Follow Discord
Sweep 31 Oct 2026 · 01:10Z Build v2.1.316 534 read Stable v2.1.309 Latest v2.1.316 Next v2.1.316 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One capture · api

One read of Claude Developer Platformapi-20261031T010031Z

45 pages moved out of 845 read.

Pages moved 45 significant first
Pages read 845 in this capture
Captured 01:00 UTC
Corpus hash 6633f06377b7 corpus-hash

What this read moved

26-45 of 45, page 2 of 2

This capture is too large to show at once. Changes 26-45 of 45 are below, significant first; the rest are on the following screens.

build-with-claude/refusals-and-fallback Changed · +6 / -6 lines

from line 12
1212 - claude-sonnet-5-5
1313 - claude-haiku-5-5
1414 supportedPlatforms:
15 Claude API: ga
16 Claude Platform on AWS: ga
17 Claude Models on Google Cloud (Anthropic managed): ga
18 Amazon Bedrock: ga
19 Claude Models on Google Cloud (Google managed): ga
20 Microsoft Foundry: ga
15 Claude API: stable
16 Claude Platform on AWS: stable
17 Claude Models on Google Cloud (Anthropic managed): stable
18 Amazon Bedrock: stable
19 Claude Models on Google Cloud (Google managed): stable
20 Microsoft Foundry: stable
2121---
2222 
2323Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Haiku 5.5 include safety classifiers that can decline a request. When that happens, you receive a normal response, not an error, with `stop_reason: "refusal"`. Its `stop_details.category` names the policy area (see [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response)). You can usually still get an answer by sending the same request to another Claude model. This page shows you how to recognize a refusal and how to set up that retry.

build-with-claude/search-results Changed · +7 / -7 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/search-results
44description: Get natural citations for RAG applications by providing search results with source attribution
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: eligible
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
30 Claude Platform on AWS: ga
31 Amazon Bedrock: ga
32 Amazon Bedrock (InvokeModel): ga
33 Claude Models on Google Cloud (Google managed): ga
34 Microsoft Foundry: ga
29 Claude API: stable
30 Claude Platform on AWS: stable
31 Amazon Bedrock: stable
32 Amazon Bedrock (InvokeModel): stable
33 Claude Models on Google Cloud (Google managed): stable
34 Microsoft Foundry: stable
3535---
3636 
3737**API support**: Usage differs by product.

build-with-claude/streaming Changed · +8 / -8 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/streaming
44description: Stream Messages API responses incrementally with server-sent events, including text, tool use, and thinking deltas.
55featureMetadata:
6 status: ga
6 status: stable
77 supportedModels:
88 - claude-fable-5-1
99 - claude-mythos-5-1
from line 23
2323 - claude-opus-4-5-20251101
2424 - claude-sonnet-4-5-20250929
2525 supportedPlatforms:
26 Claude API: ga
27 Claude Platform on AWS: ga
28 Claude Models on Google Cloud (Anthropic managed): ga
29 Amazon Bedrock: ga
26 Claude API: stable
27 Claude Platform on AWS: stable
28 Claude Models on Google Cloud (Anthropic managed): stable
29 Amazon Bedrock: stable
3030 Amazon Bedrock (InvokeModel):
31 availability: ga
31 availability: stable
3232 note: The older Amazon Bedrock InvokeModel integration does not stream plain server-sent events.
33 Claude Models on Google Cloud (Google managed): ga
34 Microsoft Foundry: ga
33 Claude Models on Google Cloud (Google managed): stable
34 Microsoft Foundry: stable
3535---
3636 
3737When creating a Message, you can set `"stream": true` to incrementally stream the response using [server-sent events](https://developer.mozilla.org/en-US/Web/API/Server-sent%5Fevents/Using%5Fserver-sent%5Fevents) (SSE).

build-with-claude/structured-outputs Changed · +8 / -8 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/structured-outputs
44description: Get validated JSON results from agent workflows
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: qualified
99 note: "Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Your prompts and Claude's outputs are not stored. Only the JSON schema is cached, for up to 24 hours since last use. This also covers strict tool use (`strict: true` on tools), which uses the same grammar pipeline."
from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
30 Claude Platform on AWS: ga
31 Claude Models on Google Cloud (Anthropic managed): ga
32 Amazon Bedrock: ga
33 Amazon Bedrock (InvokeModel): ga
34 Claude Models on Google Cloud (Google managed): ga
35 Microsoft Foundry: ga
29 Claude API: stable
30 Claude Platform on AWS: stable
31 Claude Models on Google Cloud (Anthropic managed): stable
32 Amazon Bedrock: stable
33 Amazon Bedrock (InvokeModel): stable
34 Claude Models on Google Cloud (Google managed): stable
35 Microsoft Foundry: stable
3636---
3737 
3838Structured outputs constrain Claude’s responses to follow a specific schema, ensuring valid, parseable output for downstream processing. Structured outputs provide two complementary features:

build-with-claude/thinking Changed · +8 / -8 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/thinking
44description: "Understand how Claude's thinking works: turn it on, read thinking output, steer thinking depth with effort, and use thinking with tools, caching, and streaming."
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: eligible
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
30 Claude Platform on AWS: ga
31 Claude Models on Google Cloud (Anthropic managed): ga
32 Amazon Bedrock: ga
33 Amazon Bedrock (InvokeModel): ga
34 Claude Models on Google Cloud (Google managed): ga
35 Microsoft Foundry: ga
29 Claude API: stable
30 Claude Platform on AWS: stable
31 Claude Models on Google Cloud (Anthropic managed): stable
32 Amazon Bedrock: stable
33 Amazon Bedrock (InvokeModel): stable
34 Claude Models on Google Cloud (Google managed): stable
35 Microsoft Foundry: stable
3636---
3737 
3838**API support**: Usage differs by product.

build-with-claude/token-counting Changed · +8 / -8 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/token-counting
44description: Count the tokens in a message before you send it to Claude. Use token counts to manage rate limits and costs, make model routing decisions, and fit prompts to a target length.
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: eligible
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Count tokens before sending requests.
from line 25
2525 - claude-sonnet-4-6
2626 - claude-opus-4-5-20251101
2727 supportedPlatforms:
28 Claude API: ga
29 Claude Platform on AWS: ga
30 Claude Models on Google Cloud (Anthropic managed): ga
31 Amazon Bedrock: ga
32 Amazon Bedrock (InvokeModel): ga
33 Claude Models on Google Cloud (Google managed): ga
34 Microsoft Foundry: ga
28 Claude API: stable
29 Claude Platform on AWS: stable
30 Claude Models on Google Cloud (Anthropic managed): stable
31 Amazon Bedrock: stable
32 Amazon Bedrock (InvokeModel): stable
33 Claude Models on Google Cloud (Google managed): stable
34 Microsoft Foundry: stable
3535---
3636 
3737Token counting lets you determine the number of tokens in a message before you send it to Claude. This helps you make informed decisions about your prompts and usage. With token counting, you can:

build-with-claude/vision Changed · +8 / -8 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/vision
44description: Claude's vision capabilities allow it to process and analyze images, opening up exciting possibilities for multimodal interaction.
55featureMetadata:
6 status: ga
6 status: stable
77 supportedModels:
88 - claude-fable-5-1
99 - claude-mythos-5-1
from line 23
2323 - claude-opus-4-5-20251101
2424 - claude-sonnet-4-5-20250929
2525 supportedPlatforms:
26 Claude API: ga
27 Claude Platform on AWS: ga
28 Claude Models on Google Cloud (Anthropic managed): ga
26 Claude API: stable
27 Claude Platform on AWS: stable
28 Claude Models on Google Cloud (Anthropic managed): stable
2929 Amazon Bedrock:
30 availability: ga
30 availability: stable
3131 note: Only base64 image sources; per-image limit 5 MB (base64-encoded) and a lower total request size.
3232 Amazon Bedrock (InvokeModel):
33 availability: ga
33 availability: stable
3434 note: Only base64 image sources; per-image limit 5 MB (base64-encoded) and a lower total request size.
3535 Claude Models on Google Cloud (Google managed):
36 availability: ga
36 availability: stable
3737 note: Only base64 image sources; per-image limit 5 MB (base64-encoded) and a lower total request size.
38 Microsoft Foundry: ga
38 Microsoft Foundry: stable
3939---
4040 
4141This guide describes how to send images to Claude, the limits and costs that apply, and where to find guidance for [coordinate-based workflows](https://platform.claude.com/docs/en/build-with-claude/vision-coordinates).

build-with-claude/working-with-messages Changed · +8 / -8 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/working-with-messages
44description: Practical patterns and examples for using the Messages API effectively
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: eligible
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Standard API calls for generating Claude responses.
from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
30 Claude Platform on AWS: ga
31 Claude Models on Google Cloud (Anthropic managed): ga
32 Amazon Bedrock: ga
33 Amazon Bedrock (InvokeModel): ga
34 Claude Models on Google Cloud (Google managed): ga
35 Microsoft Foundry: ga
29 Claude API: stable
30 Claude Platform on AWS: stable
31 Claude Models on Google Cloud (Anthropic managed): stable
32 Amazon Bedrock: stable
33 Amazon Bedrock (InvokeModel): stable
34 Claude Models on Google Cloud (Google managed): stable
35 Microsoft Foundry: stable
3636---
3737 
3838Anthropic offers two ways to build with Claude, each suited to different use cases:

cli-sdks-libraries/middleware Changed · +6 / -6 lines

from line 22
2222 - claude-opus-4-5-20251101
2323 - claude-sonnet-4-5-20250929
2424 supportedPlatforms:
25 Claude API: ga
26 Claude Platform on AWS: ga
27 Amazon Bedrock: ga
28 Amazon Bedrock (InvokeModel): ga
29 Claude Models on Google Cloud (Google managed): ga
30 Microsoft Foundry: ga
25 Claude API: stable
26 Claude Platform on AWS: stable
27 Amazon Bedrock: stable
28 Amazon Bedrock (InvokeModel): stable
29 Claude Models on Google Cloud (Google managed): stable
30 Microsoft Foundry: stable
3131---
3232 
3333The Claude SDK provides a middleware (or interceptor) hook that lets you run code before a request is sent and after the response is received. Use middleware for cross-cutting concerns such as logging, custom retries, request annotation, and refusal fallback handling.

manage-claude/compliance-errors Changed · +3 / -3 lines

from line 287
287287 
288288**Cause:** The file ID does not exist in an organization your key can read, or the file has been deleted. Deleting a chat in claude.ai also deletes the files attached to it, although the chat itself remains listed. The message identifies the file by its underlying UUID rather than by the `claude_file_...` ID sent in the request. The metadata, content, and delete endpoints return this body; it applies to both chat-attached files (`claude_file_...`) and project files.
289289 
290**Fix:** Reconcile against recent `claude_file_uploaded` or `claude_file_deleted` activities. Files deleted along with a chat have no `claude_file_deleted` activity, so check for the chat’s `claude_chat_deleted` activity as well. If the file was deleted, the binary is gone; the activity records remain in the feed for the 6-year retention window.
290**Fix:** Reconcile against recent `claude_file_uploaded` or `claude_file_deleted` activities. Files deleted along with a chat have no `claude_file_deleted` activity, so check for the chat’s `claude_chat_deleted` activity as well. When your organization’s retention policy deletes a chat, the Activity Feed records no `claude_chat_deleted` activity. If the file was deleted, the binary is gone; the activity records remain in the feed for the 6-year retention window.
291291 
292292### Generated file or artifact not found
293293 
from line 307
307307 
308308**Cause:** The ID in the path does not match a tool-generated file or artifact version readable through the Compliance API. The generated-file metadata endpoint returns the first body, the content endpoint returns the second, and both artifact endpoints return the third. Generated files and artifacts are deleted with the chat they were created in, including when a user deletes the chat in claude.ai.
309309 
310**Fix:** Use [Get chat messages](https://platform.claude.com/docs/en/api/compliance/apps/chats/messages/list) to look up the chat the ID came from. If the chat’s `deleted_at` is populated, or a `claude_chat_deleted` activity names the chat, the content is gone; remove the ID from your queue. Otherwise, confirm the ID against the `generated_files` and `artifacts` arrays on the chat’s messages.
310**Fix:** Use [Get chat messages](https://platform.claude.com/docs/en/api/compliance/apps/chats/messages/list) to look up the chat the ID came from. If the chat’s `deleted_at` is populated, or a `claude_chat_deleted` activity names the chat, the content is gone; remove the ID from your queue. Otherwise, confirm the ID against the `generated_files` and `artifacts` arrays on the chat’s messages. When your organization’s retention policy deletes a chat, the Activity Feed records no `claude_chat_deleted` activity.
311311 
312312### Project not found
313313 
from line 323
323323 
324324**Cause:** The project ID does not exist or has been deleted. The project detail, attachments, and collaborators endpoints return the first body; `DELETE /v1/compliance/apps/projects/{project_id}` returns the second.
325325 
326**Fix:** Reconcile against recent `claude_project_created` or `claude_project_deleted` activities. The Activity Feed continues to expose the project’s lifecycle events even after the project itself is gone.
326**Fix:** Reconcile against recent `claude_project_created` or `claude_project_deleted` activities. The Activity Feed continues to expose the project’s lifecycle events even after the project itself is gone. When your organization’s retention policy deletes a project, the Activity Feed records no `claude_project_deleted` activity.
327327 
328328### Project document not found
329329 

manage-claude/data-residency Changed · +4 / -4 lines

from line 3
33url: https://platform.claude.com/docs/en/manage-claude/data-residency
44description: Manage where model inference runs and where data is stored with geographic controls.
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: eligible
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
from line 23
2323 - claude-opus-4-6
2424 - claude-sonnet-4-6
2525 supportedPlatforms:
26 Claude API: ga
26 Claude API: stable
2727 Claude Platform on AWS:
28 availability: ga
28 availability: stable
2929 note: Workspace geo is not configurable; Managed Agents sessions there run with workspace geo "us".
3030 Claude Models on Google Cloud (Anthropic managed):
31 availability: ga
31 availability: stable
3232 note: Workspace geo is not configurable.
3333---
3434 

managed-agents/dreams Changed · +6 / -15 lines

from line 11
1111 supportedModels:
1212 - claude-fable-5-1
1313 - claude-fable-5
14 - claude-mythos-preview
1514 - claude-opus-5-5
1615 - claude-opus-5
1716 - claude-sonnet-5-5
from line 34
3534 
3635The input store is never modified, so you can review the output and discard it if you don’t like the result.
3736 
38<Note>
39 Dream endpoints are gated by the `dreaming-2026-04-21` beta header; the `managed-agents-2026-04-01` header on its own doesn’t grant access to dreams. The dream-endpoint examples on this page send both headers; session and memory-store calls need only `managed-agents-2026-04-01`. The SDK sets these automatically.
40</Note>
41 
4237## How it works
4338 
4439A **dream** is an asynchronous job that takes:
from line 166
171166 ```
172167</CodeGroup>
173168 
174Dreaming inputs include the pre-existing memory store and an array of sessions. The selected model runs the dreaming pipeline. During the research preview, `claude-opus-5-5`, `claude-fable-5-1`, `claude-opus-5`, `claude-fable-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-sonnet-5-5`, `claude-sonnet-5`, and `claude-sonnet-4-6` are supported. You can optionally pass `instructions` (csharp, go: `Instructions`) to steer the dreaming process. See [Steer with instructions](https://platform.claude.com/docs/en/managed-agents/dreams#steer-with-instructions).
169Dreaming inputs include the pre-existing memory store and an array of sessions. The model you choose runs the dreaming pipeline. Only [select models](https://platform.claude.com/docs/en/managed-agents/dreams#feature-availability) are supported. You can optionally pass `instructions` (csharp, go: `Instructions`) to steer the dreaming process. See [Steer with instructions](https://platform.claude.com/docs/en/managed-agents/dreams#steer-with-instructions).
175170 
176171The response is the full `dream` resource with `status: "pending"`:
177172 
from line 644
649644 
650645## Limits
651646 
652| Limit | Value |
653| -------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
654| Sessions per dream | 100 |
655| `instructions` (csharp, go: `Instructions`) length | 4,096 characters |
656| Supported models | `claude-opus-5-5`, `claude-fable-5-1`, `claude-opus-5`, `claude-fable-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-sonnet-5-5`, `claude-sonnet-5`, `claude-sonnet-4-6` |
657 
658647Default rate limits apply to dream creation while this feature is in research preview. [Contact support](https://support.claude.com) if you need higher limits.
659648 
660649## Availability
from line 656
667656 
668657* Availability: Available
669658 
670| Status | Cloud platforms | Models |
671| ---------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
672| Research preview | Claude API | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) |
659| Status | Cloud platforms | Models |
660| ---------------- | --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
661| Research preview | Claude API | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) |
673662 
674663### Required beta headers
675664 
from line 668
679668 
680669* `managed-agents-2026-04-01`
681670* `dreaming-2026-04-21`
671 
672Dream endpoints require the `dreaming-2026-04-21` beta header. The `managed-agents-2026-04-01` header on its own doesn’t grant access to dreams. Session calls use `managed-agents-2026-04-01`, and memory store calls use `agent-memory-2026-07-22`. The SDK sets the right header on each call.
682673 
683674### Data handling
684675 

release-notes/overview Changed · +3 / -3 lines

from line 93
9393### October 1, 2026
9494 
9595* We’ve added a `line` field to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now return the model line each model belongs to. Claude Opus 4.5 and Claude Opus 4.6 both report `opus`, for example. Use `line` to group models without parsing their IDs. `line` is `null` for a model that belongs to no line. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
96* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Opus 5.5, Claude Fable 5.1, and Claude Sonnet 5.5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#limits).
96* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Opus 5.5, Claude Fable 5.1, and Claude Sonnet 5.5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#feature-availability).
9797 
9898### September 30, 2026
9999 
from line 220
220220 
221221### August 1, 2026
222222 
223* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Opus 5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#limits).
223* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Opus 5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#feature-availability).
224224 
225225### July 24, 2026
226226 
from line 254
254254 
255255### July 10, 2026
256256 
257* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Fable 5 and Claude Sonnet 5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#limits).
257* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Fable 5 and Claude Sonnet 5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#feature-availability).
258258* We’ve expanded the [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency) documentation of `cmek_preserve` events with a filter example, an example event payload, and two preservation reason codes (`policy_violation_investigation`, `csae_report`). The documentation now also clarifies that a preservation event is written whether the preservation was initiated by a human reviewer or an automated safety pipeline. See [CMEK content preservation](https://platform.claude.com/docs/en/manage-claude/access-transparency#cmek-content-preservation).
259259 
260260### July 8, 2026

test-and-evaluate/strengthen-guardrails/handle-streaming-refusals Changed · +6 / -6 lines

from line 22
2222 - claude-opus-4-5-20251101
2323 - claude-sonnet-4-5-20250929
2424 supportedPlatforms:
25 Claude API: ga
26 Claude Platform on AWS: ga
27 Amazon Bedrock: ga
28 Amazon Bedrock (InvokeModel): ga
29 Claude Models on Google Cloud (Google managed): ga
30 Microsoft Foundry: ga
25 Claude API: stable
26 Claude Platform on AWS: stable
27 Amazon Bedrock: stable
28 Amazon Bedrock (InvokeModel): stable
29 Claude Models on Google Cloud (Google managed): stable
30 Microsoft Foundry: stable
3131---
3232 
3333**API support**: Usage differs by product.

agents-and-tools/tool-use/computer-use-tool Changed · +2 / -2 lines

from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
29 Claude API: stable
3030 Claude Platform on AWS: beta
3131 Amazon Bedrock: beta
3232 Amazon Bedrock (InvokeModel): beta
33 Claude Models on Google Cloud (Google managed): ga
33 Claude Models on Google Cloud (Google managed): stable
3434 Microsoft Foundry: beta
3535 details:
3636 - On the Claude API and Claude Models on Google Cloud (Google managed), Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier `computer_20251124` and `computer_20250124` tool versions. To move an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide.

api/service-tiers Changed · +2 / -2 lines

from line 3
33url: https://platform.claude.com/docs/en/api/service-tiers
44description: Different tiers of service allow you to balance availability, performance, and predictable costs based on your application's needs.
55featureMetadata:
6 status: ga
6 status: stable
77 supportedModels:
88 - claude-fable-5-1
99 - claude-mythos-5-1
from line 23
2323 - claude-opus-4-5-20251101
2424 - claude-sonnet-4-5-20250929
2525 supportedPlatforms:
26 Claude API: ga
26 Claude API: stable
2727---
2828 
2929<Warning>

build-with-claude/cache-diagnostics Changed · +2 / -2 lines

from line 3
33url: https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics
44description: Diagnose unexpected prompt cache misses by comparing consecutive requests and identifying exactly where the prompt prefix diverged.
55featureMetadata:
6 status: ga
6 status: stable
77 zdr:
88 eligibility: qualified
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Your prompts and Claude's outputs are not stored. A fingerprint of cryptographic hashes and token-count estimates is retained briefly to allow comparison against the next request.
from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
29 Claude API: stable
3030---
3131 
3232[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) cuts latency and cost significantly, but only when the beginning of your prompt is byte-for-byte identical to a recent request. A reordered tool, a timestamp interpolated into your system prompt, or an edit to an earlier message can silently invalidate the cache. Without cache diagnostics, the only signal is `usage.cache_read_input_tokens` dropping to zero, with no indication of what changed.

cli-sdks-libraries/libraries/openai-sdk Changed · +2 / -2 lines

from line 3
33url: https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk
44description: Anthropic provides a compatibility layer that lets you use the OpenAI SDK to test the Claude API. With a few code changes, you can evaluate Anthropic model capabilities.
55featureMetadata:
6 status: ga
6 status: stable
77 supportedModels:
88 - claude-fable-5-1
99 - claude-mythos-5-1
from line 23
2323 - claude-opus-4-5-20251101
2424 - claude-sonnet-4-5-20250929
2525 supportedPlatforms:
26 Claude API: ga
26 Claude API: stable
2727---
2828 
2929<Note>

manage-claude/compliance-activity-feed Changed · +2 / -0 lines

from line 164
164164 
165165A `claude_*_viewed` activity means a Claude app loaded content, not that a person viewed it. Types such as `claude_chat_viewed`, `claude_file_viewed`, and `claude_project_viewed` are recorded each time a Claude app loads the chat, file, or project from Anthropic’s servers. Repeated loads are not deduplicated. The web, desktop, and mobile apps load content at different moments, sometimes in the background, and can display a cached copy without loading it. Counts of these activities vary by platform as a result, and they do not correspond to messages sent or screens viewed.
166166 
167A missing `*_deleted` activity does not mean the content still exists. When your organization’s retention policy deletes a chat, project, or published artifact, the Activity Feed records no `claude_chat_deleted`, `claude_project_deleted`, or `claude_published_artifact_deleted` activity. An admin’s change to the policy is recorded as a `data_retention_periods` update in `claude_organization_settings_updated`.
168 
167169Activities about a file, project document, or artifact do not include its name or title. As of September 24, 2026, the `filename` and `title` fields on these activities are always `null`, an empty string, or omitted, including on activities recorded before that date. To look up a name or title, pass the activity’s `claude_file_*`, `claude_proj_doc_*`, or `claude_artifact_version_*` ID to the matching metadata endpoint in [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts), using a Compliance Access Key with the `read:compliance_user_data` scope. You cannot look up a name or title after the file, document, or artifact is deleted, or when the activity has no such ID.
168170 
169171<Note>

managed-agents/tools-web-restrictions Changed · +1 / -1 lines

from line 26
2626 - claude-opus-4-5-20251101
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
29 Claude API: ga
29 Claude API: stable
3030 Claude Platform on AWS: beta
3131 Claude Models on Google Cloud (Anthropic managed): beta
3232---
Feedback