HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
821pages tracked
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
145 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
65 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
10,173 of the ledger's changes in api. Show every change
ReadSourcePageWhatLines
9 Oct 2026
560 pages
+55980 −25839 lines
api
agents-and-tools/tool-use/computer-use-tool
±changed
+5−5
apichanged
agents-and-tools/tool-use/computer-use-tool
- On the Claude API and Google Cloud, Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier
- On Amazon Bedrock, Claude Opus 5.5 and Claude Sonnet 5.5 accept the earlier `computer_20251124` tool version as Claude Opus 5 and Claude Sonnet 5 do.
- On the Claude API and Google Cloud, Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier
- On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 accept the earlier `computer_20251124` tool version as Claude Opus 5 and Claude Sonnet 5 do.
Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-an
+5 −5 lines
Recorded here 9 Oct 2026 15:37 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+0−2
apichanged
agents-and-tools/tool-use/code-execution-tool
Amazon Bedrock: not available
Google Cloud: not available
+0 −2 lines
Recorded here 9 Oct 2026 15:37 UTC
api
agents-and-tools/tool-use/browser-use-tool
±changed
+1−4
apichanged
agents-and-tools/tool-use/browser-use-tool
Claude Platform on AWS: not available
Amazon Bedrock: not available
Microsoft Foundry: not available
**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,610 on Claude Fable 5, Claude Myt
**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,670 on Claude Sonnet 5 and about
+1 −4 lines
Recorded here 9 Oct 2026 15:37 UTC
api
agents-and-tools/tool-use/bash-tool
±changed
+4−4
apichanged
agents-and-tools/tool-use/bash-tool
| Model | Additional input tokens |
| --------------------------------------------------- | ----------------------- |
| Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7 | 325 tokens |
| Claude Opus 4.6, Claude Sonnet 4.6, and earlier | 244 tokens |
| Model | Additional input tokens |
+4 −4 lines
Recorded here 9 Oct 2026 15:37 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+32−30
apichanged
agents-and-tools/tool-use/advisor-tool
If a Haiku executor has not called the advisor in its first assistant turn, append a short reminder as an additional user message before the second assistant turn. In Anthropic's i
If a Haiku executor has not called the advisor in its first assistant turn, append a short reminder as an additional user message before the second assistant turn. In Anthropic's i
model="claude-haiku-4-5",
model="claude-haiku-5-5",
if response.stop_reason == "end_turn":
+32 −30 lines
Recorded here 9 Oct 2026 15:37 UTC
api
agents-and-tools/mcp-connector
±changed
+0−2
apichanged
agents-and-tools/mcp-connector
Amazon Bedrock: not available
Google Cloud: not available
+0 −2 lines
Recorded here 9 Oct 2026 15:37 UTC
api
about-claude/pricing
±changed
+13−12
apichanged
about-claude/pricing
* **Google Cloud** offers three endpoint types: global endpoints, multi-region endpoints (dynamic routing within a geographic area), and regional endpoints.
* **Google Cloud** offers global endpoints and multi-region endpoints (dynamic routing within a geographic area) for these models, and regional endpoints for Claude Sonnet 4.6 an
For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens
For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens
| Model | Additional input tokens |
+13 −12 lines
Recorded here 9 Oct 2026 15:37 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+21−12
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
The cache is a byte-exact prefix match over the request in order (tools, then system prompt, then messages), so a change anywhere invalidates everything after it. Changing [`effort
The cache is a byte-exact prefix match over the request in order (tools, then system prompt, then messages), so a change anywhere invalidates everything after it. Changing [`effort
Compare on cost per solved task, not per token: the same text costs about 30% more tokens on Claude Opus 4.7 and later, so a per-token comparison makes the newer models look more e
Compare on cost per solved task, not per token: the same text costs about 30% more tokens on Claude 4.7 and later models, so a per-token comparison makes the newer models look more
1. Pull a few tasks from production logs, weighted like real traffic, and [write outcome checks](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) for each: test
+21 −12 lines
Recorded here 9 Oct 2026 15:37 UTC
api
about-claude/models/choosing-a-model
±changed
+5−1
apichanged
about-claude/models/choosing-a-model
* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within
* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within
<Card title="What's new in Claude Haiku 5.5" icon="sparkle" href="https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5">
The latest Haiku model: breaking changes, new features, and behavior differences
</Card>
+5 −1 lines
Recorded here 9 Oct 2026 15:37 UTC
api
about-claude/model-deprecations
±changed
+8−8
apichanged
about-claude/model-deprecations
| June 15, 2026 | `claude-sonnet-4-20250514` | `claude-sonnet-4-6` |
| June 15, 2026 | `claude-sonnet-4-20250514` | `claude-sonnet-5-5` |
| February 19, 2026 | `claude-3-7-sonnet-20250219` | `claude-sonnet-4-6` |
| February 19, 2026 | `claude-3-7-sonnet-20250219` | `claude-sonnet-5-5` |
| October 28, 2025 | `claude-3-5-sonnet-20240620` | `claude-sonnet-4-6` |
+8 −8 lines
Recorded here 9 Oct 2026 15:37 UTC
api
about-claude/glossary
±changed
+1−1
apichanged
about-claude/glossary
Tokens are the smallest individual units of a language model, and can correspond to words, subwords, characters, or even bytes (in the case of Unicode). For Claude, a token approxi
Tokens are the smallest individual units of a language model, and can correspond to words, subwords, characters, or even bytes (in the case of Unicode). For Claude, the number of c
+1 −1 lines
Recorded here 9 Oct 2026 15:37 UTC
api
manage-claude/workspaces
±changed
+16−12
apichanged
manage-claude/workspaces
Click **Create** to finalize.
Click **Create workspace** to finalize.
To switch between workspaces in the Console, use the **Workspaces** selector in the top-left corner.
To switch between workspaces in the Console, leave Settings and use the workspace picker at the top of the sidebar.
2. Click the ellipsis menu (**...**) and choose **Edit details**.
+16 −12 lines
Recorded here 9 Oct 2026 00:07 UTC
api
manage-claude/api-and-data-retention
±changed
+1−1
apichanged
manage-claude/api-and-data-retention
In [Claude Console > Settings > Workspaces](https://platform.claude.com/settings/workspaces), select the workspace and open its **Privacy controls** tab.
In [Claude Console > Settings > Workspaces](https://platform.claude.com/settings/workspaces), select the workspace. In the panel that opens, click **Security** to open the work
+1 −1 lines
Recorded here 9 Oct 2026 00:07 UTC
api
about-claude/pricing
±changed
+1−1
apichanged
about-claude/pricing
Claude Haiku 5.5 is priced by prompt length: a prompt of over 100,000 tokens pays higher prices. [Model pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pric
Claude Haiku 5.5 is priced by prompt length: a request whose prompt is over 100,000 tokens pays higher prices. A request's prompt length counts all of its input tokens, including c
+1 −1 lines
Recorded here 9 Oct 2026 00:07 UTC
8 Oct 2026
171 pages
+50915 −21102 lines
api
managed-agents/self-hosted-sandboxes-workers
±changed
+1−1
apichanged
managed-agents/self-hosted-sandboxes-workers
ARG ANT_VERSION=1.39.0
ARG ANT_VERSION=1.39.1
+1 −1 lines
Recorded here 8 Oct 2026 16:07 UTC
api
managed-agents/quickstart
±changed
+2−2
apichanged
managed-agents/quickstart
VERSION=1.39.0
VERSION=1.39.1
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
+2 −2 lines
Recorded here 8 Oct 2026 16:07 UTC
api
get-started
±changed
+2−2
apichanged
get-started
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
<version>2.69.0</version>
<version>2.70.0</version>
+2 −2 lines
Recorded here 8 Oct 2026 16:07 UTC
api
cli-sdks-libraries/sdks/java
±changed
+2−2
apichanged
cli-sdks-libraries/sdks/java
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
<version>2.69.0</version>
<version>2.70.0</version>
+2 −2 lines
Recorded here 8 Oct 2026 16:07 UTC
api
cli-sdks-libraries/cli/quickstart
±changed
+1−1
apichanged
cli-sdks-libraries/cli/quickstart
VERSION=1.39.0
VERSION=1.39.1
+1 −1 lines
Recorded here 8 Oct 2026 16:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+4−4
apichanged
build-with-claude/claude-platform-on-aws
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-aws:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
implementation("com.anthropic:anthropic-java-aws:2.70.0")
<version>2.69.0</version>
+4 −4 lines
Recorded here 8 Oct 2026 16:07 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+4−4
apichanged
build-with-claude/claude-on-vertex-ai
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-vertex:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
implementation("com.anthropic:anthropic-java-vertex:2.70.0")
<version>2.69.0</version>
+4 −4 lines
Recorded here 8 Oct 2026 16:07 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+4−4
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-bedrock:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
implementation("com.anthropic:anthropic-java-bedrock:2.70.0")
<version>2.69.0</version>
+4 −4 lines
Recorded here 8 Oct 2026 16:07 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+4−4
apichanged
build-with-claude/claude-in-microsoft-foundry
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-foundry:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
implementation("com.anthropic:anthropic-java-foundry:2.70.0")
<version>2.69.0</version>
+4 −4 lines
Recorded here 8 Oct 2026 16:07 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+4−4
apichanged
build-with-claude/claude-in-amazon-bedrock
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-bedrock:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
implementation("com.anthropic:anthropic-java-bedrock:2.70.0")
<version>2.69.0</version>
+4 −4 lines
Recorded here 8 Oct 2026 16:07 UTC
api
agents-and-tools/mcp-connector
±changed
+4−4
apichanged
agents-and-tools/mcp-connector
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-mcp:2.69.0")
implementation("com.anthropic:anthropic-java:2.70.0")
implementation("com.anthropic:anthropic-java-mcp:2.70.0")
<version>2.69.0</version>
+4 −4 lines
Recorded here 8 Oct 2026 16:07 UTC
api
manage-claude/workspaces
±changed
+6−6
apichanged
manage-claude/workspaces
* Claude Code usage is rate-limited separately, and admins can cap its share of the organization's limits under [Settings > Workspaces](https://platform.claude.com/settings/workspa
* Claude Code usage is rate-limited separately, and admins can cap its share of the organization's limits on the [Rate limits](https://platform.claude.com/usage/limits) page in the
Each workspace's settings split these across two tabs:
* **Rate limits:** On the **Rate limits** tab, set limits per model tier for requests per minute, input tokens, or output tokens
+6 −6 lines
Recorded here 8 Oct 2026 08:37 UTC
api
manage-claude/rate-limits-api
±changed
+2−2
apichanged
manage-claude/rate-limits-api
The Rate Limits API provides programmatic access to the rate limits configured for your organization and its workspaces. This is the same information shown on the [Rate limits](htt
The Rate Limits API provides programmatic access to the rate limits configured for your organization and its workspaces. This is the same information shown on the [Rate limits](htt
No. To set workspace rate limits, open the workspace in the [Claude Console](https://platform.claude.com/settings/workspaces) and use the **Rate limits** tab.
No. To set workspace rate limits, go to the [Rate limits](https://platform.claude.com/usage/limits) page in the Claude Console, select the workspace from the **Workspace** dropdown
+2 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
manage-claude/analytics-api
±changed
+14−2
apichanged
manage-claude/analytics-api
* **User activity:** per-user daily metrics across chat (conversations, messages, projects, files, artifacts), Claude Code (sessions, commits, pull requests, lines of code, tool ac
* **User activity:** per-user daily metrics across chat (conversations, messages, projects, files, artifacts), Claude Code (sessions, commits, pull requests, lines of code, tool ac
**Per-product metric blocks.** Per-product metric objects (for example, Office Agent or Cowork metrics on a user-activity record) are always present on every record. Organizations
**Chat and Cowork unified (beta).** Chat and Cowork unified brings Cowork's features into claude.ai chat. Most activity in Chat and Cowork unified is reported under the `chat_cowor
+14 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
build-with-claude/token-counting
±changed
+1−1
apichanged
build-with-claude/token-counting
Token counting is **free to use** but subject to requests per minute rate limits based on your [usage tier](https://platform.claude.com/docs/en/api/rate-limits#rate-limits). If you
Token counting is **free to use** but subject to requests per minute rate limits based on your [usage tier](https://platform.claude.com/docs/en/api/rate-limits#rate-limits). If you
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+1−1
apichanged
build-with-claude/claude-platform-on-aws
Organizations on Claude Platform on AWS can move to a higher usage tier automatically as they build a history of paid AWS Marketplace invoices. The self-service **Request rate limi
Organizations on Claude Platform on AWS can move to a higher usage tier automatically as they build a history of paid AWS Marketplace invoices. The self-service **Request tier incr
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/rate-limits
±changed
+9−9
apichanged
api/rate-limits
**[Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws):** The rate limits on this page apply to Claude Platform on AWS, but bill
**[Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws):** The rate limits on this page apply to Claude Platform on AWS, but bill
* Limits are set at the organization level. You can see your organization's tier and current limits on the [Rate limits](https://platform.claude.com/settings/limits) page in the [C
* Limits are set at the organization level. You can see your organization's tier and current limits on the [Rate limits](https://platform.claude.com/usage/limits) page in the [Clau
Rate limits are applied separately for each model; therefore you can use different models up to their respective limits simultaneously. You can check your current rate limits and b
+9 −9 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/overview
±changed
+1−1
apichanged
api/overview
You can view your rate limits on the [Rate limits](https://platform.claude.com/settings/limits) page and your spend limits on the [Billing](https://platform.claude.com/settings/bil
You can view your rate limits on the [Rate limits](https://platform.claude.com/usage/limits) page and your spend limits on the [Billing](https://platform.claude.com/settings/billin
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/models/retrieve
±changed
+31−0
apichanged
api/models/retrieve
- `deprecated_at: string or null`
RFC 3339 datetime string representing the time of the model's most recent deprecation. Populated for `deprecated` and `retired` models; `null` while the model is `active`.
format: date-time
+31 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/models/list
±changed
+43−0
apichanged
api/models/list
- `lifecycle: optional array of "active" or "deprecated" or "retired"`
Filter the list to models in any of the given lifecycle stages (`active`, `deprecated`, or `retired`). Up to 3 values. When omitted, the list contains the `active` and `deprecate
maxItems: 3
+43 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/models
±changed
+102−0
apichanged
api/models
- `lifecycle: optional array of "active" or "deprecated" or "retired"`
Filter the list to models in any of the given lifecycle stages (`active`, `deprecated`, or `retired`). Up to 3 values. When omitted, the list contains the `active` and `deprecate
maxItems: 3
+102 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/compliance/apps/chats/messages
±changed
+3−0
apichanged
api/compliance/apps/chats/messages
When the chat's `deleted_at` is set, `content` is an empty list and `files`,
`generated_files` and `artifacts` are null.
+3 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/compliance/apps/chats/delete
±changed
+5−0
apichanged
api/compliance/apps/chats/delete
A chat's remote sessions are deleted first. If that deletion cannot be
confirmed, the request returns a 503 with error code
`chat_delete_remote_sessions_unconfirmed` and leaves the chat unchanged.
You can retry the request.
+5 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/compliance/apps/chats
±changed
+5−0
apichanged
api/compliance/apps/chats
A chat's remote sessions are deleted first. If that deletion cannot be
confirmed, the request returns a 503 with error code
`chat_delete_remote_sessions_unconfirmed` and leaves the chat unchanged.
You can retry the request.
+5 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/compliance/apps
±changed
+5−0
apichanged
api/compliance/apps
A chat's remote sessions are deleted first. If that deletion cannot be
confirmed, the request returns a 503 with error code
`chat_delete_remote_sessions_unconfirmed` and leaves the chat unchanged.
You can retry the request.
+5 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/compliance
±changed
+5−0
apichanged
api/compliance
A chat's remote sessions are deleted first. If that deletion cannot be
confirmed, the request returns a 503 with error code
`chat_delete_remote_sessions_unconfirmed` and leaves the chat unchanged.
You can retry the request.
+5 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/spend_limits/list
±changed
+2−1
apichanged
api/beta/organization/spend_limits/list
is not creation order.
is not creation order. Listing Claude Console limits is in an early access
preview. To request access, contact your Anthropic account team.
+2 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/spend_limits/effective/list
±changed
+3−1
apichanged
api/beta/organization/spend_limits/effective/list
Paginates by member, so a member's periods never split across pages.
Paginates by member, so a member's periods never split across pages. Listing
Claude Console limits is in an early access preview. To request access,
contact your Anthropic account team.
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/spend_limits/effective
±changed
+3−1
apichanged
api/beta/organization/spend_limits/effective
Paginates by member, so a member's periods never split across pages.
Paginates by member, so a member's periods never split across pages. Listing
Claude Console limits is in an early access preview. To request access,
contact your Anthropic account team.
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/spend_limits
±changed
+5−2
apichanged
api/beta/organization/spend_limits
is not creation order.
is not creation order. Listing Claude Console limits is in an early access
preview. To request access, contact your Anthropic account team.
Paginates by member, so a member's periods never split across pages.
Paginates by member, so a member's periods never split across pages. Listing
+5 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/users/list
±changed
+166−1
apichanged
api/beta/organization/analytics/users/list
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
- `chat_cowork_unified_metrics: optional object or null`
+166 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/users
±changed
+166−1
apichanged
api/beta/organization/analytics/users
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
- `chat_cowork_unified_metrics: optional object or null`
+166 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/user_usage_report/list
±changed
+3−1
apichanged
api/beta/organization/analytics/user_usage_report/list
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/user_usage_report
±changed
+3−1
apichanged
api/beta/organization/analytics/user_usage_report
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/user_cost_report/list
±changed
+3−1
apichanged
api/beta/organization/analytics/user_cost_report/list
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/user_cost_report
±changed
+3−1
apichanged
api/beta/organization/analytics/user_cost_report
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/usage_report/list
±changed
+3−1
apichanged
api/beta/organization/analytics/usage_report/list
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/usage_report
±changed
+3−1
apichanged
api/beta/organization/analytics/usage_report
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/summaries/list
±changed
+31−1
apichanged
api/beta/organization/analytics/summaries/list
`next_page` is always null (`summaries` is a deprecated alias of `data`).
`next_page` is always null.
- `chat_cowork_unified_daily_active_user_count: optional number or null`
Number of users with activity in Chat and Cowork unified on the requested day. Omitted from the response on deployments that do not offer Chat and Cowork unified.
+31 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/summaries
±changed
+31−1
apichanged
api/beta/organization/analytics/summaries
`next_page` is always null (`summaries` is a deprecated alias of `data`).
`next_page` is always null.
- `chat_cowork_unified_daily_active_user_count: optional number or null`
Number of users with activity in Chat and Cowork unified on the requested day. Omitted from the response on deployments that do not offer Chat and Cowork unified.
+31 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/skills/list
±changed
+32−2
apichanged
api/beta/organization/analytics/skills/list
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
- `chat_cowork_unified_metrics: optional object or null`
Skill use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into chat conversations and Cowork sessions. A count is
+32 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/skills
±changed
+32−2
apichanged
api/beta/organization/analytics/skills
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
- `chat_cowork_unified_metrics: optional object or null`
Skill use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into chat conversations and Cowork sessions. A count is
+32 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/plugins/list
±changed
+14−3
apichanged
api/beta/organization/analytics/plugins/list
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. On this endpoint `product` takes the values `cl
Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. On this endpoint `product` takes the values `ch
- `chat_cowork_unified_metrics: optional object or null`
+14 −3 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/plugins
±changed
+14−3
apichanged
api/beta/organization/analytics/plugins
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. On this endpoint `product` takes the values `cl
Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. On this endpoint `product` takes the values `ch
- `chat_cowork_unified_metrics: optional object or null`
+14 −3 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/cost_report/list
±changed
+3−1
apichanged
api/beta/organization/analytics/cost_report/list
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/cost_report
±changed
+3−1
apichanged
api/beta/organization/analytics/cost_report
- `"chat_cowork_unified"`
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surfa
+3 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/connectors/list
±changed
+32−2
apichanged
api/beta/organization/analytics/connectors/list
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
- `chat_cowork_unified_metrics: optional object or null`
Connector use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into chat conversations and Cowork sessions. A count
+32 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/connectors
±changed
+32−2
apichanged
api/beta/organization/analytics/connectors
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
- `chat_cowork_unified_metrics: optional object or null`
Connector use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into chat conversations and Cowork sessions. A count
+32 −2 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/artifacts/list
±changed
+3−3
apichanged
api/beta/organization/analytics/artifacts/list
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Dimensions to break results out by: `product`, `user_id` and/or `rbac_group_id`. The ungrouped artifact-type cube is finite and returned in full; grouped queries multiply the cub
Dimensions to break results out by: `product`, `user_id` and/or `rbac_group_id`. The ungrouped artifact-type cube is finite and returned in full; grouped queries multiply the cub
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
+3 −3 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/artifacts
±changed
+3−3
apichanged
api/beta/organization/analytics/artifacts
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint:
Dimensions to break results out by: `product`, `user_id` and/or `rbac_group_id`. The ungrouped artifact-type cube is finite and returned in full; grouped queries multiply the cub
Dimensions to break results out by: `product`, `user_id` and/or `rbac_group_id`. The ungrouped artifact-type cube is finite and returned in full; grouped queries multiply the cub
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
+3 −3 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/apps/chat/projects/list
±changed
+1−1
apichanged
api/beta/organization/analytics/apps/chat/projects/list
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical C
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/apps/chat/projects
±changed
+1−1
apichanged
api/beta/organization/analytics/apps/chat/projects
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical C
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/apps/chat
±changed
+1−1
apichanged
api/beta/organization/analytics/apps/chat
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical C
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics/apps
±changed
+1−1
apichanged
api/beta/organization/analytics/apps
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical C
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization/analytics
±changed
+680−36
apichanged
api/beta/organization/analytics
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, or `office_agent` (the canonical Cost & Usage product naming; an `office_agent` row's per-sur
Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical C
### Beta Analytics Chat Cowork Unified Chat Metrics
- `BetaAnalyticsChatCoworkUnifiedChatMetrics object`
+680 −36 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/organization
±changed
+296−19
apichanged
api/beta/organization
`next_page` is always null (`summaries` is a deprecated alias of `data`).
`next_page` is always null.
- `chat_cowork_unified_daily_active_user_count: optional number or null`
Number of users with activity in Chat and Cowork unified on the requested day. Omitted from the response on deployments that do not offer Chat and Cowork unified.
+296 −19 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/models/retrieve
±changed
+31−0
apichanged
api/beta/models/retrieve
- `deprecated_at: string or null`
RFC 3339 datetime string representing the time of the model's most recent deprecation. Populated for `deprecated` and `retired` models; `null` while the model is `active`.
format: date-time
+31 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/models/list
±changed
+43−0
apichanged
api/beta/models/list
- `lifecycle: optional array of "active" or "deprecated" or "retired"`
Filter the list to models in any of the given lifecycle stages (`active`, `deprecated`, or `retired`). Up to 3 values. When omitted, the list contains the `active` and `deprecate
maxItems: 3
+43 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta/models
±changed
+102−0
apichanged
api/beta/models
- `lifecycle: optional array of "active" or "deprecated" or "retired"`
Filter the list to models in any of the given lifecycle stages (`active`, `deprecated`, or `retired`). Up to 3 values. When omitted, the list contains the `active` and `deprecate
maxItems: 3
+102 −0 lines
Recorded here 8 Oct 2026 08:37 UTC
api
api/beta
±changed
+370−19
apichanged
api/beta
- `lifecycle: optional array of "active" or "deprecated" or "retired"`
Filter the list to models in any of the given lifecycle stages (`active`, `deprecated`, or `retired`). Up to 3 values. When omitted, the list contains the `active` and `deprecate
maxItems: 3
+370 −19 lines
Recorded here 8 Oct 2026 08:37 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/web-search-tool
To protect shared capacity, the Batches API throttles web search requests per organization, so large batches with many searches might take longer to complete. You can see your orga
To protect shared capacity, the Batches API throttles web search requests per organization, so large batches with many searches might take longer to complete. You can see your orga
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
about-claude/pricing
±changed
+1−1
apichanged
about-claude/pricing
Contact the sales team at [[email protected]](mailto:[email protected]) or through the [Claude Console](https://platform.claude.com/settings/limits) to discuss enterprise prici
Contact the sales team at [[email protected]](mailto:[email protected]) or through the [Claude Console](https://platform.claude.com/usage/limits) to discuss enterprise pricing
+1 −1 lines
Recorded here 8 Oct 2026 08:37 UTC
api
release-notes/system-prompts/claude-haiku-5-5
+new page
+173−0
apinew page
release-notes/system-prompts/claude-haiku-5-5
No line of the body moved in this read.
+173 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
release-notes/overview
±changed
+5−15
apichanged
release-notes/overview
### October 7, 2026
### October 7, 2026
+5 −15 lines
Recorded here 8 Oct 2026 02:07 UTC
api
models/haiku-5-5/whats-new-haiku-5-5
+new page
+53−0
apinew page
models/haiku-5-5/whats-new-haiku-5-5
No line of the body moved in this read.
+53 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
models/haiku-5-5/overview
+new page
+139−0
apinew page
models/haiku-5-5/overview
No line of the body moved in this read.
+139 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
models/haiku-5-5/migration-guide
+new page
+151−0
apinew page
models/haiku-5-5/migration-guide
No line of the body moved in this read.
+151 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
models/haiku-4-5/overview
±changed
+2−4
apichanged
models/haiku-4-5/overview
description: "Claude Haiku 4.5 reference: lifecycle status, model IDs on every platform, context window, output limits, pricing, and migration resources. Claude Haiku 5.5 is the cu
description: "Claude Haiku 4.5 reference: lifecycle status, model IDs on every platform, context window, output limits, pricing, and migration resources. Claude Haiku 4.5 is a lega
The fastest model with near-frontier intelligence
## How it compares
+2 −4 lines
Recorded here 8 Oct 2026 02:07 UTC
api
models/haiku-4-5/migration-guide
−removed
+0−91
apiremoved
models/haiku-4-5/migration-guide
No line of the body moved in this read.
+0 −91 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/sessions
±changed
+1−1
apichanged
managed-agents/sessions
Each event in `initial_events` is validated and persisted before the create response returns, in list order, with a server-assigned ID, exactly as if you had posted it to the [send
Each event in `initial_events` is validated and persisted before the create response returns, in list order, with a server-assigned ID, exactly as if you had posted it to the [send
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/session-operations
±changed
+4−4
apichanged
managed-agents/session-operations
Only the agent's `tools` and `mcp_servers` can change after a session is created. To run a session with `model`, `system`, or `skills` values other than the agent's, use [agent con
Only the agent's `tools` and `mcp_servers` can change after a session is created. To run a session with `model`, `system`, or `skills` values other than the agent's, use [agent con
The session must be `idle` to update the agent. To update the agent while the session is running, send a [`user.interrupt` event](https://platform.claude.com/docs/en/managed-agents
The session must be `idle` to update the agent. To update the agent while the session is running, send a [`user.interrupt` event](https://platform.claude.com/docs/en/managed-agents
Archive a session to prevent new events from being sent while preserving its history. A `running` session cannot be archived; to archive one, send a [`user.interrupt` event](https:
+4 −4 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/session-observability
+new page
+114−0
apinew page
managed-agents/session-observability
No line of the body moved in this read.
+114 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/self-hosted-sandboxes-operations
±changed
+6−6
apichanged
managed-agents/self-hosted-sandboxes-operations
| Symptom | Cause
| --------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------
| The worker log contains `the work item carried no sessions token` (in Go, the `ErrSessionMemoryNoToken` error) and the work item fails. | The work item's per-session `secret` did
| The worker log contains `something already exists at the memory store's path`. | A directory left over from a previous se
| The worker log contains `cannot create the memory store's folder` and `the worker host must make this mount path writable`. | The user the worker runs as cannot creat
+6 −6 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/self-hosted-sandboxes-custom-tools
±changed
+1−1
apichanged
managed-agents/self-hosted-sandboxes-custom-tools
The worker answers only the tools registered with it. If a tool is declared on the agent but no worker or client serves it, the session pauses with a `requires_action` stop reason.
The worker answers only the tools registered with it. If a tool is declared on the agent but no worker or client serves it, the session pauses with a `requires_action` stop reason.
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/reference
±changed
+4−4
apichanged
managed-agents/reference
| Type | Description
| ---------------- | -----------------------------------------------------------------------------------------------------------------------------------------------------------
| `system.message` | Append privileged system-level context that applies to the accompanying turn and all subsequent turns. Supported on Claude Fable 5.1, Claude Mythos 5.1, Cl
| Type | Description
| ---------------- | -----------------------------------------------------------------------------------------------------------------------------------------------------------
+4 −4 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/permission-policies
±changed
+20−2
apichanged
managed-agents/permission-policies
For example, a `bash` call paused under an `always_ask` policy appears on the stream as follows:
```json
{
"type": "agent.tool_use",
+20 −2 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/multiagent-orchestration
±changed
+1−1
apichanged
managed-agents/multiagent-orchestration
Each session thread has its own event stream at `/v1/sessions/{session_id}/threads/{thread_id}/stream`, and it accepts the same `event_deltas[]` parameter as the session-level stre
Each session thread has its own event stream at `/v1/sessions/{session_id}/threads/{thread_id}/stream`, and it accepts the same `event_deltas[]` parameter as the session-level stre
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/mcp-connector
±changed
+1−1
apichanged
managed-agents/mcp-connector
Session creation does not validate MCP connectivity or credentials. It does check each declared server's host against the environment's networking: with a `limited` environment, se
Session creation does not validate MCP connectivity or credentials. It does check each declared server's host against the environment's networking: with a `limited` environment, se
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/events-and-streaming
±changed
+1050−1927
apichanged
managed-agents/events-and-streaming
Communication with Claude Managed Agents is event-based. You send user events to the agent, and receive agent and session events back to track status.
Communication with Claude Managed Agents is event-based. You open a stream to follow a session, send events to direct it, and answer it when it pauses for input.
Events flow in two directions.
* **User events** and **system events** are what you send to the agent: `user.*` events start a session and steer it as it progresses; `system.message` appends system-level context
+1050 −1927 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/event-deltas
+new page
+889−0
apinew page
managed-agents/event-deltas
No line of the body moved in this read.
+889 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/dreams
±changed
+6−6
apichanged
managed-agents/dreams
Dreaming 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`, `claude
Dreaming 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`, `clau
| Limit | Value |
| --------------------- | --------------------------------------------------------------------------------------------------------------- |
| Sessions per dream | 100 |
+6 −6 lines
Recorded here 8 Oct 2026 02:07 UTC
api
managed-agents/budgets
±changed
+1−1
apichanged
managed-agents/budgets
To read usage from the stream and the session object, see [Tracking usage](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#tracking-usage).
To read usage from the stream and the session object, see [Track usage](https://platform.claude.com/docs/en/managed-agents/session-observability#track-usage).
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-haiku-5-5
+new page
+133−0
apinew page
build-with-claude/prompt-engineering/prompting-claude-haiku-5-5
No line of the body moved in this read.
+133 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
build-with-claude/prompt-caching
±changed
+24−24
apichanged
build-with-claude/prompt-caching
| Model | Base input tokens | 5m cache writes | 1h c
| :------------------------------------------------------------------------------------------------------------------------------------ | :---------------- | :-------------- | :---
| Claude Fable 5.1 | $10 / MTok | $12.50 / MTok | $20
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok | $20
| Claude Fable 5 | $10 / MTok | $12.50 / MTok | $20
+24 −24 lines
Recorded here 8 Oct 2026 02:07 UTC
api
build-with-claude/preserved-thinking
±changed
+1−1
apichanged
build-with-claude/preserved-thinking
* **A conversation that moves down to an earlier model loses Claude Fable 5.1's reasoning for that request.** This happens when a router sends a turn to a cheaper model, after a [c
* **A conversation that moves down to an earlier model loses Claude Fable 5.1's reasoning for that request.** This occurs when a router sends a turn to a cheaper model, after a [cl
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+0−1
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
| Claude Haiku 3.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | `anthropic.claude-3-5-haiku-20241022-v1:0` | No | Yes | No | No
+0 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.