api-20260925T153714Z / page 12 of 13 / documentation capture

api/files/upload Changed · +2 / -2 lines

from line 57

5757

5858 Original filename of the uploaded file.

5959

60 maxLength: 500, minLength: 1

60 minLength: 1, maxLength: 500

6161

6262 - `mime_type: string`

6363

6464 MIME type of the file.

6565

66 maxLength: 255, minLength: 1

66 minLength: 1, maxLength: 255

6767

6868 - `size_bytes: number`

6969

api/messages/batches/list Changed · +1 / -1 lines

from line 27

2727

2828 Defaults to `20`. Ranges from `1` to `1000`.

2929

30 default: 20, maximum: 1000, minimum: 1

30 default: 20, minimum: 1, maximum: 1000

3131

3232## Headers

3333

api/overview Changed · +1 / -1 lines

from line 25

2525

2626* **[Messages API](https://platform.claude.com/docs/en/api/messages/create)**: Send messages to Claude for conversational interactions (`POST /v1/messages`)

2727* **[Message Batches API](https://platform.claude.com/docs/en/api/messages/batches/create)**: Process large volumes of Messages requests asynchronously with 50% cost reduction (`POST /v1/messages/batches`)

28* **[Token Counting API](https://platform.claude.com/docs/en/api/messages-count-tokens)**: Count tokens in a message before sending to manage costs and rate limits (`POST /v1/messages/count_tokens`)

28* **[Token Counting API](https://platform.claude.com/docs/en/api/messages/count_tokens)**: Count tokens in a message before sending to manage costs and rate limits (`POST /v1/messages/count_tokens`)

2929* **[Models API](https://platform.claude.com/docs/en/api/models/list)**: List available Claude models and their details (`GET /v1/models`)

3030* **[Files API](https://platform.claude.com/docs/en/api/files/upload)**: Upload and manage files for use across multiple API calls (`POST /v1/files`, `GET /v1/files`)

3131* **[Skills API](https://platform.claude.com/docs/en/api/skills/create)**: Create and manage custom agent skills (`POST /v1/skills`, `GET /v1/skills`)

build-with-claude/overview Changed · +1 / -1 lines

from line 84

8484| ------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------- | ----------------------------------------------------------------------------- |

8585| [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) | Extend Claude's capabilities with Skills. Use pre-built Skills (PowerPoint, Excel, Word, PDF) or create custom Skills with instructions and scripts. Skills use progressive disclosure to efficiently manage context. | Not ZDR eligible | <PlatformAvailability claudeApi claudePlatformAwsBeta azureAiBeta />†‡ |

8686| [Fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) | Stream tool use parameters without buffering/JSON validation, reducing latency for receiving large parameters. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

87| [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) | Connect to remote [MCP](https://platform.claude.com/docs/en/mcp) servers directly from the Messages API without a separate MCP client. | Not ZDR eligible | <PlatformAvailability claudeApiBeta claudePlatformAwsBeta azureAiBeta /> |

87| [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) | Connect to remote [MCP](https://modelcontextprotocol.io/) servers directly from the Messages API without a separate MCP client. | Not ZDR eligible | <PlatformAvailability claudeApiBeta claudePlatformAwsBeta azureAiBeta /> |

8888| [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) | Enable Claude to call your tools programmatically from within code execution containers, reducing latency and token consumption for multi-tool workflows. | Not ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws azureAi />† |

8989| [Tool search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) | Scale to thousands of tools by dynamically discovering and loading tools on-demand using regex- and BM25-based search, optimizing context usage and improving tool selection accuracy. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

9090

build-with-claude/prompt-engineering/prompting-claude-fable-5 Changed · +1 / -1 lines

from line 172

172172* **Start at the top of your difficulty range.** Pick a task harder than what you'd assign to prior models, and have Claude Fable 5 scope it, ask clarifying questions, and execute.

173173* **Make self-verification explicit in long-run prompts.** Separate, fresh-context verifier subagents tend to outperform self-critique. For long-running tasks, instruct: `Establish a method for checking your own work at an interval of [X] as you build. Run this every [X interval], verifying your work with subagents against the specification.`

174174* **Refactor existing prompts and skills.** Skills developed for prior models are often too prescriptive for Claude Fable 5 and can degrade output quality. Review and consider removing older instructions if default performance is better. Claude Fable 5 also does a good job of updating skills on the fly based on what it learns from the task at hand.

175* **Don't instruct Claude to reproduce its reasoning in the response.** Prompts, skills, or harness instructions that tell the model to echo, transcribe, or explain its internal reasoning as response text can trigger the [`reasoning_extraction` refusal category](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) on Claude Fable 5, causing elevated fallbacks to Claude Opus 4.8. Audit existing skills and system prompts for reflection or show-your-thinking instructions when migrating. If your application needs reasoning visibility, read the structured `thinking` blocks from [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) instead, and use a [send-to-user tool](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5#create-a-send-to-user-tool) to surface progress during long runs.

175* **Don't instruct Claude to reproduce its reasoning in the response.** Prompts, skills, or harness instructions that tell the model to echo, transcribe, or explain its internal reasoning as response text can trigger the [`reasoning_extraction` refusal category](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) on Claude Fable 5. Server-side fallback with `fallbacks: "default"` doesn't retry requests declined with `reasoning_extraction`; that refusal is returned to you. Audit existing skills and system prompts for reflection or show-your-thinking instructions when migrating. If your application needs reasoning visibility, read the structured `thinking` blocks from [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) instead, and use a [send-to-user tool](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5#create-a-send-to-user-tool) to surface progress during long runs.

176176* **Create a send-to-user tool.** For long, asynchronous agents, a client-side tool delivers messages to the user verbatim without ending the turn. See [Create a send-to-user tool](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5#create-a-send-to-user-tool).

177177

build-with-claude/skills-guide Changed · +2 / -2 lines

from line 2175

21752175 -F "files[]=@financial_skill/analyze.py;filename=financial_skill/analyze.py"

21762176 ```

21772177

2178 <MultiFileExample language="cli" label="CLI">

2178 <CodeGroupItem>

21792179 ```bash CLI

21802180 ant apply financial_skill

21812181 ```

from line 2194

21942194 print("financial analysis helper")

21952195 ```

21962196 </File>

2197 </MultiFileExample>

2197 </CodeGroupItem>

21982198

21992199 ```python Python

22002200 from anthropic.lib import files_from_dir

build-with-claude/token-counting Changed · +2 / -2 lines

from line 25

2525

2626## How to count message tokens

2727

28The [token counting](https://platform.claude.com/docs/en/api/messages-count-tokens) endpoint accepts the same structured list of inputs for creating a message, including support for system prompts, [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), [images](https://platform.claude.com/docs/en/build-with-claude/vision), and [PDFs](https://platform.claude.com/docs/en/build-with-claude/pdf-support). The response contains the total number of input tokens.

28The [token counting](https://platform.claude.com/docs/en/api/messages/count_tokens) endpoint accepts the same structured list of inputs for creating a message, including support for system prompts, [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), [images](https://platform.claude.com/docs/en/build-with-claude/vision), and [PDFs](https://platform.claude.com/docs/en/build-with-claude/pdf-support). The response contains the total number of input tokens.

2929

3030This endpoint returns an `invalid_request_error` for a few inputs that the Messages API accepts: [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) such as web search, web fetch, code execution, and tool search (every server tool except the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool)), the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector), and `image` or `document` blocks with a `url` or `file` source. Send images and PDFs as base64 to count them. For requests that use server tools or MCP servers, the Messages API response reports the tokens used in its `usage` object.

3131

from line 1436

14361436## Next steps

14371437

14381438<CardGroup cols={2}>

1439 <Card title="Count message tokens" icon="code" href="https://platform.claude.com/docs/en/api/messages-count-tokens">

1439 <Card title="Count message tokens" icon="code" href="https://platform.claude.com/docs/en/api/messages/count_tokens">

14401440 Read the full API reference for the token counting endpoint.

14411441 </Card>

14421442

cli-sdks-libraries/sdks/python Changed · +2 / -1 lines

from line 218

218218

219219```python

220220count = client.messages.count_tokens(

221 model="claude-opus-5-5", messages=[{"role": "user", "content": "Hello, world"}]

221 model="claude-opus-5-5",

222 messages=[{"role": "user", "content": "Hello, world"}],

222223)

223224print(count.input_tokens) # 10

224225```

get-api-key Changed · +1 / -1 lines

from line 48

4848

4949## API keys and the Admin API

5050

51The [Admin API](https://platform.claude.com/docs/en/api/admin) includes endpoints for managing your organization's API keys programmatically, such as [Retrieve API Key](https://platform.claude.com/docs/en/api/admin/api_keys/retrieve) and [List API Keys](https://platform.claude.com/docs/en/api/admin/api_keys/list). These endpoints are for organization admins automating key management. They accept an [Admin API key](https://platform.claude.com/docs/en/manage-claude/admin-api-keys), an OAuth token with the `org:admin` scope, or a personal or service account key that isn't scoped to a specific workspace; workspace keys don't work there. They never return a key's secret value, only a partially redacted hint.

51The [Admin API](https://platform.claude.com/docs/en/api/beta/organization) includes endpoints for managing your organization's API keys programmatically, such as [Retrieve API Key](https://platform.claude.com/docs/en/api/beta/organization/api_keys/retrieve) and [List API Keys](https://platform.claude.com/docs/en/api/beta/organization/api_keys/list). These endpoints are for organization admins automating key management. They accept an [Admin API key](https://platform.claude.com/docs/en/manage-claude/admin-api-keys), an OAuth token with the `org:admin` scope, or a personal or service account key that isn't scoped to a specific workspace; workspace keys don't work there. They never return a key's secret value, only a partially redacted hint.

5252

5353<Note>

5454 The Admin API can't recover a lost key or give you a key to call the Claude API with. To get a usable API key, create one in [Settings → API keys](https://platform.claude.com/settings/keys) in the Claude Console.

manage-claude/claude-code-analytics-api Changed · +2 / -2 lines

from line 65

6565* **Cursor-based pagination:** Handle large datasets with stable pagination using opaque cursors

6666* **Data freshness:** Metrics are available with up to 1-hour delay for consistency

6767

68For complete parameter details and response schemas, see the [Claude Code Analytics API reference](https://platform.claude.com/docs/en/api/admin/usage_report/retrieve_claude_code).

68For complete parameter details and response schemas, see the [Claude Code Analytics API reference](https://platform.claude.com/docs/en/api/beta/organization/usage_report/retrieve_claude_code).

6969

7070### Basic examples

7171

from line 271

271271The Claude Code Analytics API helps you understand and optimize your team's development workflow. Learn more about related features:

272272

273273* [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api)

274* [Admin API reference](https://platform.claude.com/docs/en/api/admin)

274* [Admin API reference](https://platform.claude.com/docs/en/api/beta/organization)

275275* [Claude Code Analytics dashboard](https://platform.claude.com/claude-code)

276276* [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api) - Track API usage across all Anthropic services

277277* [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) - Retrieve audit and activity data

manage-claude/cmek-azure-key-vault Changed · +1 / -1 lines

from line 76

7676 The `--tags` option adds the organization tag, `anthropic-org-<ORGANIZATION_UUID>` with the value `true`, where `<ORGANIZATION_UUID>` is your Anthropic organization ID in lowercase. The tag is required for Anthropic to validate the key.

7777

7878 <Note>

79 **Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization** in claude.ai, or read the `id` field from the [Organization Info](https://platform.claude.com/docs/en/api/admin-api/organization/get-me) endpoint. Use the bare UUID, not the `org_`-prefixed ID.

79 **Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization** in claude.ai, or read the `id` field from the [Organization Info](https://platform.claude.com/docs/en/api/beta/organization/retrieve) endpoint. Use the bare UUID, not the `org_`-prefixed ID.

8080 </Note>

8181

8282 ```bash

manage-claude/cmek-google-cloud-kms Changed · +1 / -1 lines

from line 58

5858 The `--labels` option adds the organization label, `anthropic-org-<ORGANIZATION_UUID>` with the value `true`, where `<ORGANIZATION_UUID>` is your Anthropic organization ID in lowercase. The label is required for Anthropic to validate the key.

5959

6060 <Note>

61 **Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization** in claude.ai, or read the `id` field from the [Organization Info](https://platform.claude.com/docs/en/api/admin-api/organization/get-me) endpoint. Use the bare UUID, not the `org_`-prefixed ID.

61 **Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization** in claude.ai, or read the `id` field from the [Organization Info](https://platform.claude.com/docs/en/api/beta/organization/retrieve) endpoint. Use the bare UUID, not the `org_`-prefixed ID.

6262 </Note>

6363

6464 ```bash

manage-claude/compliance-errors Changed · +1 / -1 lines

from line 315

315315

316316**Cause:** The project document ID does not exist or has been deleted. The document content and metadata endpoints return the first body; `DELETE /v1/compliance/apps/projects/documents/{document_id}` returns the second. This error applies to text project documents (`claude_proj_doc_...`), not to project files.

317317

318**Fix:** Use `GET /v1/compliance/apps/projects/{project_id}/attachments` to list current attachments. If the document is missing, it was deleted; retrieve it through a `claude_project_document_uploaded` activity record if you only need the metadata.

318**Fix:** Use `GET /v1/compliance/apps/projects/{project_id}/attachments` to list current attachments. If the document is missing, it was deleted; retrieve it through a `claude_project_document_uploaded` activity record if you only need the metadata. The activity record shows who uploaded the document, when, and to which project, but not its name.

319319

320320### Local session not found

321321

manage-claude/compliance-faq Changed · +1 / -1 lines

from line 74

7474

7575 Local sessions are captured as their requests reach the Claude API, so nothing is installed on the device, and on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and [Claude Code cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web), which run on cloud infrastructure instead of the user's machine, are not captured. These cloud sessions are not remote sessions, even though both run in the cloud; the remote session endpoints return Cowork sessions only. Organizations with [HIPAA readiness](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness) enabled get no local session data, and sessions for which [zero data retention (ZDR)](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) is in effect are excluded.

7676

77 The local and remote session endpoints are stable for Cowork and Claude Code sessions; coverage of Claude Science, Claude for Microsoft 365, and Claude in Chrome sessions is in beta.

77 The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Microsoft 365 sessions; coverage of Claude Science and Claude in Chrome sessions is in beta.

7878 </Accordion>

7979

8080 <Accordion title="What do session transcripts include?">

manage-claude/compliance-sessions Changed · +1 / -1 lines

from line 5

55---

66

77<Note>

8 The endpoints on this page are available only to Claude Enterprise organizations. The local and remote session endpoints are stable for Cowork and Claude Code sessions; coverage of Claude Science, Claude for Microsoft 365, and Claude in Chrome sessions is in beta. The endpoints work with the same Compliance Access Key and `read:compliance_user_data` scope as the [chat, file, and project endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-content-data); no new key, scope, setting, or client update is required. See [Set up the Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api-access).

8 The endpoints on this page are available only to Claude Enterprise organizations. The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Microsoft 365 sessions; coverage of Claude Science and Claude in Chrome sessions is in beta. The endpoints work with the same Compliance Access Key and `read:compliance_user_data` scope as the [chat, file, and project endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-content-data); no new key, scope, setting, or client update is required. See [Set up the Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api-access).

99</Note>

1010

1111<Check>

manage-claude/workload-identity-federation Changed · +2 / -2 lines

from line 79

7979 </Step>

8080</Steps>

8181

82To manage these resources programmatically, see [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api) for the curl walkthrough, or see the [Service accounts API reference](https://platform.claude.com/docs/en/api/admin/service_accounts), [Federation issuers API reference](https://platform.claude.com/docs/en/api/admin/federation_issuers), and [Federation rules API reference](https://platform.claude.com/docs/en/api/admin/federation_rules) for complete parameter details and response schemas.

82To manage these resources programmatically, see [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api) for the curl walkthrough, or see the [Service accounts API reference](https://platform.claude.com/docs/en/api/beta/organization/service_accounts), [Federation issuers API reference](https://platform.claude.com/docs/en/api/beta/organization/federation/issuers), and [Federation rules API reference](https://platform.claude.com/docs/en/api/beta/organization/federation/rules) for complete parameter details and response schemas.

8383

8484## Authenticate from your workload

8585

from line 402

402402* [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api): create issuers, service accounts, and rules from infrastructure as code

403403* [WIF reference](https://platform.claude.com/docs/en/manage-claude/wif-reference): environment variables, profile file schema, validation rules, and error codes

404404* [Authentication](https://platform.claude.com/docs/en/manage-claude/authentication): all authentication options across the Anthropic SDKs

405* [Admin API reference](https://platform.claude.com/docs/en/api/admin): generated request and response schemas for every Admin API endpoint

405* [Admin API reference](https://platform.claude.com/docs/en/api/beta/organization): generated request and response schemas for every Admin API endpoint

406406

managed-agents/github Changed · +2 / -2 lines

from line 49

4949 )

5050 ```

5151

52 <MultiFileExample language="cli" label="CLI">

52 <CodeGroupItem>

5353 ```bash CLI

5454 ant apply code-reviewer.md

5555 ```

from line 72

7272 You are a code review assistant with access to GitHub.

7373 ```

7474 </File>

75 </MultiFileExample>

75 </CodeGroupItem>

7676

7777 ```python Python

7878 agent = client.beta.agents.create(

managed-agents/mcp-connector Changed · +2 / -2 lines

from line 53

5353 agent_id=$(jq -r '.id' <<<"$agent_response")

5454 ```

5555

56 <MultiFileExample language="cli" label="CLI">

56 <CodeGroupItem>

5757 ```bash CLI

5858 ant apply github-assistant.md

5959 ```

from line 74

7474 ---

7575 ```

7676 </File>

77 </MultiFileExample>

77 </CodeGroupItem>

7878

7979 ```python Python

8080 agent = client.beta.agents.create(

managed-agents/memory Changed · +2 / -2 lines

from line 37

3737 -d '{"name": "User Preferences", "description": "Per-user preferences and project context."}'

3838 ```

3939

40 <MultiFileExample language="cli" label="CLI">

40 <CodeGroupItem>

4141 ```bash CLI

4242 ant apply memory_store.yaml

4343 ```

from line 49

4949 description: Per-user preferences and project context.

5050 ```

5151 </File>

52 </MultiFileExample>

52 </CodeGroupItem>

5353

5454 ```python Python

5555 store = client.beta.memory_stores.create(

managed-agents/self-hosted-sandboxes Changed · +2 / -2 lines

from line 89

8989 }'

9090 ```

9191

92 <MultiFileExample language="cli" label="CLI">

92 <CodeGroupItem>

9393 ```bash CLI

9494 ant apply environment.yaml

9595 ```

from line 102

102102 type: self_hosted

103103 ```

104104 </File>

105 </MultiFileExample>

105 </CodeGroupItem>

106106

107107 ```python Python

108108 client = anthropic.Anthropic()

managed-agents/vaults Changed · +2 / -2 lines

from line 37

3737 EOF

3838 ```

3939

40 <MultiFileExample language="cli" label="CLI">

40 <CodeGroupItem>

4141 ```bash CLI

4242 ant beta:vaults create < alice.vault.yaml

4343 ```

from line 49

4949 external_user_id: usr_abc123

5050 ```

5151 </File>

52 </MultiFileExample>

52 </CodeGroupItem>

5353

5454 ```python Python

5555 vault = client.beta.vaults.create(

models/fable-5-1/whats-new-fable-5-1 Changed · +1 / -1 lines

from line 403

403403

404404* **Refusals:** a declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area that fired.

405405* **Fallback:** retry a refused request on another model with [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback), or your own retry. `fallbacks: "default"` (beta) retries a declined request on the model Anthropic recommends for that category. The permitted fallback targets for Claude Fable 5.1 are Claude Opus 4.8 and Claude Opus 5.

406* **Billing:** you aren't billed for a refusal that arrives before any output, and, for Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching models.

406* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale ([How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed)). Before September 24, 2026, these refusals weren't billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching models.

407407

408408## Pricing

409409

models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 Changed · +1 / -1 lines

from line 48

4848

4949### Billing

5050

51You are not billed for a request that is refused before any output is generated. When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching, so you avoid paying that cost twice.

51A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale. Before September 24, 2026, these refusals were not billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For the billed categories, see [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed). When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching, so you avoid paying that cost twice.

5252

5353## Availability

5454

models/fable-5/migration-guide Changed · +1 / -1 lines

from line 680

680680

6816815. **Safety classifiers and the `refusal` stop reason (Claude Fable 5 only):** `claude-fable-5` runs safety classifiers on requests and during response generation. Claude Mythos 5 does not include these classifiers. When a classifier declines a request, the Messages API returns `stop_reason: "refusal"` as a successful HTTP 200 response, not an error. The `stop_details.category` field reports which classifier fired, with categories such as `"cyber"`, `"bio"`, and `"reasoning_extraction"`, or `null` when the refusal maps to no named category. See the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the full set.

682682

683 You are not billed for the input tokens of a request refused before any output is generated. When a classifier fires mid-stream, the input and already-streamed output are billed; discard the partial output.

683 A refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category, or with a `null` category, is not billed ([How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed)). Before September 24, 2026, no refusal before any output was billed on Claude Fable 5. When a classifier fires mid-stream, the input and already-streamed output are billed; discard the partial output.

684684

685685 To re-run refused requests on another model automatically, pass the opt-in `fallbacks` parameter, which is in beta on the Claude API. The parameter is not available on the Message Batches API or on Amazon Bedrock, Google Cloud, and Microsoft Foundry; on those three platforms, run the retry client-side or use the SDK refusal-fallback middleware. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

686686

models/fable-5/overview Changed · +1 / -1 lines

from line 108

108108## Reference

109109

110110<CardGroup cols={3}>

111 <Card title="System prompt" icon="text" href="https://platform.claude.com/docs/en/release-notes/system-prompts#claude-fable-5">

111 <Card title="System prompt" icon="text" href="https://platform.claude.com/docs/en/release-notes/system-prompts/overview#claude-fable-5">

112112 The system prompt Claude Fable 5 uses on claude.ai and the Claude apps.

113113 </Card>

114114

One read of Claude Developer Platformapi-20260925T153714Z

What this read moved

api/files/upload Changed · +2 / -2 lines

api/messages/batches/list Changed · +1 / -1 lines

api/overview Changed · +1 / -1 lines

build-with-claude/overview Changed · +1 / -1 lines

build-with-claude/prompt-engineering/prompting-claude-fable-5 Changed · +1 / -1 lines

build-with-claude/skills-guide Changed · +2 / -2 lines

build-with-claude/token-counting Changed · +2 / -2 lines

cli-sdks-libraries/sdks/python Changed · +2 / -1 lines

get-api-key Changed · +1 / -1 lines

manage-claude/claude-code-analytics-api Changed · +2 / -2 lines

manage-claude/cmek-azure-key-vault Changed · +1 / -1 lines

manage-claude/cmek-google-cloud-kms Changed · +1 / -1 lines

manage-claude/compliance-errors Changed · +1 / -1 lines

manage-claude/compliance-faq Changed · +1 / -1 lines

manage-claude/compliance-sessions Changed · +1 / -1 lines

manage-claude/workload-identity-federation Changed · +2 / -2 lines

managed-agents/github Changed · +2 / -2 lines

managed-agents/mcp-connector Changed · +2 / -2 lines

managed-agents/memory Changed · +2 / -2 lines

managed-agents/self-hosted-sandboxes Changed · +2 / -2 lines

managed-agents/vaults Changed · +2 / -2 lines

models/fable-5-1/whats-new-fable-5-1 Changed · +1 / -1 lines

models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 Changed · +1 / -1 lines

models/fable-5/migration-guide Changed · +1 / -1 lines

models/fable-5/overview Changed · +1 / -1 lines