reallocation

- Reduce Instagram/Twitter investment by 60%
- Increase YouTube technical content production
- Expand LinkedIn thought leadership posting

###### Content calendar optimization

- Publish primary content Tuesday-Thursday mornings
- Reserve Mondays for content promotion and distribution
- Use Fridays for community engagement and social listening

##### Strategic content expansion (next 6 months)

###### Technical audience development

- Current 8% audience generates 24.6% conversion rates
- **Potential revenue impact:** 3x current technical content ROI
- **Target:** Monthly technical tutorial series, API documentation updates

###### Industry-specific content tracks

- Create vertical content for healthcare, manufacturing, financial services
- Develop industry-specific case studies and use cases
- Customize messaging for different compliance and regulatory needs

###### Video content strategy

- Focus on educational, problem-solving content vs. general presentations
- Create customer interview series (combines case study + video strengths)
- Develop technical implementation video library

##### Long-term positioning (next 12 months)

###### Community building initiative

- Leverage high-engagement technical audience for peer discussions
- Create user-generated content programs
- Develop customer advisory board for content input

###### International expansion

- 29% of audience outside North America presents localization opportunity
- Adapt high-performing content for international markets
- Consider regional compliance and regulatory content needs

###### Competitive differentiation

- Current content volume below industry average (20 vs. 31 pieces/month)
- Quality metrics above average (4.8% vs. 3.9% engagement)
- **Strategy:** Maintain quality while strategically increasing volume in high-converting categories

#### Success metrics and targets

##### 90-day targets

- Increase technical content from 10% to 25% of monthly output
- Achieve 15%+ average conversion rate across all content
- Generate 1,500+ leads monthly (vs. current 1,342)

##### 6-month targets

- Expand video content to 30% of production
- Reach 15,000+ monthly website visitors through organic content
- Achieve \$120,000+ monthly revenue attribution

##### 12-month targets

- Build technical community of 2,500+ engaged members
- Establish thought leadership in 3 industry verticals
- Generate \$200,000+ monthly revenue through content marketing

#### Implementation priority matrix

##### High impact, quick wins

- Expand case study production
- Create monthly interactive tools
- Reallocate social media resources to high-performing channels

##### High impact, medium effort

- Develop technical content series
- Launch customer interview video program
- Build industry-specific content tracks

##### Strategic investments

- International content localization
- Community platform development
- Advanced video production capabilities

Your content strategy should focus on amplifying what's already working (case studies, technical guides, practical tools) while strategically expanding into underutilized high-conversion opportunities, particularly technical content and video education formats.

### Creators

Plan content strategy in Claude apps, then handle website updates with Claude Code.

Why people choose Max

Some use it all for Claude apps—writing, research, analysis. Others live in Claude Code. Most discover they need both.

### The capacity to do more

With up to 20x more usage per session, you can finally pursue every thread, explore every possibility, and complete ambitious projects.

### More room for Claude’s best features

Run multiple \[\[research\|Research\|Build research reports in minutes, complete with easy-to-check citations.\]\] sessions daily. Build complex \[\[artifacts\|Artifacts\|Turn ideas into shareable creations. Build tools, visualizations, and experiences by simply describing what you need.\]\] iteratively. \[\[Create files, analyze data\|Code execution and file creation\|Claude executes code to quickly analyze data and create ready-to-use documents, spreadsheets, slides, PDFs, and more.\]\] and pull context from all your integrated \[\[tools\|Tools\|Connect Claude to your favorite tools like JIRA, Zapier, and Intercom, or build your own.\]\] freely.

### Access to the latest and greatest

New features and models often launch on Max first, before they expand to other plans.

How can I help?

I have tons of messy data and need to find meaningful patterns. What questions should I be asking to surface insights I wouldn't think to look for?

Ask Claude

[Ask Claude](#)

Ask Claude

How can I help?

My app performance is inconsistent and I can't pinpoint why. Help me think through a systematic debugging approach that goes beyond the obvious metrics.

Ask Claude

[Ask Claude](#)

Ask Claude

[Prev](#)

Choose your Max plan

Do more with Max. [Explore features](/pricing#individual-features)

### Max 5x

Great for frequent users who work with Claude on a variety of tasks, with 5x more usage per session than Pro.

\$100

Per person billed monthly

[Sign up](https://claude.ai/upgrade/max?plan=max_5x&returnTo=/claude-code-install)

### Max 20x

Perfect for daily users who collaborate often with Claude for most tasks, with 20x more usage per session than Pro.

\$200

Per person billed monthly

[Sign up](https://claude.ai/upgrade/max?plan=max_20x&returnTo=/claude-code-install)

Extra [usage limits](https://support.claude.com/en/articles/9797557-usage-limit-best-practices) apply. Prices shown don't include applicable tax.

---
## monitoring-usage.md

> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Monitoring

> Learn how to enable and configure OpenTelemetry for Claude Code.

Claude Code supports OpenTelemetry (OTel) metrics and events for monitoring and observability.

All metrics are time series data exported via OpenTelemetry's standard metrics protocol, and events are exported via OpenTelemetry's logs/events protocol. It is the user's responsibility to ensure their metrics and logs backends are properly configured and that the aggregation granularity meets their monitoring requirements.

## Quick start

Configure OpenTelemetry using environment variables:

```bash theme={null}
# 1. Enable telemetry
export CLAUDE_CODE_ENABLE_TELEMETRY=1

# 2. Choose exporters (both are optional - configure only what you need)
export OTEL_METRICS_EXPORTER=otlp # Options: otlp, prometheus, console
export OTEL_LOGS_EXPORTER=otlp # Options: otlp, console

# 3. Configure OTLP endpoint (for OTLP exporter)
export OTEL_EXPORTER_OTLP_PROTOCOL=grpc
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

# 4. Set authentication (if required)
export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer your-token"

# 5. For debugging: reduce export intervals
export OTEL_METRIC_EXPORT_INTERVAL=10000 # 10 seconds (default: 60000ms)
export OTEL_LOGS_EXPORT_INTERVAL=5000 # 5 seconds (default: 5000ms)

# 6. Run Claude Code
claude
```

<Note>
The default export intervals are 60 seconds for metrics and 5 seconds for logs. During setup, you may want to use shorter intervals for debugging purposes. Remember to reset these for production use.
</Note>

For full configuration options, see the [OpenTelemetry specification](https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/protocol/exporter.md#configuration-options).

## Administrator configuration

Administrators can configure OpenTelemetry settings for all users through the [managed settings file](/en/settings#settings-files). This allows for centralized control of telemetry settings across an organization. See the [settings precedence](/en/settings#settings-precedence) for more information about how settings are applied.

Example managed settings configuration:

```json theme={null}
{
"env": {
"CLAUDE_CODE_ENABLE_TELEMETRY": "1",
"OTEL_METRICS_EXPORTER": "otlp",
"OTEL_LOGS_EXPORTER": "otlp",
"OTEL_EXPORTER_OTLP_PROTOCOL": "grpc",
"OTEL_EXPORTER_OTLP_ENDPOINT": "http://collector.company.com:4317",
"OTEL_EXPORTER_OTLP_HEADERS": "Authorization=Bearer company-token"
}
}
```

<Note>
Managed settings can be distributed via MDM (Mobile Device Management) or other device management solutions. Environment variables defined in the managed settings file have high precedence and cannot be overridden by users.
</Note>

## Configuration details

### Common configuration variables

| Environment Variable | Description | Example Values |
| ----------------------------------------------- | ------------------------------------------------------------------------- | ------------------------------------ |
| `CLAUDE_CODE_ENABLE_TELEMETRY` | Enables telemetry collection (required) | `1` |
| `OTEL_METRICS_EXPORTER` | Metrics exporter type(s) (comma-separated) | `console`, `otlp`, `prometheus` |
| `OTEL_LOGS_EXPORTER` | Logs/events exporter type(s) (comma-separated) | `console`, `otlp` |
| `OTEL_EXPORTER_OTLP_PROTOCOL` | Protocol for OTLP exporter (all signals) | `grpc`, `http/json`, `http/protobuf` |
| `OTEL_EXPORTER_OTLP_ENDPOINT` | OTLP collector endpoint (all signals) | `http://localhost:4317` |
| `OTEL_EXPORTER_OTLP_METRICS_PROTOCOL` | Protocol for metrics (overrides general) | `grpc`, `http/json`, `http/protobuf` |
| `OTEL_EXPORTER_OTLP_METRICS_ENDPOINT` | OTLP metrics endpoint (overrides general) | `http://localhost:4318/v1/metrics` |
| `OTEL_EXPORTER_OTLP_LOGS_PROTOCOL` | Protocol for logs (overrides general) | `grpc`, `http/json`, `http/protobuf` |
| `OTEL_EXPORTER_OTLP_LOGS_ENDPOINT` | OTLP logs endpoint (overrides general) | `http://localhost:4318/v1/logs` |
| `OTEL_EXPORTER_OTLP_HEADERS` | Authentication headers for OTLP | `Authorization=Bearer token` |
| `OTEL_EXPORTER_OTLP_METRICS_CLIENT_KEY` | Client key for mTLS authentication | Path to client key file |
| `OTEL_EXPORTER_OTLP_METRICS_CLIENT_CERTIFICATE` | Client certificate for mTLS authentication | Path to client cert file |
| `OTEL_METRIC_EXPORT_INTERVAL` | Export interval in milliseconds (default: 60000) | `5000`, `60000` |
| `OTEL_LOGS_EXPORT_INTERVAL` | Logs export interval in milliseconds (default: 5000) | `1000`, `10000` |
| `OTEL_LOG_USER_PROMPTS` | Enable logging of user prompt content (default: disabled) | `1` to enable |
| `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` | Interval for refreshing dynamic headers (default: 1740000ms / 29 minutes) | `900000` |

### Metrics cardinality control

The following environment variables control which attributes are included in metrics to manage cardinality:

| Environment Variable | Description | Default Value | Example to Disable |
| ----------------------------------- | ----------------------------------------------- | ------------- | ------------------ |
| `OTEL_METRICS_INCLUDE_SESSION_ID` | Include session.id attribute in metrics | `true` | `false` |
| `OTEL_METRICS_INCLUDE_VERSION` | Include app.version attribute in metrics | `false` | `true` |
| `OTEL_METRICS_INCLUDE_ACCOUNT_UUID` | Include user.account\_uuid attribute in metrics | `true` | `false` |

These variables help control the cardinality of metrics, which affects storage requirements and query performance in your metrics backend. Lower cardinality generally means better performance and lower storage costs but less granular data for analysis.

### Dynamic headers

For enterprise environments that require dynamic authentication, you can configure a script to generate headers dynamically:

#### Settings configuration

Add to your `.claude/settings.json`:

```json theme={null}
{
"otelHeadersHelper": "/bin/generate_opentelemetry_headers.sh"
}
```

#### Script requirements

The script must output valid JSON with string key-value pairs representing HTTP headers:

```bash theme={null}
#!/bin/bash
# Example: Multiple headers
echo "{\"Authorization\": \"Bearer $(get-token.sh)\", \"X-API-Key\": \"$(get-api-key.sh)\"}"
```

#### Refresh behavior

The headers helper script runs at startup and periodically thereafter to support token refresh. By default, the script runs every 29 minutes. Customize the interval with the `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` environment variable.

### Multi-team organization support

Organizations with multiple teams or departments can add custom attributes to distinguish between different groups using the `OTEL_RESOURCE_ATTRIBUTES` environment variable:

```bash theme={null}
# Add custom attributes for team identification
export OTEL_RESOURCE_ATTRIBUTES="department=engineering,team.id=platform,cost_center=eng-123"
```

These custom attributes will be included in all metrics and events, allowing you to:

* Filter metrics by team or department
* Track costs per cost center
* Create team-specific dashboards
* Set up alerts for specific teams

<Warning>
**Important formatting requirements for OTEL\_RESOURCE\_ATTRIBUTES:**

The `OTEL_RESOURCE_ATTRIBUTES` environment variable follows the [W3C Baggage specification](https://www.w3.org/TR/baggage/), which has strict formatting requirements:

* **No spaces allowed**: Values cannot contain spaces. For example, `user.organizationName=My Company` is invalid
* **Format**: Must be comma-separated key=value pairs: `key1=value1,key2=value2`
* **Allowed characters**: Only US-ASCII characters excluding control characters, whitespace, double quotes, commas, semicolons, and backslashes
* **Special characters**: Characters outside the allowed range must be percent-encoded

**Examples:**

```bash theme={null}
# ❌ Invalid - contains spaces
export OTEL_RESOURCE_ATTRIBUTES="org.name=John's Organization"

# ✅ Valid - use underscores or camelCase instead
export OTEL_RESOURCE_ATTRIBUTES="org.name=Johns_Organization"
export OTEL_RESOURCE_ATTRIBUTES="org.name=JohnsOrganization"

# ✅ Valid - percent-encode special characters if needed
export OTEL_RESOURCE_ATTRIBUTES="org.name=John%27s%20Organization"
```

Note: wrapping values in quotes doesn't escape spaces. For example, `org.name="My Company"` results in the literal value `"My Company"` (with quotes included), not `My Company`.
</Warning>

### Example configurations

```bash theme={null}
# Console debugging (1-second intervals)
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_METRICS_EXPORTER=console
export OTEL_METRIC_EXPORT_INTERVAL=1000

# OTLP/gRPC
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_METRICS_EXPORTER=otlp
export OTEL_EXPORTER_OTLP_PROTOCOL=grpc
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

# Prometheus
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_METRICS_EXPORTER=prometheus

# Multiple exporters
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_METRICS_EXPORTER=console,otlp
export OTEL_EXPORTER_OTLP_PROTOCOL=http/json

# Different endpoints/backends for metrics and logs
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_METRICS_EXPORTER=otlp
export OTEL_LOGS_EXPORTER=otlp
export OTEL_EXPORTER_OTLP_METRICS_PROTOCOL=http/protobuf
export OTEL_EXPORTER_OTLP_METRICS_ENDPOINT=http://metrics.company.com:4318
export OTEL_EXPORTER_OTLP_LOGS_PROTOCOL=grpc
export OTEL_EXPORTER_OTLP_LOGS_ENDPOINT=http://logs.company.com:4317

# Metrics only (no events/logs)
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_METRICS_EXPORTER=otlp
export OTEL_EXPORTER_OTLP_PROTOCOL=grpc
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

# Events/logs only (no metrics)
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export OTEL_LOGS_EXPORTER=otlp
export OTEL_EXPORTER_OTLP_PROTOCOL=grpc
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
```

## Available metrics and events

### Standard attributes

All metrics and events share these standard attributes:

| Attribute | Description | Controlled By |
| ------------------- | -------------------------------------------------------------------- | --------------------------------------------------- |
| `session.id` | Unique session identifier | `OTEL_METRICS_INCLUDE_SESSION_ID` (default: true) |
| `app.version` | Current Claude Code version | `OTEL_METRICS_INCLUDE_VERSION` (default: false) |
| `organization.id` | Organization UUID (when authenticated) | Always included when available |
| `user.account_uuid` | Account UUID (when authenticated) | `OTEL_METRICS_INCLUDE_ACCOUNT_UUID` (default: true) |
| `terminal.type` | Terminal type (for example, `iTerm.app`, `vscode`, `cursor`, `tmux`) | Always included when detected |

### Metrics

Claude Code exports the following metrics:

| Metric Name | Description | Unit |
| ------------------------------------- | ----------------------------------------------- | ------ |
| `claude_code.session.count` | Count of CLI sessions started | count |
| `claude_code.lines_of_code.count` | Count of lines of code modified | count |
| `claude_code.pull_request.count` | Number of pull requests created | count |
| `claude_code.commit.count` | Number of git commits created | count |
| `claude_code.cost.usage` | Cost of the Claude Code session | USD |
| `claude_code.token.usage` | Number of tokens used | tokens |
| `claude_code.code_edit_tool.decision` | Count of code editing tool permission decisions | count |
| `claude_code.active_time.total` | Total active time in seconds | s |

### Metric details

#### Session counter

Incremented at the start of each session.

**Attributes**:

* All [standard attributes](#standard-attributes)

#### Lines of code counter

Incremented when code is added or removed.

**Attributes**:

* All [standard attributes](#standard-attributes)
* `type`: (`"added"`, `"removed"`)

#### Pull request counter

Incremented when creating pull requests via Claude Code.

**Attributes**:

* All [standard attributes](#standard-attributes)

#### Commit counter

Incremented when creating git commits via Claude Code.

**Attributes**:

* All [standard attributes](#standard-attributes)

#### Cost counter

Incremented after each API request.

**Attributes**:

* All [standard attributes](#standard-attributes)
* `model`: Model identifier (for example, "claude-sonnet-4-5-20250929")

#### Token counter

Incremented after each API request.

**Attributes**:

* All [standard attributes](#standard-attributes)
* `type`: (`"input"`, `"output"`, `"cacheRead"`, `"cacheCreation"`)
* `model`: Model identifier (for example, "claude-sonnet-4-5-20250929")

#### Code edit tool decision counter

Incremented when user accepts or rejects Edit, Write, or NotebookEdit tool usage.

**Attributes**:

* All [standard attributes](#standard-attributes)
* `tool`: Tool name (`"Edit"`, `"Write"`, `"NotebookEdit"`)
* `decision`: User decision (`"accept"`, `"reject"`)
* `language`: Programming language of the edited file (for example, `"TypeScript"`, `"Python"`, `"JavaScript"`, `"Markdown"`). Returns `"unknown"` for unrecognized file extensions.

#### Active time counter

Tracks actual time spent actively using Claude Code (not idle time). This metric is incremented during user interactions such as typing prompts or receiving responses.

**Attributes**:

* All [standard attributes](#standard-attributes)

### Events

Claude Code exports the following events via OpenTelemetry logs/events (when `OTEL_LOGS_EXPORTER` is configured):

#### User prompt event

Logged when a user submits a prompt.

**Event Name**: `claude_code.user_prompt`

**Attributes**:

* All [standard attributes](#standard-attributes)
* `event.name`: `"user_prompt"`
* `event.timestamp`: ISO 8601 timestamp
* `prompt_length`: Length of the prompt
* `prompt`: Prompt content (redacted by default, enable with `OTEL_LOG_USER_PROMPTS=1`)

#### Tool result event

Logged when a tool completes execution.

**Event Name**: `claude_code.tool_result`

**Attributes**:

* All [standard attributes](#standard-attributes)
* `event.name`: `"tool_result"`
* `event.timestamp`: ISO 8601 timestamp
* `tool_name`: Name of the tool
* `success`: `"true"` or `"false"`
* `duration_ms`: Execution time in milliseconds
* `error`: Error message (if failed)
* `decision`: Either `"accept"` or `"reject"`
* `source`: Decision source - `"config"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`
* `tool_parameters`: JSON string containing tool-specific parameters (when available)
* For Bash tool: includes `bash_command`, `full_command`, `timeout`, `description`, `sandbox`

#### API request event

Logged for each API request to Claude.

**Event Name**: `claude_code.api_request`

**Attributes**:

* All [standard attributes](#standard-attributes)
* `event.name`: `"api_request"`
* `event.timestamp`: ISO 8601 timestamp
* `model`: Model used (for example, "claude-sonnet-4-5-20250929")
* `cost_usd`: Estimated cost in USD
* `duration_ms`: Request duration in milliseconds
* `input_tokens`: Number of input tokens
* `output_tokens`: Number of output tokens
* `cache_read_tokens`: Number of tokens read from cache
* `cache_creation_tokens`: Number of tokens used for cache creation

#### API error event

Logged when an API request to Claude fails.

**Event Name**: `claude_code.api_error`

**Attributes**:

* All [standard attributes](#standard-attributes)
* `event.name`: `"api_error"`
* `event.timestamp`: ISO 8601 timestamp
* `model`: Model used (for example, "claude-sonnet-4-5-20250929")
* `error`: Error message
* `status_code`: HTTP status code (if applicable)
* `duration_ms`: Request duration in milliseconds
* `attempt`: Attempt number (for retried requests)

#### Tool decision event

Logged when a tool permission decision is made (accept/reject).

**Event Name**: `claude_code.tool_decision`

**Attributes**:

* All [standard attributes](#standard-attributes)
* `event.name`: `"tool_decision"`
* `event.timestamp`: ISO 8601 timestamp
* `tool_name`: Name of the tool (for example, "Read", "Edit", "Write", "NotebookEdit")
* `decision`: Either `"accept"` or `"reject"`
* `source`: Decision source - `"config"`, `"user_permanent"`, `"user_temporary"`, `"user_abort"`, or `"user_reject"`

## Interpreting metrics and events data

The metrics exported by Claude Code provide valuable insights into usage patterns and productivity. Here are some common visualizations and analyses you can create:

### Usage monitoring

| Metric | Analysis Opportunity |
| ------------------------------------------------------------- | --------------------------------------------------------- |
| `claude_code.token.usage` | Break down by `type` (input/output), user, team, or model |
| `claude_code.session.count` | Track adoption and engagement over time |
| `claude_code.lines_of_code.count` | Measure productivity by tracking code additions/removals |
| `claude_code.commit.count` & `claude_code.pull_request.count` | Understand impact on development workflows |

### Cost monitoring

The `claude_code.cost.usage` metric helps with:

* Tracking usage trends across teams or individuals
* Identifying high-usage sessions for optimization

<Note>
Cost metrics are approximations. For official billing data, refer to your API provider (Claude Console, AWS Bedrock, or Google Cloud Vertex).
</Note>

### Alerting and segmentation

Common alerts to consider:

* Cost spikes
* Unusual token consumption
* High session volume from specific users

All metrics can be segmented by `user.account_uuid`, `organization.id`, `session.id`, `model`, and `app.version`.

### Event analysis

The event data provides detailed insights into Claude Code interactions:

**Tool Usage Patterns**: analyze tool result events to identify:

* Most frequently used tools
* Tool success rates
* Average tool execution times
* Error patterns by tool type

**Performance Monitoring**: track API request durations and tool execution times to identify performance bottlenecks.

## Backend considerations

Your choice of metrics and logs backends determines the types of analyses you can perform:

### For metrics

* **Time series databases (for example, Prometheus)**: Rate calculations, aggregated metrics
* **Columnar stores (for example, ClickHouse)**: Complex queries, unique user analysis
* **Full-featured observability platforms (for example, Honeycomb, Datadog)**: Advanced querying, visualization, alerting

### For events/logs

* **Log aggregation systems (for example, Elasticsearch, Loki)**: Full-text search, log analysis
* **Columnar stores (for example, ClickHouse)**: Structured event analysis
* **Full-featured observability platforms (for example, Honeycomb, Datadog)**: Correlation between metrics and events

For organizations requiring Daily/Weekly/Monthly Active User (DAU/WAU/MAU) metrics, consider backends that support efficient unique value queries.

## Service information

All metrics and events are exported with the following resource attributes:

* `service.name`: `claude-code`
* `service.version`: Current Claude Code version
* `os.type`: Operating system type (for example, `linux`, `darwin`, `windows`)
* `os.version`: Operating system version string
* `host.arch`: Host architecture (for example, `amd64`, `arm64`)
* `wsl.version`: WSL version number (only present when running on Windows Subsystem for Linux)
* Meter Name: `com.anthropic.claude_code`

## ROI measurement resources

For a comprehensive guide on measuring return on investment for Claude Code, including telemetry setup, cost analysis, productivity metrics, and automated reporting, see the [Claude Code ROI Measurement Guide](https://github.com/anthropics/claude-code-monitoring-guide). This repository provides ready-to-use Docker Compose configurations, Prometheus and OpenTelemetry setups, and templates for generating productivity reports integrated with tools like Linear.

## Security/privacy considerations

* Telemetry is opt-in and requires explicit configuration
* Sensitive information like API keys or file contents are never included in metrics or events
* User prompt content is redacted by default - only prompt length is recorded. To enable user prompt logging, set `OTEL_LOG_USER_PROMPTS=1`

## Monitoring Claude Code on Amazon Bedrock

For detailed Claude Code usage monitoring guidance for Amazon Bedrock, see [Claude Code Monitoring Implementation (Bedrock)](https://github.com/aws-solutions-library-samples/guidance-for-claude-code-with-amazon-bedrock/blob/main/assets/docs/MONITORING.md).

---
## paid-plan-billing-faqs-0d4b98bda9.md

# Paid plan billing FAQs

This article covers Pro and Max subscriptions purchased on the web. If you subscribed through Claude for iOS or Claude for Android, your payment is handled by the Apple App Store or Google Play, and you'll manage your payment method and receipts through your app store account. To cancel or manage an app store subscription, see **[Cancel your Pro or Max subscription](https://support.claude.com/en/articles/8325617)**.

## Where can I find the invoice or receipt for my Pro or Max plan payment?

If you are subscribed to a paid plan (Pro or Max), follow these steps to access your invoices:

1. Click on your initials or name in the lower left corner and select “Settings” from the menu.

2. Navigate to **[Settings \> Billing](https://claude.ai/settings/billing)**.

3. Find the **Invoices** section.

4. Click the "View" button next to the invoice you want to open.

Additionally, all invoices are automatically emailed to your billing email address. To find previously emailed invoices in your inbox, search by the subject line "Your receipt from Anthropic."

## How can I edit the billing details for my existing paid Claude subscription?

1. Click on your initials or name in the lower left corner and select “Settings” from the menu.

2. Navigate to **[Settings \> Billing](https://claude.ai/settings/billing)**.

3. Click the "Update" button next to your payment method.

4. Enter your new billing details in the payment update form.

5. Click "Update" to save your changes.

6. Your updated payment method will be charged the next time your subscription renews.

## How can I change or remove the card on my Pro or Max subscription?

To change the card on your Pro or Max subscription:

1. Navigate to **[Settings \> Billing](https://claude.ai/settings/billing)**.

2. Click the “Update” button next to your payment method.

3. Enter your new card details.

4. Click “Update” to save your changes.

The new card becomes your default payment method, and all future subscription renewals are charged to it. Your previous card is no longer billed.

There's no separate option to remove a card, and updating to a new card replaces the old one for billing purposes. The billing page only shows your current default card. Previously used cards are no longer charged, but they may remain stored with our payment processor. If you need a previous card fully removed from your account, please contact **[our support team](https://support.claude.com/en/articles/9015913-how-to-get-support)**.

## How can I use a different name on my invoices?

If you want to use a name other than the one tied to your payment method, check the "Use a different name on invoices" box when adding or updating your payment method in **[Settings \> Billing](https://claude.ai/settings/billing)**.

## How can I edit a paid invoice?

Once an invoice is paid, there isn't a way to edit the information on the finalized invoice. Additionally, our internal teams cannot reissue paid invoices or modify information on previous invoices.

## Can I change the date I'm charged for my Pro or Max subscription?

No, there isn't a direct way to change your subscription billing date. However, you can unsubscribe from your current plan, then resubscribe on your preferred billing date to establish your new monthly billing cycle on a different date.

## What alternate payment methods are available?

For subscriptions purchased on the web, we only accept credit or debit cards. If you subscribed through Claude for iOS or Claude for Android, available payment options are determined by the Apple App Store or Google Play.

## I have a paid plan, but my account is showing as free; how can I access my paid account?

If you've paid for a Pro or Max plan but are not seeing this reflected in your account, there are two things you should check:

1. You've logged in with a different email. We recommend trying to sign in with any alternative emails you may have used to create your paid account.

2. Your payment method failed and your account was downgraded. To check this, navigate to **[Settings \> Billing](https://claude.ai/settings/billing)** to confirm your recent payment status and update your payment method or billing details if needed.

---
## paid-plan-billing-faqs.md

# Paid Plan Billing FAQs

## Where can I find the invoice or receipt for my Pro or Max plan payment?

If you are subscribed to a paid plan (Pro or Max), follow these steps to access your invoices:

1. Click on your initials or name in the lower left corner and select “Settings” from the menu.

2. Navigate to [Settings \> Billing](http://claude.ai/settings/billing).

3. Find the **Invoices** section.

4. Click the "View" button next to the invoice you want to open.

Additionally, all invoices are automatically emailed to your billing email address. To find previously emailed invoices in your inbox, search by the subject line "Your receipt from Anthropic."

## How can I edit the billing details for my existing paid Claude subscription?

1. Click on your initials or name in the lower left corner and select “Settings” from the menu.

2. Navigate to [Settings \> Billing](http://claude.ai/settings/billing).

3. Click the "Update" button next to your payment method.

4. Enter your new billing details in the payment update form.

5. Click "Update" to save your changes.

6. Your updated payment method will be charged the next time your subscription renews.

## How can I use a different name on my invoices?

If you want to use a name other than the one tied to your payment method, check the "Use a different name on invoices" box when adding or updating your payment method in [Settings \> Billing](http://claude.ai/settings/billing).

## How can I edit a paid invoice?

Once an invoice is paid, there isn't a way to edit the information on the finalized invoice. Additionally, our internal teams cannot reissue paid invoices or modify information on previous invoices.

## Can I change the date I'm charged for my Pro or Max subscription?

## What alternate payment methods are available?

We only accept credit or debit cards for Pro or Max plan payments.

## I have a paid plan, but my account is showing as free; how can I access my paid account?

If you've paid for a Pro or Max plan but are not seeing this reflected in your account, there are two things you should check:

1. You've logged in with a different email. We recommend trying to sign in with any alternative emails you may have used to create your paid account.

2. Your payment method failed and your account was downgraded. To check this, navigate to [Settings \> Billing](https://claude.ai/settings/billing) to confirm your recent payment status and update your payment method or billing details if needed.

---
## plans-amp-pricing-claude-by-anthropic-af3a9291ae.md

# Pricing

Individual

Team & Enterprise

API

Active

### Free

\$0

Free for everyone

[Try Claude](https://claude.ai/login?plan=free)

- Chat on web, iOS, Android, and on your desktop
- Generate code and visualize data
- Write, edit, and create content
- Ability to search the web
- Memory across conversations
- Create files and execute code
- Unlock more from Claude with desktop extensions
- Connect Slack and Google Workspace services
- Integrate any context or tool through connectors with remote MCP
- Extended thinking for complex work

### Pro

For everyday productivity

\$17

Per month with annual subscription discount (\$200 billed up front). \$20 if billed monthly.

[Try Claude](https://claude.ai/login?plan=pro)

Everything in Free, plus:

- More usage\*
- Includes Claude Code
- Includes Claude Cowork
- Includes Claude Design
- Includes Claude Science
- Access to unlimited projects to organize chats and documents
- Access to Research
- Ability to use more Claude models
- Claude for Microsoft 365

### Max

Get the most out of Claude

From \$100

Per month

[Try Claude](https://claude.ai/login?plan=max)

Everything in Pro, plus:

- Choose 5x or 20x more usage than Pro\*
- Higher output limits for all tasks
- Early access to advanced Claude features
- Priority access at high traffic times

[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Price and plans are subject to change at Anthropic's discretion.

## Compare features across plans

Free

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Pro

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Max 5x

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Max 20x

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

### Features and capabilities

[TABLE]

### Security and administration

[TABLE]

### Payment options

[TABLE]

### Models and usage

[TABLE]

### Team

For teams of 2 to 150

Get Team plan

[Get Team plan](https://claude.ai/upgrade?initialPlanType=team)

Get Team plan

Standard seat

All Claude features, plus more usage than Pro\*

\$20

Per seat / month if billed annually. \$25 if billed monthly.

Premium seat

5x more usage than standard seats\*

\$100

Per seat / month if billed annually. \$125 if billed monthly.

- Includes Claude Code and Claude Cowork
- Includes Claude Design
- Includes Claude Science
- Connect Microsoft 365, @Claude, and more
- Enterprise search across your organization
- Central billing and administration
- Single sign-on (SSO)
- Admin controls for remote and local connectors
- Enterprise deployment for the Claude desktop app
- No model training on your content by default
- Mix and match seat types

### Enterprise

For large businesses operating at scale

Get Enterprise plan

[Get Enterprise plan](http://claude.ai/create/enterprise)

Get Enterprise plan

Chat with buying specialist

[Chat with buying specialist](https://claude.ai/buying-specialist)

Chat with buying specialist

Seat price + usage at API rates

\$20/seat. Usage cost scales with model and task.

All Team plan features, plus:

- Admins set user and org spend limits
- Role-based access with fine grained permissioning
- System for Cross-domain Identity Management (SCIM)
- Audit logs
- Compliance API for observability and monitoring
- Custom data retention controls
- Network-level access control
- IP allowlisting
- HIPAA-ready offering available
- Claude Security (beta)

[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Price and plans are subject to change at Anthropic's discretion.

Education plan

Get a comprehensive university‐wide plan for an institution, including its students, faculty, and staff.

Learn more

[Learn more](/solutions/education)

Learn more

Student and faculty access

Comprehensive access for all university members at discounted rates

Academic research and learning mode

Dedicated API credits and educational features for student learning

Training and enablement

Resources for successful adoption across your institution

## Compare features across plans

Team

Create plan

[Create plan](https://claude.ai/upgrade?initialPlanType=team)

Create plan

Enterprise (self-serve)

Create plan

[Create plan](http://claude.ai/create/enterprise)

Create plan

Enterprise (sales-assisted)

[Contact sales](/contact-sales)

### Features and capabilities

[TABLE]

### Security and administration

[TABLE]

### Payment options

[TABLE]

### Partnership

[TABLE]

### Models and usage

[TABLE]

Latest models

[Contact sales](/contact-sales)

Start building

[Start building](https://platform.claude.com/)

Start building

Save 50% with batch processing.

[Learn more](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

Batch processing

### Fable 5

Next generation intelligence for long-running agents

Input

\$10 / MTok

Output

\$50 / MTok

Prompt caching

Write

\$12.50 / MTok

Read

\$1 / MTok

### Opus 5

Ideal for complex agentic coding and enterprise work

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Sonnet 5

High-performance model for coding and agents

Input\*

\$2 / MTok

Output\*

\$10 / MTok

Prompt caching

Write\*

\$2.50 / MTok

Read\*

\$0.20 / MTok

\*Introductory pricing of \$2/\$10 per million input/output tokens through August 31, 2026; **\$3/\$15 standard pricing thereafter.**

### Haiku 4.5

Fastest, most cost-efficient model

Input

\$1 / MTok

Output

\$5 / MTok

Prompt caching

Write

\$1.25 / MTok

Read

\$0.10 / MTok

**For workloads that need to run in the US, US-only inference is available at 1.1x pricing for input and output tokens.** [**Learn more**](https://platform.claude.com/docs/en/build-with-claude/data-residency)**.**

Get up to 2.5x faster speeds with fast mode for Opus 5 at 2x standard pricing. [Learn more](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing).

Prompt caching pricing reflects 5-minute TTL. Learn about [extended prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#1-hour-cache-duration).

Explore detailed pricing

[Explore detailed pricing](https://platform.claude.com/docs/en/about-claude/pricing)

Explore detailed pricing

Pricing for Claude Platform features

Get more out of Claude with advanced features and capabilities.

Learn more

[Learn more](https://platform.claude.com/docs/en/about-claude/pricing#specific-tool-pricing)

Learn more

#### Managed Agents

Build and deploy agents at scale with a suite of composable APIs. Standard token rates apply.

Cost

\$0.08 per session-hour for active runtime

#### Web search

Give Claude access to the latest information from the web. Doesn’t include input and output tokens required to process requests.

Cost

\$10 / 1K searches

Code execution

Run Python code in a sandboxed environment for advanced data analysis. 50 free hours of usage daily per organization.

Additional hours

\$0.05 per hour per container

Service tiers

Balance availability, performance, and predictable costs based on your needs.

Learn more

[Learn more](https://platform.claude.com/docs/en/api/service-tiers)

Learn more

[Contact sales](/contact-sales)

Standard

Default tier for both piloting and scaling everyday use cases

Batch

For asynchronous workloads that can be processed together for better efficiency

Legacy models

Learn more

[Learn more](https://platform.claude.com/docs/en/about-claude/models/overview)

Learn more

Explore detailed pricing

[Explore detailed pricing](https://platform.claude.com/docs/en/about-claude/pricing)

Explore detailed pricing

### Opus 4.8

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

Save 50% with batch processing.

[Learn more](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

Batch processing

### Sonnet 4.6

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Opus 4.7

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Opus 4.6

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Sonnet 4.5

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Opus 4.5

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Opus 4.1

Input

\$15 / MTok

Output

\$75 / MTok

Prompt caching

Write

\$18.75 / MTok

Read

\$1.50 / MTok

Prompt caching pricing reflects 5-minute TTL. Learn about [extended prompt caching](https://docs.claude.com/en/docs/build-with-claude/prompt-caching#pricing).

## FAQ

Plans and usage

Billing and payments

Managing your plan

Active

### Plans and usage

### What do I get with Claude Pro?

The [Pro plan](https://support.claude.com/en/articles/8325606-what-is-the-pro-plan) gives you everything in a Free plan with more usage and the full set of Claude capabilities. That includes Claude Code, Claude Cowork, Claude Design, along with projects to organize your chats and documents, access to more Claude models, and Claude for Microsoft 365. You can choose a monthly or annual subscription.

### How is Claude Max different from Pro?

The [Max plan](https://support.claude.com/en/articles/11049741-what-is-the-max-plan) is built for people who work with Claude throughout the day and want longer, uninterrupted sessions. You get everything in Pro, plus more usage: choose from 5x or 20x the usage of Pro per 5-hour session. Max also gives you higher output limits. Both options are billed monthly. See the cards above for current pricing.

### What are the usage limits on each plan, and what happens when I hit them?

Every plan has [usage limits](https://support.claude.com/en/articles/9797557-usage-limit-best-practices) that reset on a rolling five-hour session window, and paid plans add weekly limits on top. Your activity across Claude on web, desktop, mobile, and Claude Code all draws from the same pool. How much you can do depends on the length and complexity of your conversations, the model you choose, and the features you use, so there's no fixed message count. Free covers everyday questions. Pro gives you at least 5x more usage per 5-hour session than Free. Max gives you 5x or 20x more usage per 5-hour session than Pro. On Team plans, Standard seats give more than Pro and Premium seats give 5x more than Standard. To manage capacity and make sure all users have fair access, we may limit your usage in other ways, such as weekly and monthly caps or model and feature usage, at our discretion. When you reach a limit, you can wait for it to reset, move to a higher plan, or, on paid plans, turn on [usage credits](https://support.claude.com/en/articles/12429409-manage-usage-credits-for-paid-claude-plans) to keep working at standard API rates. You can see where you stand anytime in [Settings \> Usage](https://claude.ai/settings/usage).

### Is Claude Code included in my plan?

[Claude Code](https://claude.com/product/claude-code) is included in all paid plans. It shares the same usage limits as the rest of your plan, so your work in the terminal and your chats draw from one pool. For heavy coding sessions, you can also switch to pay-as-you-go API credits through a [Console account](https://platform.claude.com/).

### How much does the Claude Enterprise plan cost?

The [Claude Enterprise plan](https://claude.com/solutions/enterprise) is built for large businesses operating at scale. Pricing is \$20 per seat per month plus usage billed at API rates, so cost scales with the models and tasks your team runs. Enterprise is billed annually and includes everything in Team plus advanced security and admin controls, including SCIM, audit logs, custom data retention, and role-based access. You can get started self-serve or [contact sales](https://claude.com/contact-sales) for a tailored quote.

[Prev](#)

### Billing and payments

### Can I pay annually? Does it cost less than if I pay monthly?

Yes, annual plans are designed to cost less than monthly subscriptions. Annual subscriptions are available for Pro and Team plans. Enterprise plans are only available as annual subscriptions.

When you choose to pay annually, you're billed once up front for the year. If you're already on a monthly plan, you can switch to annual in [Settings \> Billing](https://claude.ai/settings/billing), and any unused time is credited toward your first annual invoice. See the steps for [Pro](https://support.claude.com/en/articles/10185996-how-to-change-your-pro-plan-from-monthly-to-annual-billing) and [Team](https://support.claude.com/en/articles/12083917-change-your-team-plan-from-monthly-to-annual-billing).

### Does Claude offer refunds?

Payments are generally non-refundable, except where our [Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms) say otherwise or where local law requires it.

Customers outside of Europe can follow this process to [request a refund](https://support.claude.com/en/articles/12386328-requesting-a-refund-for-a-paid-claude-plan):

- Log in, open Get help from the menu, start a message, and choose Claude Refund Request to check your eligibility.
- If you subscribed through the App Store, [Apple](https://support.apple.com/billing) handles the refund, so you'll request it from Apple.
- If you subscribed through Google Play, [contact our Support team](https://support.claude.com/en/articles/9015913-how-to-get-support) to check eligibility for an active subscription.

If you're in the European Economic Area and the United Kingdom, and within your 14-day withdrawal period, you can request a refund directly in the app.

[Prev](#)

### Managing your plan

### How do I upgrade, downgrade, or switch between plans?

You can change your plan any time in Settings.

- For individual plans, go to [Settings \> Billing](https://claude.ai/settings/billing) and choose Manage subscription.
- On Team plans, an Owner or Primary Owner manages this under Organization settings \> Billing. [See more details here](https://support.claude.com/en/articles/12004354-purchase-and-manage-seats-on-team-plans).

Upgrades take effect right away, and any unused time on your current plan is credited toward the new one, so you won't pay twice for the same days.

Moving from monthly to annual works the same way, with your remaining time credited to the first annual invoice.

In some upgrades (for example Pro Annual to Max 5x Monthly), your remaining value on your old plan is larger than the cost of one billing period of the new plan. In this case, the excess will be stored as credit, which will automatically get used for future purchases.

Downgrades take effect at the end of your current billing period, and your chats, projects, and files stay with your account whichever plan you're on.

### How do I cancel my Claude subscription?

You can cancel anytime, and your plan stays active until the end of your current billing period. To avoid the next charge, cancel at least 24 hours before your renewal date.

- If you signed up on the web or the desktop app, go to [Settings \> Billing](https://claude.ai/settings/billing) and click Cancel.
- If you subscribed through the App Store or Google Play, cancel from that app under Billing \> Manage subscription, or directly in your [Apple](https://support.apple.com/en-us/118428) or [Google Play](https://support.google.com/googleplay/answer/7018481) account.
- Team and self-serve Enterprise: an Owner or Primary Owner cancels under [Organization settings \> Billing](https://claude.ai/admin-settings/billing).
- Sales-assisted Enterprise: Reach out to your Anthropic Contact or our Sales team to discuss cancellation.

Canceling doesn't delete your data. Your chats, projects, and files stay with your account, though some features aren't available on the Free plan. For Pro and Max, your account moves to the Free plan once the period ends. For step-by-step help, see [how to cancel a Pro or Max plan](https://support.claude.com/en/articles/8325617-how-do-i-cancel-my-paid-claude-subscription) or [cancel a Team plan](https://support.claude.com/en/articles/9267323-cancel-your-organization-s-team-plan-subscription).

[Prev](#)

[Homepage](https://claude.com)

Homepage

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Write

[Button Text](#)

Button Text

Learn

[Button Text](#)

Button Text

Code

[Button Text](#)

Button Text

Write

- Help me develop a unique voice for an audience

- Improve my writing style

- Brainstorm creative ideas

Learn

- Explain a complex topic simply

- Help me make sense of these ideas

- Prepare for an exam or interview

Code

- Explain a programming concept

- Look over my code and give me tips

- Vibe code with me

- Write case studies

This is another test

- Write grant proposals

- Write video scripts

this is a test

[Anthropic](https://www.anthropic.com/)

Anthropic

Products

- Claude

[Claude](/product/overview)
Claude

- Claude Code

[Claude Code](/product/claude-code)
Claude Code

- Claude Code for Enterprise

[Claude Code for Enterprise](/product/claude-code/enterprise)
Claude Code for Enterprise

- Claude Cowork

[Claude Cowork](/product/cowork)
Claude Cowork

- @Claude

[@Claude](/product/tag)
@Claude

- Claude Design

[Claude Design](/product/design)
Claude Design

- Claude Science

[Claude Science](/product/claude-science)
Claude Science

- Claude Security

[Claude Security](/product/claude-security)
Claude Security

- Download app

[Download app](/download)
Download app

- Pricing

[Pricing](/pricing)
Pricing

- Log in

[Log in](https://claude.ai/login)

Features

- Claude for Chrome

[Claude for Chrome](/claude-for-chrome)
Claude for Chrome

- Claude for Microsoft 365

[Claude for Microsoft 365](/claude-for-microsoft-365)
Claude for Microsoft 365

- Skills

[Skills](/skills)
Skills

Models

- Mythos

[Mythos](https://www.anthropic.com/claude/mythos)
Mythos

- Fable

[Fable](https://www.anthropic.com/claude/fable)
Fable

- Opus

[Opus](https://www.anthropic.com/claude/opus)
Opus

- Sonnet

[Sonnet](https://www.anthropic.com/claude/sonnet)
Sonnet

- Haiku

[Haiku](https://www.anthropic.com/claude/haiku)
Haiku

Solutions

- AI agents

[AI agents](/solutions/agents)
AI agents

- Code modernization

[Code modernization](/solutions/code-modernization)
Code modernization

- Coding

[Coding](/solutions/coding)
Coding

- Customer support

[Customer support](/solutions/customer-support)
Customer support

- Cybersecurity

[Cybersecurity](/solutions/cybersecurity)
Cybersecurity

- Enterprise

[Enterprise](/solutions/enterprise)
Enterprise

- Financial services

[Financial services](/solutions/financial-services)
Financial services

- Government

[Government](/solutions/government)
Government

- Healthcare

[Healthcare](/solutions/healthcare)
Healthcare

- Higher education

[Higher education](/solutions/education)
Higher education

- K-12 teachers

[K-12 teachers](/solutions/teachers)
K-12 teachers

- Legal

[Legal](/solutions/legal)
Legal

- Life sciences

[Life sciences](/solutions/life-sciences)
Life sciences

- Nonprofits

[Nonprofits](/solutions/nonprofits)
Nonprofits

- Small business

[Small business](/solutions/small-business)
Small business

Claude Platform

- Overview

[Overview](/platform/api)
Overview

- Developer docs

[Developer docs](https://platform.claude.com/docs)
Developer docs

- Pricing

[Pricing](https://claude.com/pricing#api)
Pricing

- Ecosystem

[Ecosystem](/ecosystem)
Ecosystem

- Marketplace

[Marketplace](/platform/marketplace)
Marketplace

- Claude on AWS

[Claude on AWS](/partners/claude-on-aws)
Claude on AWS

- Google Cloud

[Google Cloud](/partners/google-cloud)
Google Cloud

- Microsoft Foundry

[Microsoft Foundry](/partners/microsoft-foundry)
Microsoft Foundry

- Regional compliance

[Regional compliance](/regional-compliance)
Regional compliance

- Console login

[Console login](https://platform.claude.com/)
Console login

Resources

- Blog

[Blog](/blog)
Blog

- Claude partner network

[Claude partner network](/partners)
Claude partner network

- Community

[Community](/community)
Community

- Connectors

[Connectors](/connectors)
Connectors

- Courses

[Courses](https://www.anthropic.com/learn)
Courses

- Customer stories

[Customer stories](/customers)
Customer stories

- Engineering at Anthropic

[Engineering at Anthropic](https://www.anthropic.com/engineering)
Engineering at Anthropic

- Events

[Events](https://www.anthropic.com/events)
Events

- Plugins

[Plugins](/plugins)
Plugins

- Powered by Claude

[Powered by Claude](/partners/powered-by-claude)
Powered by Claude

- Service partners

[Service partners](/partners/services)
Service partners

- Tutorials

[Tutorials](/resources/tutorials)
Tutorials

- Use cases

[Use cases](/resources/use-cases)
Use cases

Company

- Anthropic

[Anthropic](https://www.anthropic.com/)
Anthropic

- Careers

[Careers](https://www.anthropic.com/careers)
Careers

- Policy

[Policy](https://www.anthropic.com/policy)
Policy

- Economic Futures

[Economic Futures](https://www.anthropic.com/economic-futures)
Economic Futures

- Research

[Research](https://www.anthropic.com/research)
Research

- News

[News](https://www.anthropic.com/news)
News

- Policy on the AI Exponential

---
## plans-amp-pricing-claude-by-anthropic-de38b04b74.md

# Pricing

Individual

Team & Enterprise

API

Active

### Free

\$0

Free for everyone

[Try Claude](https://claude.ai/login?plan=free)

### Pro

For everyday productivity

\$17

Per month with annual subscription discount (\$200 billed up front). \$20 if billed monthly.

[Try Claude](https://claude.ai/login?plan=pro)

Everything in Free, plus:

### Max

Get the most out of Claude

From \$100

Per month

[Try Claude](https://claude.ai/login?plan=max)

Everything in Pro, plus:

- Choose 5x or 20x more usage than Pro\*
- Higher output limits for all tasks
- Early access to advanced Claude features
- Priority access at high traffic times

[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Price and plans are subject to change at Anthropic's discretion.

## Compare features across plans

Free

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Pro

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Max 5x

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Max 20x

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

### Features and capabilities

[TABLE]

### Security and administration

[TABLE]

### Payment options

[TABLE]

### Models and usage

[TABLE]

### Team

For teams of 2 to 150

Get Team plan

[Get Team plan](https://claude.ai/upgrade?initialPlanType=team)

Get Team plan

Standard seat

All Claude features, plus more usage than Pro\*

\$20

Per seat / month if billed annually. \$25 if billed monthly.

Premium seat

5x more usage than standard seats\*

\$100

Per seat / month if billed annually. \$125 if billed monthly.

### Enterprise

For large businesses operating at scale

Get Enterprise plan

[Get Enterprise plan](http://claude.ai/create/enterprise)

Get Enterprise plan

Chat with buying specialist

[Chat with buying specialist](https://claude.ai/buying-specialist)

Chat with buying specialist

Seat price + usage at API rates

\$20/seat. Usage cost scales with model and task.

All Team plan features, plus:

[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. Price and plans are subject to change at Anthropic's discretion.

Education plan

Get a comprehensive university‐wide plan for an institution, including its students, faculty, and staff.

Learn more

[Learn more](/solutions/education)

Learn more

Student and faculty access

Comprehensive access for all university members at discounted rates

Academic research and learning mode

Dedicated API credits and educational features for student learning

Training and enablement

Resources for successful adoption across your institution

## Compare features across plans

Team

Create plan

[Create plan](https://claude.ai/upgrade?initialPlanType=team)

Create plan

Enterprise (self-serve)

Create plan

[Create plan](http://claude.ai/create/enterprise)

Create plan

Enterprise (sales-assisted)

[Contact sales](/contact-sales)

### Features and capabilities

[TABLE]

### Security and administration

[TABLE]

### Payment options

[TABLE]

### Partnership

[TABLE]

### Models and usage

[TABLE]

Latest models

[Contact sales](/contact-sales)

Start building

[Start building](https://platform.claude.com/)

Start building

Save 50% with batch processing.

[Learn more](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

Batch processing

### Fable 5

Next generation intelligence for long-running agents

Input

\$10 / MTok

Output

\$50 / MTok

Prompt caching

Write

\$12.50 / MTok

Read

\$1 / MTok

### Opus 5

Ideal for complex agentic coding and enterprise work

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Sonnet 5

High-performance model for coding and agents

Input\*

\$2 / MTok

Output\*

\$10 / MTok

Prompt caching

Write\*

\$2.50 / MTok

Read\*

\$0.20 / MTok

\*Introductory pricing of \$2/\$10 per million input/output tokens through August 31, 2026; **\$3/\$15 standard pricing thereafter.**

### Haiku 4.5

Fastest, most cost-efficient model

Input

\$1 / MTok

Output

\$5 / MTok

Prompt caching

Write

\$1.25 / MTok

Read

\$0.10 / MTok

Get up to 2.5x faster speeds with fast mode for Opus 5 at 2x standard pricing. [Learn more](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing).

Prompt caching pricing reflects 5-minute TTL. Learn about [extended prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#1-hour-cache-duration).

Explore detailed pricing

[Explore detailed pricing](https://platform.claude.com/docs/en/about-claude/pricing)

Explore detailed pricing

Pricing for Claude Platform features

Get more out of Claude with advanced features and capabilities.

Learn more

[Learn more](https://platform.claude.com/docs/en/about-claude/pricing#specific-tool-pricing)

Learn more

#### Managed Agents

Build and deploy agents at scale with a suite of composable APIs. Standard token rates apply.

Cost

\$0.08 per session-hour for active runtime

#### Web search

Give Claude access to the latest information from the web. Doesn’t include input and output tokens required to process requests.

Cost

\$10 / 1K searches

Code execution

Run Python code in a sandboxed environment for advanced data analysis. 50 free hours of usage daily per organization.

Additional hours

\$0.05 per hour per container

Service tiers

Balance availability, performance, and predictable costs based on your needs.

Learn more

[Learn more](https://platform.claude.com/docs/en/api/service-tiers)

Learn more

[Contact sales](/contact-sales)

Standard

Default tier for both piloting and scaling everyday use cases

Batch

For asynchronous workloads that can be processed together for better efficiency

Legacy models

Learn more

[Learn more](https://platform.claude.com/docs/en/about-claude/models/overview)

Learn more

Explore detailed pricing

[Explore detailed pricing](https://platform.claude.com/docs/en/about-claude/pricing)

Explore detailed pricing

### Opus 4.8

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

Save 50% with batch processing.

[Learn more](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

Batch processing

### Sonnet 4.6

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Opus 4.7

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Opus 4.6

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Sonnet 4.5

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Opus 4.5

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Opus 4.1

Input

\$15 / MTok

Output

\$75 / MTok

Prompt caching

Write

\$18.75 / MTok

Read

\$1.50 / MTok

Prompt caching pricing reflects 5-minute TTL. Learn about [extended prompt caching](https://docs.claude.com/en/docs/build-with-claude/prompt-caching#pricing).

## FAQ

Plans and usage

Billing and payments

Managing your plan

Active

### Plans and usage

### What do I get with Claude Pro?

### How is Claude Max different from Pro?

### What are the usage limits on each plan, and what happens when I hit them?

### Is Claude Code included in my plan?

### How much does the Claude Enterprise plan cost?

[Prev](#)

### Billing and payments

### Can I pay annually? Does it cost less than if I pay monthly?

Yes, annual plans are designed to cost less than monthly subscriptions. Annual subscriptions are available for Pro and Team plans. Enterprise plans are only available as annual subscriptions.

### Does Claude offer refunds?

Payments are generally non-refundable, except where our [Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms) say otherwise or where local law requires it.

Customers outside of Europe can follow this process to [request a refund](https://support.claude.com/en/articles/12386328-requesting-a-refund-for-a-paid-claude-plan):

If you're in the European Economic Area and the United Kingdom, and within your 14-day withdrawal period, you can request a refund directly in the app.

[Prev](#)

### Managing your plan

### How do I upgrade, downgrade, or switch between plans?

You can change your plan any time in Settings.

Upgrades take effect right away, and any unused time on your current plan is credited toward the new one, so you won't pay twice for the same days.

Moving from monthly to annual works the same way, with your remaining time credited to the first annual invoice.

Downgrades take effect at the end of your current billing period, and your chats, projects, and files stay with your account whichever plan you're on.

### How do I cancel my Claude subscription?

You can cancel anytime, and your plan stays active until the end of your current billing period. To avoid the next charge, cancel at least 24 hours before your renewal date.

[Prev](#)

[Homepage](https://claude.com)

Homepage

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Write

[Button Text](#)

Button Text

Learn

[Button Text](#)

Button Text

Code

[Button Text](#)

Button Text

Write

- Help me develop a unique voice for an audience

- Improve my writing style

- Brainstorm creative ideas

Learn

- Explain a complex topic simply

- Help me make sense of these ideas

- Prepare for an exam or interview

Code

- Explain a programming concept

- Look over my code and give me tips

- Vibe code with me

- Write case studies

This is another test

- Write grant proposals

- Write video scripts

this is a test

[Anthropic](https://www.anthropic.com/)

Anthropic

Products

- Claude

[Claude](/product/overview)
Claude

- Claude Code

[Claude Code](/product/claude-code)
Claude Code

- Claude Code for Enterprise

[Claude Code for Enterprise](/product/claude-code/enterprise)
Claude Code for Enterprise

- Claude Cowork

[Claude Cowork](/product/cowork)
Claude Cowork

- @Claude

[@Claude](/product/tag)
@Claude

- Claude Design

[Claude Design](/product/design)
Claude Design

- Claude Science

[Claude Science](/product/claude-science)
Claude Science

- Claude Security

[Claude Security](/product/claude-security)
Claude Security

- Download app

[Download app](/download)
Download app

- Pricing

[Pricing](/pricing)
Pricing

- Log in

[Log in](https://claude.ai/login)

Features

- Claude for Chrome

[Claude for Chrome](/claude-for-chrome)
Claude for Chrome

- Claude for Microsoft 365

[Claude for Microsoft 365](/claude-for-microsoft-365)
Claude for Microsoft 365

- Skills

[Skills](/skills)
Skills

Models

- Mythos

[Mythos](https://www.anthropic.com/claude/mythos)
Mythos

- Fable

[Fable](https://www.anthropic.com/claude/fable)
Fable

- Opus

[Opus](https://www.anthropic.com/claude/opus)
Opus

- Sonnet

[Sonnet](https://www.anthropic.com/claude/sonnet)
Sonnet

- Haiku

[Haiku](https://www.anthropic.com/claude/haiku)
Haiku

Solutions

- AI agents

[AI agents](/solutions/agents)
AI agents

- Code modernization

[Code modernization](/solutions/code-modernization)
Code modernization

- Coding

[Coding](/solutions/coding)
Coding

- Customer support

[Customer support](/solutions/customer-support)
Customer support

- Cybersecurity

[Cybersecurity](/solutions/cybersecurity)
Cybersecurity

- Enterprise

[Enterprise](/solutions/enterprise)
Enterprise

- Financial services

[Financial services](/solutions/financial-services)
Financial services

- Government

[Government](/solutions/government)
Government

- Healthcare

[Healthcare](/solutions/healthcare)
Healthcare

- Higher education

[Higher education](/solutions/education)
Higher education

- K-12 teachers

[K-12 teachers](/solutions/teachers)
K-12 teachers

- Legal

[Legal](/solutions/legal)
Legal

- Life sciences

[Life sciences](/solutions/life-sciences)
Life sciences

- Nonprofits

[Nonprofits](/solutions/nonprofits)
Nonprofits

- Small business

[Small business](/solutions/small-business)
Small business

Claude Platform

- Overview

[Overview](/platform/api)
Overview

- Developer docs

[Developer docs](https://platform.claude.com/docs)
Developer docs

- Pricing

[Pricing](https://claude.com/pricing#api)
Pricing

- Ecosystem

[Ecosystem](/ecosystem)
Ecosystem

- Marketplace

[Marketplace](/platform/marketplace)
Marketplace

- Claude on AWS

[Claude on AWS](/partners/claude-on-aws)
Claude on AWS

- Google Cloud

[Google Cloud](/partners/google-cloud)
Google Cloud

- Microsoft Foundry

[Microsoft Foundry](/partners/microsoft-foundry)
Microsoft Foundry

- Regional compliance

[Regional compliance](/regional-compliance)
Regional compliance

- Console login

[Console login](https://platform.claude.com/)
Console login

Resources

- Blog

[Blog](/blog)
Blog

- Claude partner network

[Claude partner network](/partners)
Claude partner network

- Community

[Community](/community)
Community

- Connectors

[Connectors](/connectors)
Connectors

- Courses

[Courses](https://www.anthropic.com/learn)
Courses

- Customer stories

[Customer stories](/customers)
Customer stories

- Engineering at Anthropic

[Engineering at Anthropic](https://www.anthropic.com/engineering)
Engineering at Anthropic

- Events

[Events](https://www.anthropic.com/events)
Events

- Plugins

[Plugins](/plugins)
Plugins

- Powered by Claude

[Powered by Claude](/partners/powered-by-claude)
Powered by Claude

- Service partners

[Service partners](/partners/services)
Service partners

- Tutorials

[Tutorials](/resources/tutorials)
Tutorials

- Use cases

[Use cases](/resources/use-cases)
Use cases

Company

- Anthropic

[Anthropic](https://www.anthropic.com/)
Anthropic

- Careers

[Careers](https://www.anthropic.com/careers)
Careers

- Policy

[Policy](https://www.anthropic.com/policy)
Policy

- Economic Futures

[Economic Futures](https://www.anthropic.com/economic-futures)
Economic Futures

- Research

[Research](https://www.anthropic.com/research)
Research

- News

[News](https://www.anthropic.com/news)
News

- Policy on the AI Exponential

---
## plans-amp-pricing-claude-by-anthropic.md

Per month with annual subscription discount (\$200 billed up front). \$20 if billed monthly.

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Everything in Free, plus:

- More usage\*
- Includes Claude Code and Cowork
- Access to unlimited projects to organize chats and documents
- Access to Research
- Ability to use more Claude models
- Claude for Excel (beta)
- Claude for PowerPoint (beta)

### Max

Get the most out of Claude

From \$100

Per person billed monthly

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Everything in Pro, plus:

- Choose 5x or 20x more usage than Pro\*
- Higher output limits for all tasks
- Early access to advanced Claude features
- Priority access at high traffic times

Country

\*[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. *Prices shown don’t include applicable tax.*

## Compare features across plans

Free

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Pro

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Max 5x

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

Max 20x

[Try Claude](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994)

### Features and capabilities

#### Chat on web, iOS, Android and Desktop

#### Claude Code

#### Claude Cowork

#### Analyze text and images

#### Ability to search the web

#### Desktop extensions

#### Voice mode

#### Incognito chats

#### User preferences

#### Artifacts

#### Projects

#### Project sharing and collaboration

#### Create and edit files with code execution

#### Research

#### Memory

#### Skills

#### Connectors

#### Web search

#### Enterprise search

#### Claude for Excel

#### Claude for PowerPoint

#### Claude for Chrome

#### Claude for Slack

### Security and administration

#### Single sign-on (SSO) and domain capture

#### Central billing and administration

#### Admin controls for remote and local connectors

#### Enterprise deployment for the Claude desktop app

#### Role-based access

#### System for Cross-domain Identity Management (SCIM)

#### Audit logs

#### Usage analytics

#### Compliance API

#### HIPAA-ready offering

#### Custom data retention controls

#### Organization wide skills deployment

#### Google Docs cataloging

### Payment options

#### Credit card

n/a

#### ACH

#### Invoicing / net terms

#### Billing cycle

n/a

Monthly and annual

#### Adding seats midterm

n/a

### Models and usage

#### Opus

#### Sonnet

#### Haiku

#### Extra usage

#### Priority access at high traffic times

#### User and organizational level spend controls

#### Model training

Opt-out

### Team

For teams of 5 to 150

Get Team plan

[Get Team plan](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994/upgrade)

Get Team plan

Standard seat

All Claude features, plus more usage than Pro\*

\$20

Per seat / month if billed annually. \$25 if billed monthly.

Premium seat

5x more usage than standard seats\*

\$100

Per seat / month if billed annually. \$125 if billed monthly.

- Includes Claude Code and Cowork
- Connect Microsoft 365, Slack, and more
- Enterprise search across your organization
- Central billing and administration
- Single sign-on (SSO) and domain capture
- Admin controls for remote and local connectors
- Enterprise deployment for the Claude desktop app
- No model training on your content by default
- Mix and match seat types

### Enterprise

For large businesses operating at scale

\$20/seat. Usage is billed as you go at [API rates](#api)

Get Enterprise plan

[Get Enterprise plan](http://claude.ai/create/enterprise)

Get Enterprise plan

All Team plan features, plus:

- Admins set user and org spend limits
- Google Docs cataloging
- Role-based access with fine grained permissioning
- System for Cross-domain Identity Management (SCIM)
- Audit logs
- Compliance API for observability and monitoring
- Custom data retention controls
- Network-level access control
- IP allowlisting
- HIPAA-ready offering available

Quiz

Which plan is right for you?

Let's find out

Country

\*[Usage limits](https://support.anthropic.com/en/articles/9797557-usage-limit-best-practices) apply. *Prices shown don’t include applicable tax.*

Education plan

Get a comprehensive university‐wide plan for an institution, including its students, faculty, and staff.

Learn more

[Learn more](/solutions/education)

Learn more

Student and faculty access

Comprehensive access for all university members at discounted rates

Academic research and learning mode

Dedicated API credits and educational features for student learning

Training and enablement

Resources for successful adoption across your institution

## Compare features across plans

Team

Create plan

[Create plan](https://claude.ai/redirect/website.v1.7e047257-6763-4812-8a7b-5bcbe8589994/upgrade)

Create plan

Enterprise (self-serve)

Create plan

[Create plan](http://claude.ai/create/enterprise)

Create plan

Enterprise (sales-assisted)

[Contact sales](/contact-sales)

### Features and capabilities

#### Chat on web, iOS, Android and Desktop

#### Claude Code

#### Cowork

#### Analyze text and images

#### Ability to search the web

#### Desktop extensions

#### Voice mode

#### Incognito chats

#### User preferences

#### Artifacts

#### Projects

#### Project sharing and collaboration

#### Create and edit files with code execution

#### Research

#### Memory

#### Skills

#### Connectors

#### Web search

#### Enterprise search

#### Claude for Excel

#### Claude for PowerPoint

#### Claude for Chrome

#### Claude for Slack

### Security and administration

#### Single sign-on (SSO) and domain capture

#### Central billing and administration

#### Admin controls for remote and local connectors

#### Enterprise deployment for the Claude desktop app

#### Role-based access

#### System for Cross-domain Identity Management (SCIM)

#### Audit logs

#### Usage analytics

#### Compliance API

#### HIPAA-ready offering

#### Custom data retention controls

#### Organization wide skills deployment

#### Google Docs cataloging

### Payment options

#### Credit card

#### ACH

#### Invoicing / net terms

#### Billing cycle

Monthly and annual

Annual

#### Adding seats midterm

### Partnership

#### AWS Marketplace availability

#### Consultation

#### Tiered incentives on committed spend

#### Trials

#### Non-standard terms

#### Customer success support at certain spend thresholds

#### MSA

### Models and usage

#### Opus

#### Sonnet

#### Haiku

#### Extra usage

n/a

#### Priority access at high traffic times

#### User and organizational level spend controls

#### Model training

None by default

Latest models

[Contact sales](/contact-sales)

Start building

[Start building](../04-API-Reference/Other/platform-claude-com.md)

Start building

Save 50% with batch processing.

[Learn more](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

Batch processing

### Opus 4.6

Most intelligent model for agents and coding

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Sonnet 4.6

Optimal balance of intelligence, cost, and speed

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Haiku 4.5

Fastest, most cost-efficient model

Input

\$1 / MTok

Output

\$5 / MTok

Prompt caching

Write

\$1.25 / MTok

Read

\$0.10 / MTok

Country

**For workloads that need to run in the US, US-only inference is available at 1.1x pricing for input and output tokens.** [**Learn more**](../04-API-Reference/Guides/build-with-claude-data-residency-6c8e324ea6.md)**.**

Prompt caching pricing reflects 5-minute TTL. Learn about [extended prompt caching](../10-Prompting-Guides/build-with-claude-prompt-caching.md#1-hour-cache-duration).

Explore detailed pricing

[Explore detailed pricing](about-claude-pricing.md)

Explore detailed pricing

Pricing for tools

Get even more out of Claude with advanced features and capabilities.

Learn more

[Learn more](about-claude-pricing.md#specific-tool-pricing)

Learn more

#### Web search

Give Claude access to the latest information from the web. Doesn’t include input and output tokens required to process requests.

Cost

\$10 / 1K searches

Code execution

Run Python code in a sandboxed environment for advanced data analysis. 50 free hours of usage daily per organization.

Additional hours

\$0.05 per hour per container

Service tiers

Balance availability, performance, and predictable costs based on your needs.

Learn more

[Learn more](../04-API-Reference/Other/api-service-tiers-165fc24251.md)

Learn more

[Contact sales](/contact-sales)

Priority

When time, availability, and predictable pricing are most important

Standard

Default tier for both piloting and scaling everyday use cases

Batch

For asynchronous workloads that can be processed together for better efficiency

Legacy models

Learn more

[Learn more](../20-Models/about-claude-models-overview.md)

Learn more

Explore detailed pricing

[Explore detailed pricing](about-claude-pricing.md)

Explore detailed pricing

Save 50% with batch processing.

[Learn more](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

Batch processing

### Sonnet 4.5

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Opus 4.5

Input

\$5 / MTok

Output

\$25 / MTok

Prompt caching

Write

\$6.25 / MTok

Read

\$0.50 / MTok

### Opus 4.1

Input

\$15 / MTok

Output

\$75 / MTok

Prompt caching

Write

\$18.75 / MTok

Read

\$1.50 / MTok

### Sonnet 4

Input

\$3 / MTok

Output

\$15 / MTok

Prompt caching

Write

\$3.75 / MTok

Read

\$0.30 / MTok

### Opus 4

Input

\$15 / MTok

Output

\$75 / MTok

Prompt caching

Write

\$18.75 / MTok

Read

\$1.50 / MTok

### Haiku 3

Input

\$0.25 / MTok

Output

\$1.25 / MTok

Prompt caching

Write

\$0.30 / MTok

Read

\$0.03 / MTok

Prompt caching pricing reflects 5-minute TTL. Learn about [extended prompt caching](https://docs.claude.com/en/docs/build-with-claude/prompt-caching#pricing).

---
## purchase-and-manage-seats-on-enterprise-plans-7f70cfcac6.md

# Purchase and manage seats on Enterprise plans

This article covers how to add seats, manage your seat allocation, and handle member access on Enterprise plans. For pricing and billing details, see **[How am I billed for my Enterprise plan?](https://support.claude.com/en/articles/11526368-usage-based-enterprise-plans)**

**Permissions note:** Only Owners and Primary Owners can purchase seats and access **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**. Admins and above can reassign seat types for members in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**. To check your role, click your name or initials in the lower left corner—your role is listed next to your organization's plan type.

For information on adding and removing members from your organization, see **[Manage members on Team and Enterprise plans](https://support.claude.com/en/articles/13133750-managing-members-on-team-and-enterprise-plans)**.

**Important:** The main sections of this article describe the current Enterprise seat model, which applies to all new Enterprise plans.

- If your organization was provisioned before the transition to the single Enterprise seat and you see **Chat** and **Chat + Claude Code** seat types in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**, refer to **[Information for Chat and Chat + Claude Code plans](#h_2673e097fb)**.

- **[HIPAA-ready Enterprise organizations](https://support.claude.com/en/articles/13296973-hipaa-ready-enterprise-plans)** are an exception: they are provisioned with separate Chat and Chat + Claude Code seat types and are not eligible for the single Enterprise seat billing model.

- If you see **Standard** and **Premium** seat types, refer to **[Information for seat-based Enterprise plans](#h_6a78e30e26)**.

- Chat-only seats and Standard/Premium seats are no longer available for new contracts—both legacy plan types are transitioning to the single Enterprise seat at their next renewal.

------------------------------------------------------------------------

## Your seat type

Usage-based Enterprise plans use a single seat type: the **Enterprise seat**, priced per user per month (billed annually). This seat includes access to Claude on web, desktop, and mobile, as well as Claude Code.

Enterprise plans require a minimum of 20 seats.

------------------------------------------------------------------------

## Purchase new seats

You can add seats to your Enterprise plan at any time during your annual term. New seats are prorated for the remainder of your billing cycle and charged immediately.

1. Log in with your Owner or Primary Owner account.

2. Go to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

3. Click "Manage" under **Total seats**.

4. Click "Add or change seats."

5. Enter the number of seats you'd like to add.

6. Review your changes and the prorated charge before confirming.

7. Click "Confirm & purchase" to finalize.

**Note:** You can also purchase a seat while adding a new member. If you don't have an available seat when inviting someone, you'll be prompted to purchase one.

For details on how seat additions are billed, see **[How am I billed for my Enterprise plan?](https://support.claude.com/en/articles/11526368-how-am-i-billed-for-my-enterprise-plan)**

------------------------------------------------------------------------

## Remove seats

**Self-serve Enterprise plans:** Seats cannot be removed during your annual term. You can add seats at any time, but reductions to your seat count only take effect at renewal. If you need to make an exception, contact **[our Sales team](https://claude.com/contact-sales)** to discuss converting to a sales-assisted plan.

**Sales-assisted Enterprise plans:** Contact your account manager to discuss changes to your seat allocation.

Removing a member from your organization is different from reducing your seat count. When you remove a member, their seat becomes available to assign to someone else, so your total seat allocation and bill don't change. To reduce your bill, you'll need to reduce your total seat allocation. See **[Manage members on Team and Enterprise plans](https://support.claude.com/en/articles/13133750-managing-members-on-team-and-enterprise-plans)** for instructions on removing members.

------------------------------------------------------------------------

## Temporarily remove a member's access

The **No seat assigned** option lets you temporarily remove a member's access to Claude without removing them from your organization. This is useful for contractors or team members who need intermittent access.

To unassign a member:

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to unassign.

3. Click the dropdown under **Tier**.

4. Select "No seat assigned."

To restore their access, repeat the process and select “Enterprise seat.”

**Note:** Members with no seat assigned remain part of your organization but can't use Claude until you reassign them a seat.

------------------------------------------------------------------------

## Seat assignment with JIT or SCIM provisioning

**[Users provisioned via JIT or SCIM](https://support.claude.com/en/articles/13133195-setting-up-jit-or-scim-provisioning-to-manage-user-assignments-on-team-or-enterprise-plans)** are automatically assigned an Enterprise seat when they're added, provided one is available in your allocation. If no seat is available, provisioning will not complete until an owner purchases an additional seat.

Admins and above can manually adjust a member's status (e.g., remove their seat assignment) afterward in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

------------------------------------------------------------------------

## Cancel your Enterprise plan

**Self-serve Enterprise plans:** An Owner or Primary Owner can cancel your plan from **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Cancellation takes effect at the end of your current annual billing cycle—your organization will continue to have access until then.

**Sales-assisted Enterprise plans:** Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** to discuss cancellation.

------------------------------------------------------------------------

## Information for Chat and Chat + Claude Code plans

Some existing usage-based Enterprise organizations currently have two seat types: **Chat** and **Chat + Claude Code**. If you see these seat types in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**, this section applies to you. Your plan will transition to the single Enterprise seat model at your next contract renewal—see below for more information.

### Seat types

[TABLE]

You can mix and match seat types based on your team's needs. Assign Chat + Claude Code seats to team members who need coding workflows, while keeping others on Chat seats.

### Reassign users between seat types

You can move users between Chat and Chat + Claude Code seats within your existing allocation.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Tier**.

4. Select "Chat" or "Chat + Claude Code."

Members moved from Chat + Claude Code to Chat will lose Claude Code access, and vice versa.

The **Tier** dropdown only shows seat types your plan already owns. If your plan includes Chat + Claude Code seats but they're all assigned, you'll be prompted to purchase one. If your plan has no seats of that type, see **[Purchase new seats](#h_91344d9191)** above to add one first.

### Swap users between seat types

If all your Chat + Claude Code seats are assigned and you need to move one user to that type while moving another off it, use **No seat assigned** to free up a seat first.

**Example:** You have ten Chat + Claude Code seats, all assigned. You want to move User A (currently on Chat + Claude Code) to Chat, and move User B (currently on Chat) to Chat + Claude Code — without purchasing an additional seat.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find User A and change their seat type to "No seat assigned." This frees up one Chat + Claude Code seat.

3. Find User B and change their seat type to "Chat + Claude Code." They now occupy the freed seat.

4. Find User A and change their seat type to "Chat."

### Seat assignment with JIT or SCIM provisioning

Users provisioned via JIT or SCIM are automatically assigned to the highest-available seat type (Chat + Claude Code, if available) when they're added. Admins and above can manually reassign seat types afterward in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

You can also use Advanced Group Mappings with JIT or SCIM to provision users directly to a specific seat type.

### Transition to the single Enterprise seat

**Note: [HIPAA-ready organizations](https://support.claude.com/en/articles/13296973-hipaa-ready-enterprise-plans)** are provisioned with separate Chat and Chat + Claude Code seat types and are not eligible for the unified seat type.

At your next renewal, you will switch to the single Enterprise seat model upon signing a new contract. This seat includes Claude Code, Cowork, Chat and more.

Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** with questions about your upcoming renewal.

------------------------------------------------------------------------

## Information for seat-based Enterprise plans

Some Enterprise organizations are on older seat-based plans with a different billing structure than the usage-based model described above. If you see **Standard** and **Premium** seats in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**, this section applies to you.

### Seat types

[TABLE]

### Reassign users between seat types

You can move users between Standard and Premium seats within your existing allocation.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Tier**.

4. Select "Standard" or "Premium."

Members moved from Premium to Standard will have lower usage limits, and vice versa.

The **Tier** dropdown only shows seat types your plan already owns. If your plan includes Premium seats but they're all assigned, reassigning another user to Premium will prompt you to purchase an additional seat. If your plan has no seats of that type, see **[Purchase new seats](#h_91344d9191)** above to add one first.

### Swap users between seat types

If all your Premium seats are assigned and you need to move one user to Premium while moving another to Standard, use **No seat assigned** to free up a seat first.

**Example:** You have ten Premium seats, all assigned. You want to move User A (currently on Premium) to Standard, and move User B (currently on Standard) to Premium—without purchasing an additional seat.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find User A and change their seat type to "No seat assigned." This frees up one Premium seat.

3. Find User B and change their seat type to "Premium." They now occupy the freed seat.

4. Find User A and change their seat type to "Standard."

### Billing and usage credits

Seat-based Enterprise plans charge a flat monthly fee per seat that includes usage limits. Owners can enable usage credits to allow team members to continue working after reaching their seat's usage limits. For details, see **[Manage usage credits for Team and seat-based Enterprise plans](https://support.claude.com/en/articles/12005970-)**.

For specific information about seat-based Enterprise pricing, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

### Transition to the single Enterprise seat

At your next contract renewal, your plan will transition to the usage-based single Enterprise seat model described in the main sections of this article. If you'd like to migrate before your renewal, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

---
## purchase-and-manage-seats-on-enterprise-plans.md

4. Purchase and manage seats on Enterprise plans

# Purchase and manage seats on Enterprise plans

**Permissions note:** Only Owners and Primary Owners can purchase seats and access **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Admins and above can reassign seat types for members in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

For information on adding and removing members from your organization, see **[Manage members on Team and Enterprise plans](managing-members-on-team-and-enterprise-plans.md)**.

**Important:** If your organization currently has **Chat** and **Chat + Claude Code** seats, see **[Information for Chat and Chat + Claude Code plans](#h_2673e097fb)**. If your organization has **Standard** and **Premium** seats, see **[Information for seat-based Enterprise plans](#h_6a78e30e26)**. Both plan types are transitioning to the single-seat model described in the main sections of this article.

------------------------------------------------------------------------

## Your seat type

Enterprise plans require a minimum of 20 seats.

------------------------------------------------------------------------

## Add seats

You can add seats to your Enterprise plan at any time during your annual term. New seats are prorated for the remainder of your billing cycle and charged immediately.

1. Log in with your Owner or Primary Owner account.

2. Go to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**.

3. Click the pencil icon under **Seats**.

4. Enter the number of seats you'd like to add.

5. Review your changes and the prorated charge before confirming.

6. Click "Upgrade" to finalize.

**Note:** You can also purchase a seat while adding a new member. If you don't have an available seat when inviting someone, you'll be prompted to purchase one.

For details on how seat additions are billed, see **[How am I billed for my Enterprise plan?](how-am-i-billed-for-my-enterprise-plan.md)**

------------------------------------------------------------------------

## Remove seats

**Self-serve Enterprise plans:** Seats cannot be removed during your annual term. You can add seats at any time, but reductions to your seat count only take effect at renewal. If you need to make an exception, contact our **[Sales team](https://claude.com/contact-sales)** to discuss converting to a sales-assisted plan.

**Sales-assisted Enterprise plans:** Contact your account manager to discuss changes to your seat allocation.

Removing a member from your organization is different from reducing your seat count. When you remove a member, their seat becomes available to assign to someone else — your total seat allocation and bill don't change. To reduce your bill, you'll need to reduce your total seat allocation. See **[Manage members on Team and Enterprise plans](managing-members-on-team-and-enterprise-plans.md)** for instructions on removing members.

------------------------------------------------------------------------

## Temporarily remove a member's access

The **unassigned** option lets you temporarily remove a member's access to Claude without removing them from your organization. This is useful for contractors or team members who need intermittent access.

To unassign a member:

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization).**

2. Find the member you want to unassign.

3. Click the dropdown under **Seat Type**.

4. Select "Unassigned."

To restore their access, repeat the process and select “Enterprise seat.”

**Note:** Unassigned members remain part of your organization but cannot use Claude until they're assigned to a seat.

------------------------------------------------------------------------

## Seat assignment with JIT or SCIM provisioning

**[Users provisioned via JIT or SCIM](../21-Account-Support/setting-up-jit-or-scim-provisioning-to-manage-user-assignments-on-team-or-enterp.md)** are automatically assigned an Enterprise seat when they're added, provided one is available in your allocation. If no seat is available, provisioning will not complete until an Owner purchases an additional seat.

Admins and above can manually adjust a member's status (e.g., set to unassigned) afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

------------------------------------------------------------------------

## Cancel your Enterprise plan

**Self-serve Enterprise plans:** An Owner or Primary Owner can cancel your plan from **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Cancellation takes effect at the end of your current annual billing cycle — your organization will continue to have access until then.

**Sales-assisted Enterprise plans:** Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** to discuss cancellation.

------------------------------------------------------------------------

## Information for Chat and Chat + Claude Code plans

Some existing usage-based Enterprise organizations currently have two seat types: **Chat** and **Chat + Claude Code**. If you see these seat types in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you. Your plan will transition to the single Enterprise seat model at your next contract renewal — see below for more information.

### Seat types

[TABLE]

You can mix and match seat types based on your team's needs. Assign Chat + Claude Code seats to team members who need coding workflows, while keeping others on Chat seats.

### Reassign users between seat types

You can move users between Chat and Chat + Claude Code seats within your existing allocation.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization).**

2. Find the member you want to reassign.

3. Click the dropdown under **Seat Type**.

4. Select Chat or Chat + Claude Code.

Members moved from Chat + Claude Code to Chat will lose Claude Code access, and vice versa. If you try to assign a user to Chat + Claude Code but don't have any available seats of that type, you'll be prompted to purchase one.

### Swap users between seat types

If all your Chat + Claude Code seats are assigned and you need to move one user to that type while moving another off it, use the unassigned option to free up a seat first.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization).**

2. Find User A and change their seat type to "Unassigned." This frees up one Chat + Claude Code seat.

3. Find User B and change their seat type to "Chat + Claude Code." They now occupy the freed seat.

4. Find User A and change their seat type to "Chat."

### Seat assignment with JIT or SCIM provisioning

Users provisioned via JIT or SCIM are automatically assigned to the highest-available seat type (Chat + Claude Code, if available) when they're added. Admins and above can manually reassign seat types afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

You can also use Advanced Group Mappings with JIT or SCIM to provision users directly to a specific seat type.

### Transition to the single Enterprise seat

At your next renewal, you will switch to the single Enterprise seat model upon signing a new contract. This seat includes Claude Code, Cowork, Chat and more.

Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** with questions about your upcoming renewal.

------------------------------------------------------------------------

## Information for seat-based Enterprise plans

Some Enterprise organizations are on older seat-based plans with a different billing structure than the usage-based model described above. If you see **Standard** and **Premium** seats in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you.

### Seat types

[TABLE]

### Reassign users between seat types

You can move users between Standard and Premium seats within your existing allocation.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**

2. Find the member you want to reassign.

3. Click the dropdown under **Seat Type**.

4. Select Standard or Premium.

Members moved from Premium to Standard will have lower usage limits, and vice versa.

If you try to reassign a user to Premium but don't have any available Premium seats, you'll be prompted to purchase an additional seat.

### Swap users between seat types

If all your Premium seats are assigned and you need to move one user to Premium while moving another to Standard, use the unassigned option to free up a seat first.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**

2. Find User A and change their seat type to "Unassigned." This frees up one Premium seat.

3. Find User B and change their seat type to "Premium." They now occupy the freed seat.

4. Find User A and change their seat type to "Standard."

### Billing and extra usage

Seat-based Enterprise plans charge a flat monthly fee per seat that includes usage limits. Owners can enable extra usage to allow team members to continue working after reaching their seat's usage limits. For details, see **[Extra usage for Team and seat-based Enterprise plans](extra-usage-for-team-and-seat-based-enterprise-plans.md)**.

For specific information about seat-based Enterprise pricing, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

### Transition to the single Enterprise seat

---
## purchase-and-manage-seats-on-team-plans-a3fca40028.md

# Purchase and manage seats on Team plans

Seat management allows Team plan owners to control their organization's seat allocation, assign users to different seat types, and manage billing. For pricing and billing details, see **[How is my Team plan bill calculated?](https://support.claude.com/en/articles/9267289-how-is-my-team-plan-bill-calculated)**

**Permissions note:** Only Owners and Primary Owners can purchase seats and access **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Admins and above can reassign seat types for members in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

For information on adding and removing members from your organization, see **[Manage members on Team and Enterprise plans](https://support.claude.com/en/articles/13133750)**.

------------------------------------------------------------------------

## Understanding seat types

Team plans offer two seat types:

[TABLE]

Organizations can mix and match seat types based on team needs. Assign Premium seats to power users who need more capacity, while keeping other team members on Standard seats.

Your plan has a total seat allocation (e.g., 30 Standard seats and 10 Premium seats). Within that allocation, you can assign and reassign users to different seat types as needed.

------------------------------------------------------------------------

## Purchase new seats

**Important:** If you want to upgrade an existing member from Standard to Premium and already have Premium seats available, you don't need to purchase a new seat. Use the seat tier reassignment in **[Organization settings \> Members](https://claude.ai/admin-settings/members)** instead. See **[Upgrade a Standard seat to Premium](#h_e7a7f4f396)** below.

Follow these steps to add seats to your plan's total allocation:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

3. Click "Manage" under "Total seats."

4. In the "Seat breakdown" modal, click "Add or change seats."

5. Click the "+" next to the seat type you want to add (Standard or Premium).

6. Click "Next" to review your purchase details and confirm the billing impact.

7. Check the confirmation box before continuing.

8. Click "Confirm & purchase" to complete the transaction.

**Note:** You can also purchase seats while adding a new member. The seat type selector only shows seat types your plan already owns—if all seats of the selected type are assigned, you'll be prompted to purchase one.

------------------------------------------------------------------------

## Reduce your seat allocation

You can reduce the total number of seats on your Team plan:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

3. If needed, remove members or reassign them to free up the seats you want to eliminate.

4. Click “Manage” under **Total seats**.

5. Click “Add or change seats” in the **Seat breakdown** modal.

6. Click the "**-**" next to the seat type you want to reduce.

7. Click “Next” to review the changes.

8. Check the confirmation box and click "Confirm & purchase" to complete the change.

------------------------------------------------------------------------

## Assign and reassign seat types

You can move users between Standard and Premium seats within your existing allocation.

To reassign a user's seat type:

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Tier**.

4. Select "Standard" or "Premium."

Members moved from Premium to Standard will have lower usage limits, and vice versa.

------------------------------------------------------------------------

## Upgrade a Standard seat to Premium

Upgrading a member from Standard to Premium is a reassignment, not a new purchase. You don't need to buy an additional seat unless your Premium allocation is already full.

**Note:** The **Tier** dropdown only shows seat types your plan already owns. If your plan has zero Premium seats, Premium won't appear as an option yet. First add at least one Premium seat by following the steps in **[Purchase new seats](#h_f05a756e78)** above. Once your plan includes a Premium seat, you can select "Premium" from the dropdown.

1\. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2\. Find the member assigned to a Standard seat you want to upgrade.

3\. Click the dropdown under **Tier**.

4\. Select "Premium."

If your plan includes Premium seats but they're all assigned, you'll be prompted to purchase an additional one at this point. The upgrade is prorated based on your billing cycle, and you'll be charged the price difference immediately.

### What if I don't have an available seat?

If your plan includes Premium seats but they're all assigned, reassigning another user to Premium will prompt you to purchase an additional Premium seat. If your plan has no Premium seats at all, see **[Purchase new seats](#h_f05a756e78)** above to add one first.

------------------------------------------------------------------------

## Swap users between seat types

Selecting **No seat assigned** lets you temporarily remove a user from a seat without removing them from your organization. This is useful when you need to swap people between seat types within your existing allocation.

**Example:** You have five Premium seats, all assigned. You want to move User A (currently on Premium) to Standard, and move User B (currently on Standard) to Premium—without purchasing an additional seat.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find User A and change their seat tier to "No seat assigned." This frees up one Premium seat.

3. Find User B and change their seat tier to "Premium." They now occupy the available Premium seat.

4. Find User A and change their seat tier to "Standard."

**Note:** Unassigned users remain members of your organization but cannot use Claude until they're assigned to a seat.

------------------------------------------------------------------------

## Seat assignment with JIT or SCIM provisioning

**[Users provisioned via JIT or SCIM](https://support.claude.com/en/articles/13133195-setting-up-jit-or-scim-provisioning-to-manage-user-assignments-on-team-or-enterprise-plans)** are automatically assigned to the highest-available seat type when they're added. Admins and above can manually reassign seat types afterward in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

You can also enable group mappings with JIT or SCIM to provision users directly to a specific seat type.

------------------------------------------------------------------------

## Understanding billing

- **New seats** are prorated based on your billing cycle and charged immediately.

- **Seat type upgrades** (Standard → Premium) are prorated and charged immediately for the price difference.

- **Removing members** does not trigger an immediate credit or refund. The seat becomes available to assign to another member. To reduce your bill, you'll need to reduce your plan's total seat allocation.

For detailed billing calculations and examples, see **[How is my Team plan bill calculated?](https://support.claude.com/en/articles/9267289-how-is-my-team-plan-bill-calculated)**

---
## purchase-and-manage-seats-on-team-plans.md

4. Purchase and manage seats on Team plans

# Purchase and manage seats on Team plans

**Permissions note:** Only Owners and Primary Owners can purchase seats and access **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Admins and above can reassign seat types for members in **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

For information on adding and removing members from your organization, see **[Managing members on Team and Enterprise plans](managing-members-on-team-and-enterprise-plans.md)**.

------------------------------------------------------------------------

## Understanding seat types

Team plans offer two seat types:

[TABLE]

Organizations can mix and match seat types based on team needs. Assign Premium seats to power users who need more capacity, while keeping other team members on Standard seats.

Your plan has a total seat allocation (e.g., 30 Standard seats and 10 Premium seats). Within that allocation, you can assign and reassign users to different seat types as needed.

------------------------------------------------------------------------

## Purchasing new seats

**Important:** If you want to upgrade an existing member from Standard to Premium, you don't need to purchase a new seat. Use the seat tier reassignment in **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)** instead — see **[Upgrading a Standard seat to Premium](#h_e7a7f4f396)** below.

Follow these steps to add seats to your plan's total allocation:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

3. Click "Manage" under "Total seats."

4. In the "Seat breakdown" modal, click "Add or change seats."

5. Click the "**+**" next to the seat type you want to add (Standard or Premium).

6. Click "Next" to review your purchase details and confirm the billing impact.

7. Check the confirmation box before continuing.

8. Click "Confirm & purchase" to complete the transaction.

**Note:** You can also purchase seats while adding a new member. If you don't have an available seat of the selected type, you'll be prompted to purchase one.

------------------------------------------------------------------------

## Reducing your seat allocation

You can reduce the total number of seats on your Team plan:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

3. If needed, remove members or reassign them to free up the seats you want to eliminate.

4. Click “Manage” under **Total seats**.

5. Click “Add or change seats” in the **Seat breakdown** modal.

6. Click the "**-**" next to the seat type you want to reduce.

7. Click “Next” to review the changes.

8. Check the confirmation box and click "Confirm & purchase" to complete the change.

------------------------------------------------------------------------

## Assigning and reassigning seat types

You can move users between Standard and Premium seats within your existing allocation.

To reassign a user's seat type:

1. Go to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Seat Tier**.

4. Select Standard or Premium.

Members moved from Premium to Standard will have lower usage limits, and vice versa.

## Upgrading a Standard seat to Premium

Upgrading a member from Standard to Premium is a reassignment, not a new purchase. You don't need to buy an additional seat unless your Premium allocation is already full.

1\. Go to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

2\. Find the member assigned to a Standard seat you want to upgrade.

3\. Click the dropdown under **Seat Tier**.

4\. Select "Premium."

If you have no available Premium seats, you'll be prompted to purchase one at this point.

The upgrade is prorated based on your billing cycle, and you'll be charged the price difference immediately.

### What if I don't have an available seat?

If you try to reassign a user to Premium but don't have any available Premium seats, you'll then be prompted to purchase an additional Premium seat.

## Using "unassigned" to swap users between seat types

The unassigned option allows you to temporarily remove a user from a seat without removing them from your organization. This is useful when you need to swap people between seat types within your existing allocation.

1. Go to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Find User A and change their seat tier to "Unassigned." This frees up one Premium seat.

3. Find User B and change their seat tier to "Premium." They now occupy the available Premium seat.

4. Find User A and change their seat tier to "Standard."

**Note:** Unassigned users remain members of your organization but cannot use Claude until they're assigned to a seat.

## Seat assignment with JIT or SCIM provisioning

**[Users provisioned via JIT or SCIM](../21-Account-Support/setting-up-jit-or-scim-provisioning-to-manage-user-assignments-on-team-or-enterp.md)** are automatically assigned to the highest-available seat type when they're added. Admins and above can manually reassign seat types afterward in **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

You can also enable group mappings with JIT or SCIM to provision users directly to a specific seat type.

------------------------------------------------------------------------

## Understanding billing

- **New seats** are prorated based on your billing cycle and charged immediately.

- **Seat type upgrades** (Standard → Premium) are prorated and charged immediately for the price difference.

For detailed billing calculations and examples, see **[How is my Team plan bill calculated?](how-is-my-team-plan-bill-calculated.md)**

---
## purchasing-and-managing-seats-on-enterprise-plans-4d55fc910a.md

# Purchase and manage seats on Enterprise plans

**Important:** The main sections of this article describe the current Enterprise seat model, which applies to all new Enterprise plans.

- If your organization was provisioned before the transition to the single Enterprise seat and you see **Chat** and **Chat + Claude Code** seat types in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**, refer to **[Information for Chat and Chat + Claude Code plans](#h_2673e097fb)**.

- If you see **Standard** and **Premium** seat types, refer to **[Information for seat-based Enterprise plans](#h_6a78e30e26)**.

- Chat-only seats and Standard/Premium seats are no longer available for new contracts—both legacy plan types are transitioning to the single Enterprise seat at their next renewal.

------------------------------------------------------------------------

## Your seat type

Enterprise plans require a minimum of 20 seats.

------------------------------------------------------------------------

## Purchase new seats

You can add seats to your Enterprise plan at any time during your annual term. New seats are prorated for the remainder of your billing cycle and charged immediately.

1. Log in with your Owner or Primary Owner account.

2. Go to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

3. Click "Manage" under **Total seats**.

4. Click "Add or change seats."

5. Enter the number of seats you'd like to add.

6. Review your changes and the prorated charge before confirming.

7. Click "Confirm & purchase" to finalize.

**Note:** You can also purchase a seat while adding a new member. If you don't have an available seat when inviting someone, you'll be prompted to purchase one.

For details on how seat additions are billed, see **[How am I billed for my Enterprise plan?](https://support.claude.com/en/articles/11526368-how-am-i-billed-for-my-enterprise-plan)**

------------------------------------------------------------------------

## Remove seats

**Sales-assisted Enterprise plans:** Contact your account manager to discuss changes to your seat allocation.

------------------------------------------------------------------------

## Temporarily remove a member's access

To unassign a member:

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to unassign.

3. Click the dropdown under **Tier**.

4. Select "No seat assigned."

To restore their access, repeat the process and select “Enterprise seat.”

**Note:** Members with no seat assigned remain part of your organization but can't use Claude until you reassign them a seat.

------------------------------------------------------------------------

## Seat assignment with JIT or SCIM provisioning

Admins and above can manually adjust a member's status (e.g., remove their seat assignment) afterward in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

------------------------------------------------------------------------

## Cancel your Enterprise plan

**Sales-assisted Enterprise plans:** Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** to discuss cancellation.

------------------------------------------------------------------------

## Information for Chat and Chat + Claude Code plans

### Seat types

[TABLE]

You can mix and match seat types based on your team's needs. Assign Chat + Claude Code seats to team members who need coding workflows, while keeping others on Chat seats.

### Reassign users between seat types

You can move users between Chat and Chat + Claude Code seats within your existing allocation.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Tier**.

4. Select "Chat" or "Chat + Claude Code."

Members moved from Chat + Claude Code to Chat will lose Claude Code access, and vice versa.

### Swap users between seat types

If all your Chat + Claude Code seats are assigned and you need to move one user to that type while moving another off it, use **No seat assigned** to free up a seat first.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find User A and change their seat type to "No seat assigned." This frees up one Chat + Claude Code seat.

3. Find User B and change their seat type to "Chat + Claude Code." They now occupy the freed seat.

4. Find User A and change their seat type to "Chat."

### Seat assignment with JIT or SCIM provisioning

You can also use Advanced Group Mappings with JIT or SCIM to provision users directly to a specific seat type.

### Transition to the single Enterprise seat

At your next renewal, you will switch to the single Enterprise seat model upon signing a new contract. This seat includes Claude Code, Cowork, Chat and more.

Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** with questions about your upcoming renewal.

------------------------------------------------------------------------

## Information for seat-based Enterprise plans

### Seat types

[TABLE]

### Reassign users between seat types

You can move users between Standard and Premium seats within your existing allocation.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Tier**.

4. Select "Standard" or "Premium."

Members moved from Premium to Standard will have lower usage limits, and vice versa.

### Swap users between seat types

If all your Premium seats are assigned and you need to move one user to Premium while moving another to Standard, use **No seat assigned** to free up a seat first.

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find User A and change their seat type to "No seat assigned." This frees up one Premium seat.

3. Find User B and change their seat type to "Premium." They now occupy the freed seat.

4. Find User A and change their seat type to "Standard."

### Billing and usage credits

For specific information about seat-based Enterprise pricing, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

### Transition to the single Enterprise seat

---
## purchasing-and-managing-seats-on-enterprise-plans.md

4. Purchase and manage seats on Enterprise plans

# Purchase and manage seats on Enterprise plans

For information on adding and removing members from your organization, see **[Manage members on Team and Enterprise plans](managing-members-on-team-and-enterprise-plans.md)**.

------------------------------------------------------------------------

## Your seat type

Enterprise plans require a minimum of 20 seats.

------------------------------------------------------------------------

## Add seats

You can add seats to your Enterprise plan at any time during your annual term. New seats are prorated for the remainder of your billing cycle and charged immediately.

1. Log in with your Owner or Primary Owner account.

2. Go to **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**.

3. Click the pencil icon under **Seats**.

4. Enter the number of seats you'd like to add.

5. Review your changes and the prorated charge before confirming.

6. Click "Upgrade" to finalize.

**Note:** You can also purchase a seat while adding a new member. If you don't have an available seat when inviting someone, you'll be prompted to purchase one.

For details on how seat additions are billed, see **[How am I billed for my Enterprise plan?](how-am-i-billed-for-my-enterprise-plan.md)**

------------------------------------------------------------------------

## Remove seats

**Self-serve Enterprise plans:** Seats cannot be removed during your annual term. You can add seats at any time, but reductions to your seat count only take effect at renewal. If you need to make an exception, contact our **[Sales team](https://claude.com/contact-sales)** to discuss converting to a sales-assisted plan.

**Sales-assisted Enterprise plans:** Contact your account manager to discuss changes to your seat allocation.

------------------------------------------------------------------------

## Temporarily remove a member's access

To unassign a member:

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization).**

2. Find the member you want to unassign.

3. Click the dropdown under **Seat Type**.

4. Select "Unassigned."

To restore their access, repeat the process and select “Enterprise seat.”

**Note:** Unassigned members remain part of your organization but cannot use Claude until they're assigned to a seat.

------------------------------------------------------------------------

## Seat assignment with JIT or SCIM provisioning

Admins and above can manually adjust a member's status (e.g., set to unassigned) afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

------------------------------------------------------------------------

## Cancel your Enterprise plan

**Self-serve Enterprise plans:** An Owner or Primary Owner can cancel your plan from **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Cancellation takes effect at the end of your current annual billing cycle — your organization will continue to have access until then.

**Sales-assisted Enterprise plans:** Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** to discuss cancellation.

------------------------------------------------------------------------

## Information for Chat and Chat + Claude Code plans

Some existing usage-based Enterprise organizations currently have two seat types: **Chat** and **Chat + Claude Code**. If you see these seat types in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you. Your plan will transition to the single Enterprise seat model at your next contract renewal — see below for more information.

### Seat types

[TABLE]

You can mix and match seat types based on your team's needs. Assign Chat + Claude Code seats to team members who need coding workflows, while keeping others on Chat seats.

### Reassign users between seat types

You can move users between Chat and Chat + Claude Code seats within your existing allocation.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization).**

2. Find the member you want to reassign.

3. Click the dropdown under **Seat Type**.

4. Select Chat or Chat + Claude Code.

### Swap users between seat types

If all your Chat + Claude Code seats are assigned and you need to move one user to that type while moving another off it, use the unassigned option to free up a seat first.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization).**

2. Find User A and change their seat type to "Unassigned." This frees up one Chat + Claude Code seat.

3. Find User B and change their seat type to "Chat + Claude Code." They now occupy the freed seat.

4. Find User A and change their seat type to "Chat."

### Seat assignment with JIT or SCIM provisioning

Users provisioned via JIT or SCIM are automatically assigned to the highest-available seat type (Chat + Claude Code, if available) when they're added. Admins and above can manually reassign seat types afterward in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**.

You can also use Advanced Group Mappings with JIT or SCIM to provision users directly to a specific seat type.

### Transition to the single Enterprise seat

At your next renewal, you will switch to the single Enterprise seat model upon signing a new contract. This seat includes Claude Code, Cowork, Chat and more.

Reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)** with questions about your upcoming renewal.

------------------------------------------------------------------------

## Information for seat-based Enterprise plans

Some Enterprise organizations are on older seat-based plans with a different billing structure than the usage-based model described above. If you see **Standard** and **Premium** seats in **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**, this section applies to you.

### Seat types

[TABLE]

### Reassign users between seat types

You can move users between Standard and Premium seats within your existing allocation.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**

2. Find the member you want to reassign.

3. Click the dropdown under **Seat Type**.

4. Select Standard or Premium.

Members moved from Premium to Standard will have lower usage limits, and vice versa.

If you try to reassign a user to Premium but don't have any available Premium seats, you'll be prompted to purchase an additional seat.

### Swap users between seat types

If all your Premium seats are assigned and you need to move one user to Premium while moving another to Standard, use the unassigned option to free up a seat first.

1. Go to **[Organization settings \> Organization](https://claude.ai/admin-settings/organization)**

2. Find User A and change their seat type to "Unassigned." This frees up one Premium seat.

3. Find User B and change their seat type to "Premium." They now occupy the freed seat.

4. Find User A and change their seat type to "Standard."

### Billing and extra usage

For specific information about seat-based Enterprise pricing, reach out to your Anthropic Contact or **[our Sales team](https://claude.com/contact-sales)**.

### Transition to the single Enterprise seat

---
## purchasing-and-managing-seats-on-team-plans-067eda0415.md

# Purchase and manage seats on Team plans

**Permissions note:** Only Owners and Primary Owners can purchase seats and access **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Admins and above can reassign seat types for members in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

For information on adding and removing members from your organization, see **[Manage members on Team and Enterprise plans](https://support.claude.com/en/articles/13133750)**.

------------------------------------------------------------------------

## Understanding seat types

Team plans offer two seat types:

[TABLE]

Organizations can mix and match seat types based on team needs. Assign Premium seats to power users who need more capacity, while keeping other team members on Standard seats.

Your plan has a total seat allocation (e.g., 30 Standard seats and 10 Premium seats). Within that allocation, you can assign and reassign users to different seat types as needed.

------------------------------------------------------------------------

## Purchase new seats

Follow these steps to add seats to your plan's total allocation:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

3. Click "Manage" under "Total seats."

4. In the "Seat breakdown" modal, click "Add or change seats."

5. Click the "+" next to the seat type you want to add (Standard or Premium).

6. Click "Next" to review your purchase details and confirm the billing impact.

7. Check the confirmation box before continuing.

8. Click "Confirm & purchase" to complete the transaction.

------------------------------------------------------------------------

## Reduce your seat allocation

You can reduce the total number of seats on your Team plan:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

3. If needed, remove members or reassign them to free up the seats you want to eliminate.

4. Click “Manage” under **Total seats**.

5. Click “Add or change seats” in the **Seat breakdown** modal.

6. Click the "**-**" next to the seat type you want to reduce.

7. Click “Next” to review the changes.

8. Check the confirmation box and click "Confirm & purchase" to complete the change.

------------------------------------------------------------------------

## Assign and reassign seat types

You can move users between Standard and Premium seats within your existing allocation.

To reassign a user's seat type:

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Tier**.

4. Select "Standard" or "Premium."

Members moved from Premium to Standard will have lower usage limits, and vice versa.

------------------------------------------------------------------------

## Upgrade a Standard seat to Premium

Upgrading a member from Standard to Premium is a reassignment, not a new purchase. You don't need to buy an additional seat unless your Premium allocation is already full.

1\. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2\. Find the member assigned to a Standard seat you want to upgrade.

3\. Click the dropdown under **Tier**.

4\. Select "Premium."

### What if I don't have an available seat?

------------------------------------------------------------------------

## Swap users between seat types

1. Go to **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

2. Find User A and change their seat tier to "No seat assigned." This frees up one Premium seat.

3. Find User B and change their seat tier to "Premium." They now occupy the available Premium seat.

4. Find User A and change their seat tier to "Standard."

**Note:** Unassigned users remain members of your organization but cannot use Claude until they're assigned to a seat.

------------------------------------------------------------------------

## Seat assignment with JIT or SCIM provisioning

**[Users provisioned via JIT or SCIM](https://support.claude.com/en/articles/13133195-setting-up-jit-or-scim-provisioning-to-manage-user-assignments-on-team-or-enterprise-plans)** are automatically assigned to the highest-available seat type when they're added. Admins and above can manually reassign seat types afterward in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**.

You can also enable group mappings with JIT or SCIM to provision users directly to a specific seat type.

------------------------------------------------------------------------

## Understanding billing

- **New seats** are prorated based on your billing cycle and charged immediately.

- **Seat type upgrades** (Standard → Premium) are prorated and charged immediately for the price difference.

For detailed billing calculations and examples, see **[How is my Team plan bill calculated?](https://support.claude.com/en/articles/9267289-how-is-my-team-plan-bill-calculated)**

---
## purchasing-and-managing-seats-on-team-plans.md

4. Purchase and manage seats on Team plans

# Purchase and manage seats on Team plans

**Permissions note:** Only Owners and Primary Owners can purchase seats and access **[Organization settings \> Billing](https://claude.ai/admin-settings/billing)**. Admins and above can reassign seat types for members in **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

For information on adding and removing members from your organization, see **[Managing members on Team and Enterprise plans](managing-members-on-team-and-enterprise-plans.md)**.

------------------------------------------------------------------------

## Understanding seat types

Team plans offer two seat types:

[TABLE]

Organizations can mix and match seat types based on team needs. Assign Premium seats to power users who need more capacity, while keeping other team members on Standard seats.

Your plan has a total seat allocation (e.g., 30 Standard seats and 10 Premium seats). Within that allocation, you can assign and reassign users to different seat types as needed.

------------------------------------------------------------------------

## Purchasing new seats

Follow these steps to add seats to your plan's total allocation:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

3. Click "Manage" under "Total seats."

4. In the "Seat breakdown" modal, click "Add or change seats."

5. Click the "**+**" next to the seat type you want to add (Standard or Premium).

6. Click "Next" to review your purchase details and confirm the billing impact.

7. Check the confirmation box before continuing.

8. Click "Confirm & purchase" to complete the transaction.

**Note:** You can also purchase seats while adding a new member. If you don't have an available seat of the selected type, you'll be prompted to purchase one.

------------------------------------------------------------------------

## Reducing your seat allocation

You can reduce the total number of seats on your Team plan:

1. Log in with your Owner or Primary Owner account.

2. Navigate to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

3. If needed, remove members or reassign them to free up the seats you want to eliminate.

4. Click “Manage” under **Total seats**.

5. Click “Add or change seats” in the **Seat breakdown** modal.

6. Click the "**-**" next to the seat type you want to reduce.

7. Click “Next” to review the changes.

8. Check the confirmation box and click "Confirm & purchase" to complete the change.

------------------------------------------------------------------------

## Assigning and reassigning seat types

You can move users between Standard and Premium seats within your existing allocation.

To reassign a user's seat type:

1. Go to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Find the member you want to reassign.

3. Click the dropdown under **Seat Tier**.

4. Select Standard or Premium.

Members moved from Premium to Standard will have lower usage limits, and vice versa.

## Upgrading a Standard seat to Premium

Upgrading a member from Standard to Premium is a reassignment, not a new purchase. You don't need to buy an additional seat unless your Premium allocation is already full.

1\. Go to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

2\. Find the member assigned to a Standard seat you want to upgrade.

3\. Click the dropdown under **Seat Tier**.

4\. Select "Premium."

If you have no available Premium seats, you'll be prompted to purchase one at this point.

The upgrade is prorated based on your billing cycle, and you'll be charged the price difference immediately.

### What if I don't have an available seat?

If you try to reassign a user to Premium but don't have any available Premium seats, you'll then be prompted to purchase an additional Premium seat.

## Using "unassigned" to swap users between seat types

1. Go to **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

2. Find User A and change their seat tier to "Unassigned." This frees up one Premium seat.

3. Find User B and change their seat tier to "Premium." They now occupy the available Premium seat.

4. Find User A and change their seat tier to "Standard."

**Note:** Unassigned users remain members of your organization but cannot use Claude until they're assigned to a seat.

## Seat assignment with JIT or SCIM provisioning

**[Users provisioned via JIT or SCIM](../21-Account-Support/setting-up-jit-or-scim-provisioning-to-manage-user-assignments-on-team-or-enterp.md)** are automatically assigned to the highest-available seat type when they're added. Admins and above can manually reassign seat types afterward in **[Organization](https://claude.ai/admin-settings/billing) [settings \> Organization](https://claude.ai/admin-settings/organization)**.

You can also enable group mappings with JIT or SCIM to provision users directly to a specific seat type.

------------------------------------------------------------------------

## Understanding billing

- **New seats** are prorated based on your billing cycle and charged immediately.

- **Seat type upgrades** (Standard → Premium) are prorated and charged immediately for the price difference.

For detailed billing calculations and examples, see **[How is my Team plan bill calculated?](how-is-my-team-plan-bill-calculated.md)**

---
## requesting-a-refund-for-a-paid-claude-plan-662fc76dd3.md

# Requesting a refund for a paid Claude plan

June 19, 2026

**Important:** Except as expressly provided in our **[Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms)** or where required by law, all payments are non-refundable.

To request a refund for a payment defined as refundable in our Terms of Service, follow these instructions:

1. Log in to your account and click on your initials or name in the lower left corner.

2. Select "Get help" from the menu to open a messenger on the right side of the window.

3. Click the "Send us a message" button.

4. Click "Accept," then "Claude Refund Request" from the available options.

5. Select your refund reason from the available options.

6. Follow the prompts to check your refund eligibility.

7. If eligible, continue in the support messenger to cancel and refund your plan.

------------------------------------------------------------------------

## Refunds for customers in the European Economic Area (EEA) and the United Kingdom (UK)

In the European Economic Area and the United Kingdom, you may receive a refund within 14 days of purchase. You may find this option available in your **Settings**. Your refunds will be prorated according to your use.

------------------------------------------------------------------------

## What should I do if I can't access the account I'm requesting a refund for?

If you're unable to log in to the account associated with your payment (for example, if you can't access the email account you used to sign up), you'll need to **[contact our Support team](https://support.claude.com/en/articles/9015913-how-to-get-support)** using another email and 'cc' the email address tied to the account you can't access. Write back to cancel your paid plan and request a refund so our team can assist.

## I paid for my plan on Claude for iOS—what's the process for requesting a refund?

If you paid for your plan on **[Claude for iOS](https://support.claude.com/en/collections/9879000-claude-for-ios)**, this means your subscription was started from the Apple App Store. We didn't process this payment, so you will need to reach out to **[Apple Support](https://support.apple.com/billing)** to request a refund.

## I paid for my plan on Claude for Android—what's the process for requesting a refund?

If you have an active subscription purchased on **[Claude for Android](https://support.claude.com/en/collections/9879004-claude-for-android)**, our Support team will need to check your eligibility before assisting with a refund. When contacting us, provide any relevant details upfront so our team can help with your request. However, if you are requesting a refund for an inactive subscription, our team won't be able to issue refunds for historical payments made through the Play Store. Please get in touch with **[Google Support](https://support.google.com/googleplay/workflow/9813244?hl=en)** for further assistance.

## How do I request a refund when I'm disputing the payment?

Our Support team cannot process refunds during pending disputes, as the disputed funds are pulled back immediately. You can choose to either continue working with your bank until the dispute is resolved, or to withdraw the bank dispute, which will allow us to process a refund.

---
## requesting-a-refund-for-a-paid-claude-plan.md

4. Requesting a refund for a paid Claude plan

# Requesting a refund for a paid Claude plan

**Important:** Except as expressly provided in our **[Consumer Terms of Service](https://www.anthropic.com/legal/consumer-terms)** or where required by law, all payments are non-refundable.

To request a refund for a payment defined as refundable in our Terms of Service, follow these instructions:

1. Log in to your account and click on your initials or name in the lower left corner.

2. Select "Get help" from the menu to open a messenger on the right side of the window.

3. Click the "Send us a message" button.

4. Click "Accept," then "Claude Refund Request" from the available options.

5. Select your refund reason from the available options.

6. Follow the prompts to check your refund eligibility.

7. If eligible, continue in the support messenger to cancel and refund your plan.

------------------------------------------------------------------------

## What should I do if I can't access the account I'm requesting a refund for?

## I paid for my plan on Claude for iOS -- what's the process for requesting a refund?

## I paid for my plan on Claude for Android -- what's the process for requesting a refund?

## How do I request a refund when I'm disputing the payment?

---
## set-up-role-based-entitlements-on-enterprise-plans-67c1b70136.md

# Set up role-based permissions on Enterprise plans

This guide walks you through setting up role-based permissions for your Enterprise organization. This lets you control which features and connectors specific teams or groups of members can access, and delegate specific admin access like billing or user management, rather than giving everyone the same permissions.

Before you start, make sure you're familiar with:

- **[Manage groups and group spend limits on Enterprise plans](https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans)** — how to create and manage groups

- **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)** — how custom roles and capabilities work

------------------------------------------------------------------------

## Before you begin

You'll need Owner or Primary Owner access to your Enterprise organization, or a custom role with Identity & Access set to Manage.

**Note:** Some of these steps require more than the Identity & Access custom role: enabling features at the organization level requires the Owner role, and changing member roles requires User Management set to Manage.

**Check which capabilities are enabled at the org level.** Go to **Organization settings** and ensure you know which capabilities members can access currently. For settings managed by RBAC, both the org setting and role setting are required to be on for users to get access.

**Back up your member list.** Export a CSV of your current members from **[Organization settings \> Members](http://claude.ai/admin-settings/members)** before making any changes. If something goes wrong during migration, this gives you a reference to restore access. See **[Manage members on Team and Enterprise plans](https://support.claude.com/en/articles/13133750-manage-members-on-team-and-enterprise-plans)**.

**Determine which teams or functions need each capability.** For example, Engineering gets Claude Code + Fast Mode and Marketing gets Cowork + Web Search. From here, define your custom roles.

**Dual-seat plans.** If your organization is on a dual-seat Enterprise plan (with Chat and Chat + Claude Code seats), custom roles don't override seat-level restrictions. A member assigned to a Chat-only seat can't access Claude Code even if their custom role grants it. The same applies in reverse: if a member's custom role doesn't grant the chat capability, they won't have chat access regardless of their seat type. Plan your role structure with seat assignments in mind.

**Note:** "Chat + Claude Code" refers to a seat type on legacy dual-seat plans. The "chat" capability in custom roles is separate—it governs chat access for any member whose role is set to "Custom" on any plan.

**Decide how you'll create groups.** You can create groups manually in Claude, or sync them from your identity provider (IdP) via SCIM. You can also use both methods simultaneously. If you plan to use IdP groups from Okta, Entra ID, or another provider, make sure SCIM directory sync is configured. See **[Set up JIT or SCIM provisioning](https://support.claude.com/en/articles/13133195-set-up-jit-or-scim-provisioning)**.

**Add the connectors you plan to govern.** Connector permissions only cover connectors that an Owner or Primary Owner has already added under **Organization settings \> Connectors** and connected with admin credentials. Review your organization-wide tool policy there as well, since role grants narrow within it and can’t widen past it. See **[Use connectors to extend Claude’s capabilities](https://support.claude.com/en/articles/11176164-)**.

------------------------------------------------------------------------

## Planning your role structure

Before creating anything, decide which features each team or group of members should have access to. Here are four common patterns:

### Base plus additive roles

This is the recommended approach for most organizations. Create a "Standard Access" role for everyone with common features like web search, memory, and projects. Then create additive roles that grant specific capabilities — for example, a "Cowork Enabled" role that only adds Cowork. Assign all members to the base role through an "All Users" group, and add specific members to additional groups that layer on extra features.

This pattern is flexible because permissions are additive — combining a base role with additive roles composes cleanly without conflicts.

### Tier-based roles

Create distinct tiers: "Full Access" with all features, "Standard Access" with most features, and "Restricted Access" with minimal features. Each member goes into exactly one group assigned to one tier.

### Department-based roles

Create roles that map to departments: "Engineering" with chat, Cowork, Claude Code, and code execution; "Research" with chat, web search, memory, and projects; "Business" with chat, web search and projects only. Assign each department group to its corresponding role.

### Admin delegation roles

Create roles that delegate parts of administration without granting the Owner role. A custom role with admin permissions does not need any user capabilities, and vice versa. You could create a "Finance" role that grants Billing access but no chat or Claude Code capability, or an "Engineering Lead" role that grants Claude Code plus Analytics view access. Learn more **[about admin permissions for custom roles](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans#h_536123d968)**.

------------------------------------------------------------------------

## Step 1: Audit your current settings

1. Review which features are currently enabled or disabled at the organization level in **[Organization settings \> Capabilities](http://claude.ai/admin-settings/capabilities)**.

2. Go to **[Organization settings \> Members](http://claude.ai/admin-settings/members)** to export or review your member list.

3. Note each member's current built-in role (User, Admin, or Owner).

4. For each team or department, decide which features they need access to.

Remember: any feature you want to control per-group must be **enabled** at the organization level. If a feature is toggled off at the organization level, no custom role can grant access to it.

**Important:** Unlike members with the User role, members assigned to custom roles don't automatically inherit organization-enabled capabilities. Every capability a "Custom" role member needs must be explicitly granted by a custom role assigned to one of their groups.

------------------------------------------------------------------------

## Step 2: Create custom roles

Create your custom roles before enabling any features or migrating members. This ensures your roles are ready to enforce access the moment features turn on.

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Click "Add role."

3. Name the role and toggle the appropriate capabilities on the **Capabilities** tab, or choose "All capabilities" or "All generally available" to grant everything at once:

4. On the **Permissions** tab, set admin permissions for the role. See **Step 3**.

5. On the **Connectors** tab, set connector permissions for the role. See **Step 4**.

6. On the **Models** tab, set model access and a default model for the role. See **Step 5**.

7. Click "Save role."

8. Repeat for each role in your plan.

Role changes may take up to 15 minutes to take effect. Members may need to refresh their browser to see updated access.

See **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)** for details on available capabilities, admin permissions, and connectors.

------------------------------------------------------------------------

## Step 3: Configure admin permissions (optional)

Set admin permissions on each role to delegate access to admin settings, like billing, user management, or privacy, without granting the Owner role. This step is optional. If you don't configure it, roles grant no admin access and administration stays with Owners and Primary Owners. For what each permission area covers, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)**.

### Locate the Permissions tab

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Open an existing role, or click “Add role” to create one.

3. Select the **Permissions** tab, between **Capabilities** and **Connectors**.

### **Set admin permissions**

The **Permissions** tab lists each admin area: Identity & Access, Billing, Analytics, Privacy, User Management, and Libraries. Set each admin area to one of the following options:

- **No access:** The member doesn't see this area in their organization settings.

- **Can manage:** Manage grants full read and write access to the area and includes view access.

Within an area, you grant all of View or all of Manage. You can't grant or restrict individual pages or settings.

**Note:** A role with Identity & Access set to Manage can create and edit groups and roles, including its own role definition. Members with this permission can expand their own access, so reserve it for trusted security and IT administrators.

### **Verify enforcement**

Verify admin permissions after you’ve migrated members to "Custom" roles (Step 7). See **Step 11: Verify and monitor**.

------------------------------------------------------------------------

## Step 4: Configure connector permissions (optional)

Set connector permissions on each role to control which connectors, and which tools on those connectors, the role can use. This step is optional. If you don’t configure it, your roles fall back to the default behavior described below. For how the permission model works end to end, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452-manage-custom-roles-on-enterprise-plans)**.

**Important:** When Anthropic enables connector permissions for your organization, every existing custom role is seeded with the “All connectors” grant at “Always allow.” Because “Always allow” is the most permissive grant, your organization-wide tool policy alone determines each member’s effective ceiling at enablement. Members neither gain nor lose access at enablement. Your first configuration pass narrows from that baseline.

**Note:** A newly created role defaults to “Needs approval” on every connector. The create-role flow steps through the Connectors tab so you see this default before saving. Raise a connector to “Always allow” or lower it to “Blocked” as needed.

### Locate the Connectors tab

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Open an existing role, or click “Add role” to create one.

3. Select the **Connectors** tab, next to **Permissions**.

The default settings for new roles are permissive. When creating or modifying a role, confirm the settings on each tab to avoid granting unintended permissions.

### Set connector-level permissions

The **Connectors** tab lists an **All connectors** row at the top, followed by every connector your organization has added. Each row has a dropdown with four options:

- **Always allow:** Every tool on the connector is available, and members can set their own approval to “Always allow.”

- **Needs approval:** Every tool is available, but members confirm each call.

- **Blocked:** The connector is hidden from members with this role.

- **Custom:** Set each tool on the connector individually. See “Set per-tool permissions” below.

Choosing “Always allow,” “Needs approval,” or “Blocked” applies that level to every tool on the connector. The **All connectors** row works the same way one level up: it sets a baseline for every connector at once, including any connector you add later. Use it to set a role’s default, then override individual connectors.

### Set per-tool permissions

Set a connector to **Custom** to reveal its tools as individual rows. Each tool has its own dropdown: “Always allow,” “Needs approval,” or “Blocked.”

Per-tool permissions let a role reach part of a connector. For example, with Jira set to **Custom**, its `search_issues` tool set to “Needs approval,” and every other Jira tool set to “Blocked,” members with the role can search Jira but nothing else. Claude only sees the tools you’ve granted, so asking it to create a ticket returns “I don’t have a tool for that” rather than an error.

### Review cross-role conflicts

Because connector permissions are additive across roles, blocking a connector in one role has no effect on a member who also holds another role that grants it. Each connector row shows a warning when other roles grant the same connector at a different level. The warning names those roles and links to them, and the most permissive grant is the one that applies.

If you have unsaved edits when you open a linked role, you’re asked to discard them first.

### Verify enforcement

Verify connector permissions after you’ve migrated members to "Custom" roles (Step 7). See **Step 11: Verify and monitor**.

**Important:** If your organization uses Claude Code, enabling connector permissions also applies your organization-wide tool policy to Claude Code. This can only narrow tool access there, never widen it, and it affects all members. Review your organization-wide tool policy before enablement if Claude Code is widely deployed. Connector permissions and Claude Code Managed Settings compose by most-restrictive. See **[Claude Code settings](https://code.claude.com/docs/en/settings#settings-files)**.

**Note:** Whether members can set "Always allow" on write-capable connector tools in Cowork is additionally controlled by the organization setting **Allow "Always allow" for connector tools**, which is off by default. Role grants can't override it. Learn more about the **[Cowork approval setting for write tools](https://support.claude.com/en/articles/13455879-use-claude-cowork-on-team-and-enterprise-plans#h_1bd1fa754d)**.

------------------------------------------------------------------------

## Step 5: Configure model access (optional)

Set model access on each role to control which Claude models the role can use, cap the maximum effort level per model, and choose the model new conversations start on. This step is optional; if you don't configure it, new roles can use every model that's enabled at the organization level, at any effort level, and start on the organization default model.

For how the model access and default model settings work end to end, see **[Manage model access for your organization](https://support.claude.com/en/articles/15694740)** and **[Set a default model for your organization](https://support.claude.com/en/articles/15330088)**.

### Locate the Models tab

1. Navigate to **[Organization settings \> Roles](https://claude.ai/admin-settings/roles)**.

2. Open an existing role, or click "Add role" to create one.

3. Select the **Models** tab, next to **Connectors**.

### Set model access

Under **Model access**, switch each model on or off for this role. Models disabled at the organization level appear but can't be enabled here until you turn them on for the organization in **[Organization settings \> Models](http://claude.ai/admin-settings/models)**. Haiku models are always on and can't be disabled.

To cap the effort level a role can select on a model, click the gear icon next to the model and choose a level.

Under **Default model**, optionally select the model new conversations start on for this role. Only models the role has access to can be selected.

### Verify enforcement

Verify model access after you've migrated members to "Custom" roles. See **Step 11: Verify and monitor**.

------------------------------------------------------------------------

## Step 6: Create groups and assign roles

1. Navigate to **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)**.

2. Click “Add group” to create a group for each team or tier in your plan.

3. Add members to the appropriate groups.

4. Assign each group to the custom roles you created in step 2.

If you use SCIM directory sync, you can sync groups from your identity provider instead of creating them manually. For details on SCIM group sync, see **[Manage groups and group spend limits on Enterprise plans](https://support.claude.com/en/articles/13799932-manage-groups-and-group-spend-limits-on-enterprise-plans)**.

**Multiple organizations under the same parent organization:** Groups are managed at the parent organization level and propagate to all child organizations. You may see members from other organizations listed in a group—this doesn't mean they have access to your organization. Custom roles assigned to a group only grant capabilities to members who are part of your specific organization.

If you request to move an organization from one parent to another (this is rare in practice), groups and roles will become undefined and you will need to re-create them.

**Important:** If your organization uses Invite only or JIT provisioning, you can only use manually created groups for RBAC. SCIM-synced groups aren't supported in these modes.

------------------------------------------------------------------------

## Step 7: Verify group and role assignments

Before migrating members to custom roles, confirm that every member you plan to migrate is in at least one group assigned to a custom role. Members who are migrated without group or role coverage will lose access to all governed features.

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Use the Role and Group filters to identify members who aren't assigned to any group.

3. Alternatively, click "Export CSV" to download the full member list with role and group columns for review.

4. Add any unassigned members to the appropriate groups before continuing.

------------------------------------------------------------------------

## Step 8: Migrate members to custom roles

For custom role capabilities to take effect, members must have their role set to "Custom." Members with the User, Admin, or Owner roles get their permissions from those roles directly, not from custom roles.

**Important:** Complete this step only after you’ve created your custom roles, configured admin and connector permissions if you’re using them, created your groups, and verified all members are assigned to groups. Members moved to custom roles before setup is complete will immediately lose access to all governed features and their previous role. Switching an Owner or Admin to custom roles removes their Owner or Admin access, so don't migrate Owners or Admins unless you intend to replace that access with custom role permissions.

Choose the migration path based on whether your organization already enabled group mappings:

### Path A: Enable group mappings (only if already in use)

Use this path only if your organization already enabled group mappings for role assignment. If you aren't already using this setting, skip to Path B.

1. Navigate to **[Organization settings \> Organization and access](https://claude.ai/admin-settings/organization)**.

2. In the role mappings section, assign the IdP groups you want governed by custom roles to the "Custom" role.

3. Save your changes. Members in those IdP groups are migrated to "Custom" roles on the next sync.

Members in IdP groups mapped to "Custom" roles follow the permissions of the custom roles assigned to their groups in Claude. Members in IdP groups mapped to User follow the organization-level capability settings. If a member is in groups across both mappings, "Custom" roles take precedence.

### Path B: Bulk assignment tool

Use this path if your organization hasn’t enabled group mappings.

**Warning:** If you didn’t already enable group mappings, do not enable it during RBAC setup. Enabling it without first assigning all members to mapped groups can result in members losing access to your organization.

1. Navigate to **[Organization settings \> Members](http://claude.ai/admin-settings/members)**.

2. Use the Role and Group filters to select the members you want to migrate.

3. Use the bulk assignment tool in the Members table to change the selected members' role to "Custom."

We recommend migrating a pilot group first—one team or department—and verifying their access is correct before expanding to the rest of the organization.

### Gradual rollout

Whichever path you use, we recommend migrating in stages:

1. Start with a pilot group of one team or department.

2. After migration, verify the pilot group has the correct feature access based on their group and role assignments.

3. If something isn't right, switch the affected members back to their previous role while you adjust.

4. Expand to more members once you've confirmed the setup works.

------------------------------------------------------------------------

## Step 9: Enable features at the organization level

Only enable organization-level features after roles, groups, and member migration are complete. This ensures custom role capabilities are already in place, with no window where unauthorized members could access a feature.

For any feature you want to control per-group:

1. Navigate to the feature's settings page in **Organization settings** (for example, **[Organization settings \> Cowork](http://claude.ai/admin-settings/cowork)**).

2. Enable the feature at the organization level.

Enabling a feature at the organization level doesn't mean everyone gets it—custom role permissions are already in place to control who can use it. Think of the organization-level toggle as making the feature "available for role-based assignment" rather than "on for everyone."

------------------------------------------------------------------------

## Step 10: Apply a group spend limit (usage-based orgs only)

Navigate to the “Usage” page to assign a per-user monthly spend limit to any group.

Note the following precedence rules:

- Individual limits always override group limits, regardless of which is higher.

- If a user belongs to multiple groups with different limits, the **Multi-group spend limit** setting under **Spending defaults** controls whether the higher or lower limit applies.

- Org-wide limits remain the hard ceiling.

Membership changes take effect automatically—users inherit or lose limits as soon as their group membership changes. Relevant only for usage-based billing orgs.

------------------------------------------------------------------------

## Step 11: Verify and monitor

1. **Spot-check access**: Open the "⋮" menu on a the right side of a member's row in **[Organization settings \> Members](https://claude.ai/admin-settings/members)** and select "View effective role." The modal shows every capability, admin permission, and connector the member has across all their roles, with a "Granted by" label naming which role provides each one. You can do the same for a group from **[Organization settings \> Groups](https://claude.ai/admin-settings/groups)**. For details, see **[Manage custom roles on Enterprise plans](https://support.claude.com/en/articles/13930452)**.

2. **Test the restricted state**: Log in as (or ask) a member who should not have a feature like Cowork. They should see it greyed out with the message "Contact your admin to request access to this feature."

3. **Test the granted state**: Confirm a member who should have the feature sees it working normally.

4. **Check edge cases**: Test members in multiple groups, members with no group, and new members joining via SSO.

**If you configured admin permissions, also check:**

- **Group and role assignments:** Owners can verify a member's access by checking their group assignments on the Members page and the roles those groups are assigned to on the Roles page.

- **Organization settings:** In organization settings, the member only sees the sections their admin permissions cover. Everything else is hidden from their settings. Members with view access see pages as read-only, with controls disabled.

- **Analytics access:** Members with Analytics access will view analytics in **[Settings \> Analytics](https://claude.ai/analytics/activity)**, not organization settings.

**If you configured connector permissions, also check:**

- **Connector menu:** blocked connectors don’t appear, and connectors with at least one granted tool do.

- **Connector settings:** blocked tools are grayed out with “This tool is not enabled for your role. Contact your administrator.” Tools capped at “Needs approval” show a personal approval menu limited to “Ask” and “Never.”

- **In a conversation:** ask Claude to use a blocked tool, and it reports it has no tool for the task. Ask it to use a “Needs approval” tool, and the approval prompt appears without an “Always allow” option.

**If you configured model access, also check:**

- **Model picker:** disabled models don't appear, and the effort menu stops at the role's cap.

- **In a conversation:** ask the member to switch to a disabled model. It shouldn't be listed, and in Claude Code CLI, /model \<disabled-model\> returns an error.

Role changes may take up to 15 minutes to take effect across the platform. Members may need to refresh their browser to see updated access.

------------------------------------------------------------------------

## Using SCIM with role-based capabilities

SCIM connects to your role-based capabilities through two mechanisms that work together.

### IdP group-to-role mapping

This controls which built-in role a member gets when they're provisioned. Map your IdP groups to "Custom" roles so that new members' access is automatically governed by custom role capabilities.

1. Navigate to **[Organization settings \> Organization and access](http://claude.ai/admin-settings/organization)**.

2. In the role mappings table, map your IdP groups to "Custom" roles.

### Group sync

This pulls your IdP groups into Claude so they can be assigned to custom roles.

1. Navigate to **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)**

2. Click “Check for updates” in the **SCIM sync** section.

3. When prompted to sync Groups, Members, or Both, select Groups only. Syncing Members can affect provisioning and member access.

4. Your IdP groups appear as SCIM-sourced groups in the list.

5. Assign SCIM groups to custom roles just like manually created groups.

6. In your IdP, only push the groups you actually intend to use for RBAC or spend limits. Syncing all IdP groups can slow page loads in the Groups section.

**Note:** Custom role permissions only apply to members with "Custom" roles selected in **[Organization settings \> Members](https://claude.ai/admin-settings/members)**. If you map an IdP group to a different role (like User) through the group-to-role mapping but assign that same SCIM group to a custom role, the custom role's permissions have no effect—the member gets their permissions from their assigned role instead. To use custom roles, make sure the IdP group is mapped to "Custom."

### Ongoing management with SCIM

- To grant a member access to a feature, add them to the appropriate IdP group. On the next sync, they pick up the custom role assigned to that group.

- To revoke access, remove them from the IdP group. On the next sync, the permission is removed.

- Click “SCIM sync” in the Groups section to force an immediate sync rather than waiting for the next scheduled sync.

------------------------------------------------------------------------

## Rollback plan

If you notice your role structure is misconfigured after migration:

1. Turn off any organization-level features that were enabled as part of the migration.

2. Change affected members back to their previous built-in role (for example, User).

3. They immediately regain the static permissions from that role, and custom role permissions stop applying.

4. Adjust roles and groups as needed, then re-migrate.

If you enabled group mappings during setup and lost admin access, follow the recovery steps in **[Set up JIT or SCIM provisioning](https://support.claude.com/en/articles/13133195-set-up-jit-or-scim-provisioning#h_74979446b3)** under "I lost Admin/Owner access after enabling group mappings."

------------------------------------------------------------------------

## Frequently asked questions

### Do I need to enable a feature at the organization level if I only want some members to have it?

Yes. The organization-level toggle must be on for custom roles to control per-member access. If a feature is off at the organization level, no one can access it regardless of their role. Think of it as a main switch—custom roles control who gets access underneath it.

### What happens if a member whose role is set to "Custom" isn't in any groups?

They have no custom role permissions, so all features that require permissions are greyed out or hidden. Make sure every member whose roles is set to "Custom" is in at least one group that's assigned to a custom role.

### A model is missing from a member's model picker.

Either the model is disabled at the organization level (**[Organization settings \> Models](http://claude.ai/admin-settings/models)**) or none of the member's custom roles grant it. Org-level disables affect everyone, including Owners and Admins.

### What if a custom role doesn't grant chat access?

Members in that role won't see Claude's chat interface. They'll land on their settings page when they sign in. If their role grants other products like Cowork or Claude Code, those remain accessible from their settings page and from the relevant apps.

Chat is enabled by default in all custom roles, so you only need to worry about this if you intentionally toggled chat off for a role.

### Can I use both built-in and custom roles?

Yes. Members with the User, Admin, or Owner roles are unaffected by custom role permissions because they get their permissions from those roles directly. Only members with a role set to "Custom" are controlled by the group-and-role system. This allows gradual migration.

### What if a member is in two groups with different roles?

Permissions are additive. If any role in a member's chain grants a feature, they have it. You can't use a role to remove a permission granted by another role.

### Can I use SCIM groups and manual groups together?

Yes. Both types can be assigned to custom roles. The difference is that SCIM group membership is managed in your identity provider, while manual group membership is managed in Claude's organization settings.

### Are Owners and Primary Owners affected by custom role permissions?

No. Owners and Primary Owners always have full access to all features.

### How does this work across parent and child organizations?

Groups and SCIM sync are managed at the parent organization level and shared across all child organizations. Role and spend limit assignments are configured independently in each child organization—changes in one child organization don't affect others. Group membership changes and SCIM resyncs propagate across all child organizations under the same parent.

### What happens to my existing custom roles when connector permissions are enabled?

Each existing role is seeded with the “All connectors” grant at “Always allow,” so members’ access doesn’t change at enablement. You narrow access from there.

### What’s the default connector permission on a new role?

“Needs approval” on every connector. The create-role flow steps through the Connectors tab so you see this before saving.

### What happens when I add a new connector after my roles exist?

A role whose “All connectors” row is set to “Always allow,” “Needs approval,” or “Blocked” covers the new connector at that level automatically. A role whose “All connectors” row is set to “Custom” treats the new connector as “Blocked” until you set it.

### I blocked a connector in a role, but a member with that role can still use it. Why?

Check whether the member holds another role that grants it, since the most permissive grant wins across roles. The conflict warning on the connector row lists those roles. Also confirm the member’s role is set to "Custom."

### My organization-wide tool policy already blocks a tool. Do I need to block it in every role?

No. The organization-wide policy is the ceiling. A tool blocked there is blocked for everyone, regardless of role grants.

### A member's role and the organization-wide policy are both set to "Always allow," but "Allow for all tasks" is grayed out in Cowork. Why?

Cowork has a separate organization setting, **Allow "Always allow" for connector tools**, that gates write-capable connector tools. It's off by default. Until it's turned on, "Allow for all tasks" stays grayed out regardless of role grants and tool policies, and previously saved always-allow preferences aren't honored. Read-only tools are exempt only when the connector annotates them as read-only, which most custom connectors don't. For more information, see **[Connector tool approvals](https://support.claude.com/en/articles/13455879-use-claude-cowork-on-team-and-enterprise-plans#h_1bd1fa754d).**

### Can a role grant a tool that the organization-wide policy sets to “Needs approval”?

The role can grant it, but the stricter setting wins, so members see it capped at “Needs approval.” To let members set “Always allow,” raise the organization-wide policy to “Always allow” first.

### Can I grant one tool on a connector without granting the whole connector?

Yes. Set the connector to “Custom,” set the one tool to “Always allow” or “Needs approval,” and leave the rest “Blocked.”

### Do connector permissions apply to built-in tools like web search or code execution?

No. Built-in features are governed on the Capabilities tab. The Connectors tab governs connectors your organization has added.

### How quickly do connector permission changes take effect?

Role changes may take up to 15 minutes to take effect. Members may need to refresh their browser.

### Can someone in a custom role with permissions give themselves more access?

Only if their role includes Identity & Access set to Manage, which covers editing roles and groups. Reserve that permission for trusted security and IT administrators, since it can be used to change role definitions including their own.

### Can I give admin permissions to a member on the User, Admin, Owner, or Primary Owner role?

No. Admin permissions only apply to members in a custom role. Members on a built-in role keep the access that role grants. To give someone specific admin permissions, change the member to a custom role and add them to a group assigned to a role with the permissions they need. Keep in mind this removes their previous built-in role access.

### What does someone see when they don’t have permissions for a certain setting?

Organization settings only shows the sections their permissions cover. Sections they don’t have access to are hidden entirely from their organization settings.

### How do I audit who has admin access?

**[Organization settings \> Roles](https://Organization%20settings%20%3E%20Roles)** shows the admin permissions each custom role grants, and **[Organization settings \> Groups](http://claude.ai/admin-settings/groups)** shows which groups are assigned to each role and who belongs to them. To check a specific member, look up their groups on **[Organization settings \> Members](http://claude.ai/admin-settings/members)**, then the roles those groups are assigned to.

### What if someone needs permissions across multiple areas?

Create one role that grants access to multiple areas, or add the member to multiple groups whose roles cover the areas they need. Permissions combine additively.

---
## set-up-role-based-permissions-on-enterprise-plans-99a481d71b.md