One read of Claude Developer Platformapi-20261022T213726Z

This capture is too large to show at once. Changes 76-100 of 115 are below, significant first; the rest are on the following screens.

api/beta/organization/plugins/retrieve Changed · +2 / -2 lines

from line 185

185185 

186186 - `assessment: "fail" or "pass" or "unknown" or "warn" or null`

187187 

188 The scan's verdict; set only when `status` is `completed`.

188 The scan's verdict; set only when `status` is `completed`. A `warn` can mean a `fail` that was allowed in claude.ai.

189189 

190190 - `"fail"`

191191 

from line 201

201201 

202202 - `status: "completed" or "errored" or "processing"`

203203 

204 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read.

204 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run. Once a scan of the version has completed, `content_scan` describes the newest completed scan, even while a later scan runs. While the scan outcome cannot be read, `status` is `errored` instead.

205205 

206206 - `"completed"`

207207 

api/beta/organization/plugins/versions/create Changed · +2 / -2 lines

from line 210

210210 

211211 - `assessment: "fail" or "pass" or "unknown" or "warn" or null`

212212 

213 The scan's verdict; set only when `status` is `completed`.

213 The scan's verdict; set only when `status` is `completed`. A `warn` can mean a `fail` that was allowed in claude.ai.

214214 

215215 - `"fail"`

216216 

from line 226

226226 

227227 - `status: "completed" or "errored" or "processing"`

228228 

229 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read.

229 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run. Once a scan of the version has completed, `content_scan` describes the newest completed scan, even while a later scan runs. While the scan outcome cannot be read, `status` is `errored` instead.

230230 

231231 - `"completed"`

232232 

api/beta/organization/plugins/versions/list Changed · +2 / -2 lines

from line 202

202202 

203203 - `assessment: "fail" or "pass" or "unknown" or "warn" or null`

204204 

205 The scan's verdict; set only when `status` is `completed`.

205 The scan's verdict; set only when `status` is `completed`. A `warn` can mean a `fail` that was allowed in claude.ai.

206206 

207207 - `"fail"`

208208 

from line 218

218218 

219219 - `status: "completed" or "errored" or "processing"`

220220 

221 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read.

221 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run. Once a scan of the version has completed, `content_scan` describes the newest completed scan, even while a later scan runs. While the scan outcome cannot be read, `status` is `errored` instead.

222222 

223223 - `"completed"`

224224 

api/beta/organization/plugins/versions/retrieve Changed · +2 / -2 lines

from line 189

189189 

190190 - `assessment: "fail" or "pass" or "unknown" or "warn" or null`

191191 

192 The scan's verdict; set only when `status` is `completed`.

192 The scan's verdict; set only when `status` is `completed`. A `warn` can mean a `fail` that was allowed in claude.ai.

193193 

194194 - `"fail"`

195195 

from line 205

205205 

206206 - `status: "completed" or "errored" or "processing"`

207207 

208 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read.

208 `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run. Once a scan of the version has completed, `content_scan` describes the newest completed scan, even while a later scan runs. While the scan outcome cannot be read, `status` is `errored` instead.

209209 

210210 - `"completed"`

211211 

api/beta/organization/rate_limits Changed · +2 / -2 lines

from line 171

171171 

172172 - `models: array of string or null`

173173 

174 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

174 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models your organization has access to, so it can differ between organizations.

175175 

176176- `next_page: string or null`

177177 

from line 323

323323 

324324 - `models: array of string or null`

325325 

326 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

326 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models your organization has access to, so it can differ between organizations.

327327 

328328### Beta Organization Rate Limit Batch Group

329329 

api/beta/organization/rate_limits/list Changed · +1 / -1 lines

from line 169

169169 

170170 - `models: array of string or null`

171171 

172 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

172 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models your organization has access to, so it can differ between organizations.

173173 

174174- `next_page: string or null`

175175 

api/beta/organization/workspaces Changed · +2 / -2 lines

from line 1468

14681468 

14691469 - `models: array of string or null`

14701470 

1471 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

1471 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

14721472 

14731473 - `rate_limit_id: string`

14741474 

from line 1721

17211721 

17221722 - `models: array of string or null`

17231723 

1724 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

1724 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

17251725 

17261726 - `rate_limit_id: string`

17271727 

api/beta/organization/workspaces/rate_limits/list Changed · +1 / -1 lines

from line 199

199199 

200200 - `models: array of string or null`

201201 

202 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

202 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

203203 

204204 - `rate_limit_id: string`

205205 

api/beta/organization/workspaces/rate_limits/update Changed · +1 / -1 lines

from line 201

201201 

202202 - `models: array of string or null`

203203 

204 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

204 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

205205 

206206 - `rate_limit_id: string`

207207 

api/errors Changed · +1 / -1 lines

from line 530

530530 

531531### Computer use tool version not supported

532532 

533On the Claude API and Google Cloud, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 support [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) only as the `computer_toolset_20260801` toolset. On those platforms, sending any of these models a `tools` entry of the earlier `computer_20251124` or `computer_20250124` type, with that tool's beta header, returns a 400 `invalid_request_error`. The message names the rejected type, then lists the tool types the model does accept after `Did you mean one of`. For Claude Opus 5.5, it begins:

533On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 support [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) only as the `computer_toolset_20260801` toolset. On those platforms, sending any of these models a `tools` entry of the earlier `computer_20251124` or `computer_20250124` type, with that tool's beta header, returns a 400 `invalid_request_error`. The message names the rejected type, then lists the tool types the model does accept after `Did you mean one of`. For Claude Opus 5.5, it begins:

534534 

535535```text wrap

536536'claude-opus-5-5' does not support tool types: computer_20251124.

api/organization/rate_limits Changed · +2 / -2 lines

from line 171

171171 

172172 - `models: array of string or null`

173173 

174 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

174 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models your organization has access to, so it can differ between organizations.

175175 

176176- `next_page: string or null`

177177 

from line 323

323323 

324324 - `models: array of string or null`

325325 

326 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

326 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models your organization has access to, so it can differ between organizations.

327327 

328328### Organization Rate Limit Batch Group

329329 

api/organization/rate_limits/list Changed · +1 / -1 lines

from line 169

169169 

170170 - `models: array of string or null`

171171 

172 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

172 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models your organization has access to, so it can differ between organizations.

173173 

174174- `next_page: string or null`

175175 

api/organization/workspaces Changed · +2 / -2 lines

from line 1358

13581358 

13591359 - `models: array of string or null`

13601360 

1361 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

1361 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

13621362 

13631363 - `rate_limit_id: string`

13641364 

from line 1611

16111611 

16121612 - `models: array of string or null`

16131613 

1614 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

1614 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

16151615 

16161616 - `rate_limit_id: string`

16171617 

api/organization/workspaces/rate_limits/list Changed · +1 / -1 lines

from line 199

199199 

200200 - `models: array of string or null`

201201 

202 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

202 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

203203 

204204 - `rate_limit_id: string`

205205 

api/organization/workspaces/rate_limits/update Changed · +1 / -1 lines

from line 201

201201 

202202 - `models: array of string or null`

203203 

204 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`.

204 Model names this entry's limits apply to, including aliases. `null` when `group.type` is not `"model_group"`. The list covers the models this workspace has access to, so it can differ between workspaces.

205205 

206206 - `rate_limit_id: string`

207207 

api/versioning Changed · +1 / -1 lines

from line 26

2626 

2727 * [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21) shows how to upgrade.

2828 

29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

3030 

3131 * Messages API:

3232 

build-with-claude/batch-processing Changed · +1 / -1 lines

from line 1551

15511551The `output-300k-2026-03-24` beta header raises the `max_tokens` cap to 300,000 for batch requests using Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6, or Claude Haiku 5.5. Include the header to generate outputs far longer than the standard 128k `max_tokens` limit in a single turn.

15521552 

15531553<Note>

1554 Extended output is available on the Message Batches API only, not the synchronous Messages API. It is supported on the Claude API and Claude Platform on AWS, and is not currently available on Amazon Bedrock, Google Cloud, or Microsoft Foundry.

1554 Extended output is available on the Message Batches API only, not the synchronous Messages API. It is supported on the Claude API and Claude Platform on AWS, and is not currently available on Amazon Bedrock, Claude Models on Google Cloud (Google managed), or Microsoft Foundry.

15551555</Note>

15561556 

15571557Use extended output for long-form generation such as book-length drafts and technical documentation, exhaustive structured data extraction, large code-generation scaffolds, and long reasoning chains.

build-with-claude/cache-diagnostics Changed · +1 / -1 lines

from line 1026

10261026 

10271027## Limitations

10281028 

1029* **Claude API only:** Not available on Amazon Bedrock or Google Cloud.

1029* **Claude API only:** Not available on Amazon Bedrock or Claude Models on Google Cloud (Google managed).

10301030* **Limited retention:** Fingerprints for `previous_message_id` lookup expire after a short period. Run diagnostic comparisons between closely spaced requests.

10311031* **Same workspace:** The previous request must have run in the same organization and workspace. To check, compare the `anthropic-workspace-id` [response header](https://platform.claude.com/docs/en/api/overview#response-headers) on the two responses.

10321032* **Comparison horizon:** For very long conversations where the only change is deep in the message list, the response might be `unavailable` rather than a precise location.

build-with-claude/claude-in-microsoft-foundry Changed · +1 / -1 lines

from line 669

669669 

670670## API responses

671671 

672API responses from Claude in Microsoft Foundry follow the standard [Claude API response format](https://platform.claude.com/docs/en/api/messages/create). This includes the `usage` object in response bodies, which provides detailed token consumption information for your requests. The `usage` object is consistent across all platforms (Claude API, Amazon Bedrock, Claude Platform on AWS, Foundry, and Google Cloud).

672API responses from Claude in Microsoft Foundry follow the standard [Claude API response format](https://platform.claude.com/docs/en/api/messages/create). This includes the `usage` object in response bodies, which provides detailed token consumption information for your requests. The `usage` object is consistent across all platforms, including the Claude API, Amazon Bedrock, Claude Platform on AWS, Foundry, and Claude Models on Google Cloud (Google managed).

673673 

674674For details on response headers specific to Foundry, see [Correlation request IDs](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#correlation-request-ids).

675675 

build-with-claude/effort Changed · +2 / -2 lines

from line 338

338338 

339339To get less thinking, lower the effort level. You can also send `thinking: {"type": "disabled"}` at `high` effort or below. At `xhigh` or `max`, it returns a 400 error, so use adaptive thinking there: omit the `thinking` field or send `thinking: {"type": "adaptive"}`.

340340 

341On the Claude API and Google Cloud, Claude Haiku 5.5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message `output_config`, which preserves the prompt cache. With `thinking: {"type": "disabled"}`, effort can't change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort per turn, use adaptive thinking.

341On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message `output_config`, which preserves the prompt cache. With `thinking: {"type": "disabled"}`, effort can't change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort per turn, use adaptive thinking.

342342 

343343## Effort with tool use

344344 

from line 372

372372 

373373### Per-message effort (beta)

374374 

375Per-message effort is in beta. On the Claude API and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), it's available on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Haiku 5.5. On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5.5. It requires the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `mid-conversation-output-config-2026-07-01`. With the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), it's available on Claude Fable 5.1 and Claude Opus 5.5, and you send that value in the `anthropic_beta` array of the request body instead.

375Per-message effort is in beta. On the Claude API and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), it's available on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Haiku 5.5. On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5.5. It requires the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `mid-conversation-output-config-2026-07-01`. With the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), it's available on Claude Fable 5.1 and Claude Opus 5.5, and you send that value in the `anthropic_beta` array of the request body instead.

376376 

377377Without the beta value, a per-message `output_config` returns a 400 error: `messages.N.output_config: Extra inputs are not permitted`, where `N` is the index of the `system` message in `messages`. With the beta value, models without per-message effort, including Claude Fable 5, return a 400 error: `output_config.effort requires a model that supports per-turn effort; this model does not`. On Amazon Bedrock, those models and Claude Opus 5 return the `Extra inputs are not permitted` error instead. On Claude Sonnet 5.5 with `thinking: {"type": "between_tools"}` and on Claude Haiku 5.5 with `thinking: {"type": "disabled"}`, effort can't change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking.

378378 

build-with-claude/extended-thinking Changed · +1 / -1 lines

from line 306

306306 

307307How platforms treat the beta header differs. The Claude API and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) accept `interleaved-thinking-2025-05-14` on any model and ignore it where unsupported. Acceptance is not the same as effect: on models that reject `type: "enabled"` (4.7 and later) or lack manual-mode interleaving (Claude Opus 4.6), the header has no manual-mode effect; adaptive thinking interleaves automatically there.

308308 

309Partner-operated platforms ([Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)) likewise accept the header on any model without returning an error, and ignore it on models that don't support interleaved thinking.

309Partner-operated platforms, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), likewise accept the header on any model without returning an error, and ignore it on models that don't support interleaved thinking.

310310 

311311## Turn structure in manual mode

312312 

build-with-claude/fast-mode Changed · +3 / -1 lines

from line 199

199199 

200200Fast mode on Claude Opus 5.5 is also available on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure. It is not available for deployments [hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options).

201201 

202Fast mode on Claude Opus 5.5 is also available on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).

203 

202204## Model availability

203205 

204206Fast mode is available only on the following models. If you were using fast mode on an earlier model, [migrate to a model that supports fast mode](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).

from line 250

248250 

249251## Checking which speed was used

250252 

251The response `usage` object includes a `speed` field that indicates which speed was used, either `"fast"` or `"standard"`. Requesting `speed: "fast"` on a [model that doesn't support fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models) returns an error, and so does exceeding fast mode's rate limits or capacity (a `429` or `529`). When a request with `speed: "fast"` succeeds, `usage.speed` is `"fast"`. Claude Opus 4.6 is an exception: instead of returning an error, a request with `speed: "fast"` and the `fast-mode-2026-02-01` beta header succeeds, but runs at standard speed. This behavior is correctly reflected in `usage.speed`, which shows `"standard"` in this situation.

253The response `usage` object includes a `speed` field that indicates which speed was used, either `"fast"` or `"standard"`. Requesting `speed: "fast"` on a [model that doesn't support fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models) returns an error, and so does exceeding fast mode's rate limits or capacity (a `429` or `529`). When a request with `speed: "fast"` succeeds, `usage.speed` is `"fast"`. Claude Opus 4.6 is an exception: instead of returning an error, a request with `speed: "fast"` and the `fast-mode-2026-02-01` beta header succeeds, but runs at standard speed. This behavior is correctly reflected in `usage.speed`, which shows `"standard"` in this situation. On Claude Models on Google Cloud (Anthropic managed), a Claude Opus 4.6 request with `speed: "fast"` returns a `400` error even with the header.

252254 

253255<CodeGroup>

254256 ```bash cURL

build-with-claude/handling-stop-reasons Changed · +1 / -1 lines

from line 1886

18861886</CodeGroup>

18871887 

18881888<Tip>

1889 If you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) or Claude Opus 4.1 (the latter [retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), you can try updating your API calls to use Haiku 4.5 (`claude-haiku-4-5-20251001`), which has different usage restrictions. Learn more about [understanding Sonnet 4.5's API safety filters](https://support.claude.com/en/articles/12449294-understanding-sonnet-4-5-s-api-safety-filters).

1889 If you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) or Claude Opus 4.1 (the latter [retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)), you can try updating your API calls to use Haiku 4.5 (`claude-haiku-4-5-20251001`), which has different usage restrictions. Learn more about [understanding Sonnet 4.5's API safety filters](https://support.claude.com/en/articles/12449294-understanding-sonnet-4-5-s-api-safety-filters).

18901890</Tip>

18911891 

18921892On a refusal, the `stop_details` object identifies the policy category that triggered it. The categories and the full refusal response shape are covered in [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). `stop_details` is `null` for all stop reasons other than `refusal`.

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

from line 26

2626| **Deprecated** | Feature is still functional but no longer recommended. A migration path and removal timeline are provided. |

2727| **Retired** | Feature is no longer available. |

2828 

29**Platform labels:** Claude API (Anthropic first-party) · [Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) (AWS-operated) · [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) (Anthropic-operated on AWS) · [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) (Google-operated) · [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (Anthropic-operated on Azure)

29**Platform labels:** Claude API (Anthropic first-party) · [Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) (AWS-operated) · [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) (Anthropic-operated on AWS) · [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) (Google-operated) · [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (Anthropic-operated on Azure)

3030 

3131## Model capabilities

3232 

build-with-claude/pdf-support Changed · +1 / -1 lines

from line 99

99993. By a `file_id` from the [Files API](https://platform.claude.com/docs/en/build-with-claude/files)

100100 

101101<Note>

102 On Amazon Bedrock and Google Cloud, only base64-encoded sources are currently available. On Microsoft Foundry, the Files API is not supported for deployments hosted on Azure.

102 On Amazon Bedrock and Claude Models on Google Cloud (Google managed), only base64-encoded sources are currently available. On Microsoft Foundry, the Files API is not supported for deployments hosted on Azure.

103103</Note>

104104 

105105#### Option 1: URL-based PDF document