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
146 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
69 changed this week · last read 24 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
7 Oct 2026
209 pages
+3198 −2398 lines
api
models/mythos-5/overview
±changed
+1−1
apichanged
models/mythos-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/mythos-5-1/overview
±changed
+1−1
apichanged
models/mythos-5-1/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/haiku-4-5/overview
±changed
+1−1
apichanged
models/haiku-4-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/fable-5/overview
±changed
+1−1
apichanged
models/fable-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/fable-5-1/overview
±changed
+1−1
apichanged
models/fable-5-1/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
build-with-claude/prompt-caching
±changed
+2−2
apichanged
build-with-claude/prompt-caching
| Claude Sonnet 5.5 | $2 / MTok | $2.50 / MTok | $4 /
| Claude Sonnet 5.5 | $2 / MTok | $2.50 / MTok | $4 /
*<sup>2 Cache hits and refreshes on Claude Opus 5.5 are priced at 0.05x the base input price.</sup>*
*<sup>2 Cache hits and refreshes on Claude Opus 5.5 and Claude Sonnet 5.5 are priced at 0.05x the base input price.</sup>*
+2 −2 lines
Recorded here 7 Oct 2026 22:07 UTC
api
about-claude/pricing
±changed
+2−2
apichanged
about-claude/pricing
| Claude Sonnet 5.5 | $2 / MTok | $2.50 / MTok |
| Claude Sonnet 5.5 | $2 / MTok | $2.50 / MTok |
*<sup>2 Cache hits and refreshes on Claude Opus 5.5 are priced at 0.05x the base input price.</sup>*
*<sup>2 Cache hits and refreshes on Claude Opus 5.5 and Claude Sonnet 5.5 are priced at 0.05x the base input price.</sup>*
+2 −2 lines
Recorded here 7 Oct 2026 22:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 7 Oct 2026 21:37 UTC
claude-docs
third-party/claude-desktop/connectors-m365
±changed
+94−3
claude-docschanged
third-party/claude-desktop/connectors-m365
Both connectors provide the same read and search tools; they differ in data path and authentication. Write actions (sending mail, managing drafts and calendar events, working with
Both connectors provide the same read and search tools; they differ in data path and authentication. Write actions (sending mail, managing drafts and calendar events, working with
* **Remote connector**: an administrator approves the scopes on the Anthropic connector app. See [Control write actions on the remote connector](#control-write-actions-on-the-remot
* **Local connector**: you [grant write scopes](#grant-write-scopes) on your own app registration and list them in the connector's configuration
+94 −3 lines
Upstream edited 7 Oct 2026 21:35 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-code
mobile
±changed
+22−22
claude-codechanged
mobile
The Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) is a clie
The Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) is a clie
Tap **Code** in the app's navigation to reach your sessions, or open [claude.ai/code/new](https://claude.ai/code/new) on your phone to start a new Code session in the app. If you d
Tap **Code** in the app's navigation to reach your sessions, or open [claude.ai/code/new](https://claude.ai/code/new) on your phone to start a new Code session in the app. If you d
| [Cloud sessions](/docs/en/claude-code-on-the-web.md) | A session on cloud infrastructure, Anthropic-managed by default | Your repository is on GitHub and the task should keep run
+22 −22 lines
Upstream edited 7 Oct 2026 21:23 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
mobile
±changed
+22−22
claude-codechanged
mobile
The Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) is a clie
The Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) is a clie
Tap **Code** in the app's navigation to reach your sessions, or open [claude.ai/code/new](https://claude.ai/code/new) on your phone to start a new Code session in the app. If you d
Tap **Code** in the app's navigation to reach your sessions, or open [claude.ai/code/new](https://claude.ai/code/new) on your phone to start a new Code session in the app. If you d
| [Cloud sessions](/docs/en/claude-code-on-the-web) | A session on cloud infrastructure, Anthropic-managed by default | Your repository is on GitHub and the task should keep runnin
+22 −22 lines
Upstream edited 7 Oct 2026 21:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
mobile
±changed
+15−17
claude-codechanged
mobile
<Note>
Claude Code doesn't have a separate mobile app: cloud sessions and Remote Control both live in the **Code** tab in the Claude app, and Dispatch is a task you message in the app.
</Note>
> [!NOTE]
>
+15 −17 lines
Upstream edited 7 Oct 2026 21:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
web-quickstart
±changed
+2−2
claude-codechanged
web-quickstart
| **[Permission modes](/docs/en/permission-modes)** | Accept edits, Plan, Auto | All modes in the terminal; see [Switch permission modes](/docs/en/permission-modes#switch-permissio
| **[Permission modes](/docs/en/permission-modes)** | Accept edits, Plan, Auto | All modes in the terminal; see [Switch permission modes](/docs/en/permission-modes#switch-permissio
The mode dropdown next to the input shows the mode the session will run in:
The [permission mode control](/docs/en/permission-modes#switch-permission-modes) shows the permission mode the session will run in:
+2 −2 lines
Upstream edited 7 Oct 2026 21:23 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-code
permission-modes
±changed
+2−2
claude-codechanged
permission-modes
Use the mode dropdown next to the prompt box on [claude.ai/code](https://claude.ai/code) or in the mobile app. Permission prompts appear in claude.ai for approval. Which modes
On [claude.ai/code](https://claude.ai/code), use the mode dropdown next to the prompt box. In the mobile app, tap the **+** button in the prompt box, then **Permission**. Cloud
* **[Remote Control](/docs/en/remote-control) sessions** on your local machine: Manual, Accept edits, and Plan for a session you started yourself, and you can't select Auto or
* **[Remote Control](/docs/en/remote-control) sessions** on your local machine: Manual, Accept edits, Plan, and Auto for a session you started yourself, and you can't select By
+2 −2 lines
Upstream edited 7 Oct 2026 21:23 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-code
mobile
±changed
+1−1
claude-codechanged
mobile
* **Permission modes**: cloud sessions offer Accept edits, Plan, and Auto in the mode dropdown, and Remote Control sessions offer Manual, Accept edits, and Plan. You can't select B
* **Permission modes**: cloud sessions offer Accept edits, Plan, and Auto, and Remote Control sessions offer Manual, Accept edits, Plan, and Auto. You can't select Bypass permissio
+1 −1 lines
Upstream edited 7 Oct 2026 21:23 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+1−1
claude-docschanged
third-party/claude-desktop/telemetry
For collector authentication headers, extra resource attributes, and the log level of the desktop application's own event stream, see [`otlpHeaders`, `otlpResourceAttributes`, and
For collector authentication headers, extra resource attributes, and the log level of the desktop application's own event stream, see [`otlpHeaders`, `otlpResourceAttributes`, and
+1 −1 lines
Upstream edited 7 Oct 2026 21:09 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-docs
third-party/claude-desktop/ssh-remote-sessions
±changed
+25−1
claude-docschanged
third-party/claude-desktop/ssh-remote-sessions
* `coworkEgressAllowedHosts`, as Claude Code managed settings. The network and filesystem sandbox it produces with `allowedWorkspaceFolders` depends on the host having Claude Code'
* `coworkEgressAllowedHosts`, as Claude Code managed settings. The network and filesystem sandbox it produces with `allowedWorkspaceFolders` depends on the host having Claude Code'
### Sandbox status on the remote host
+25 −1 lines
Upstream edited 7 Oct 2026 21:09 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-docs
third-party/claude-desktop/code
±changed
+1−1
claude-docschanged
third-party/claude-desktop/code
The network and filesystem sandboxes apply on macOS, and on Linux devices and [SSH hosts](/docs/third-party/claude-desktop/ssh-remote-sessions#managed-configuration-on-the-remote-h
The network and filesystem sandboxes apply on macOS, and on Linux devices and [SSH hosts](/docs/third-party/claude-desktop/ssh-remote-sessions#managed-configuration-on-the-remote-h
+1 −1 lines
Upstream edited 7 Oct 2026 21:09 UTC Recorded here 7 Oct 2026 21:37 UTC
claude-code
deep-links
±changed
+5−5
claude-codechanged
deep-links
To prevent registration entirely, set [`disableDeepLinkRegistration`](/docs/en/settings-reference#disabledeeplinkregistration) to `"disable"` in `settings.json`. To enforce this ac
To prevent registration entirely, set [`disableDeepLinkRegistration`](https://code.claude.com/docs/en/settings-reference#disabledeeplinkregistration) to `"disable"` in `settings.js
The VS Code extension registers its own handler at `vscode://anthropic.claude-code/open`, which opens a Claude Code editor tab rather than a terminal window. See [Launch a VS Code
The VS Code extension registers its own handler at `vscode://anthropic.claude-code/open`, which opens a Claude Code editor tab rather than a terminal window. See [Launch a VS Code
Claude Desktop handles its own `claude://` links. To open a Desktop session on a remote machine over SSH, see [Open an SSH session from a link](/docs/en/desktop.md#open-an-ssh-sess
+5 −5 lines
Upstream edited 7 Oct 2026 20:25 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
deep-links
±changed
+5−5
claude-codechanged
deep-links
To prevent registration entirely, set [`disableDeepLinkRegistration`](/docs/en/settings-reference#disabledeeplinkregistration) to `"disable"` in `settings.json`. To enforce this ac
To prevent registration entirely, set [`disableDeepLinkRegistration`](/docs/en/settings-reference#disabledeeplinkregistration) to `"disable"` in `settings.json`. To enforce this ac
The VS Code extension registers its own handler at `vscode://anthropic.claude-code/open`, which opens a Claude Code editor tab rather than a terminal window. See [Launch a VS Code
The VS Code extension registers its own handler at `vscode://anthropic.claude-code/open`, which opens a Claude Code editor tab rather than a terminal window. See [Launch a VS Code
Claude Desktop handles its own `claude://` links. To open a Desktop session on a remote machine over SSH, see [Open an SSH session from a link](/docs/en/desktop#open-an-ssh-session
+5 −5 lines
Upstream edited 7 Oct 2026 20:25 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
deep-links
±changed
+25−27
claude-codechanged
deep-links
<Tabs>
<Tab title="macOS">
The built-in `open` command passes the URL to the registered `claude-cli://` handler:
**macOS**
```bash theme={null}
+25 −27 lines
Upstream edited 7 Oct 2026 20:25 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
desktop
±changed
+53−4
claude-codechanged
desktop
The integrated terminal lets you run commands alongside your session without switching to another app. Click **Terminal** in the session's title bar or press **Ctrl+\`** on macOS o
The integrated terminal lets you run commands alongside your session without switching to another app. Click **Terminal** in the session's title bar or press **Ctrl+\`** on macOS o
#### Open an SSH session from a link
A `claude://code/new` link opens Desktop's new-session page, and it can name an SSH connection. Put such a link in a runbook, dashboard, or wiki page to open Desktop set up for the
+53 −4 lines
Upstream edited 7 Oct 2026 20:25 UTC Recorded here 7 Oct 2026 20:37 UTC
claude-code
deep-links
±changed
+5−1
claude-codechanged
deep-links
To prevent registration entirely, set [`disableDeepLinkRegistration`](/docs/en/settings-reference#disabledeeplinkregistration) to `"disable"` in `settings.json`. To enforce this ac
To prevent registration entirely, set [`disableDeepLinkRegistration`](/docs/en/settings-reference#disabledeeplinkregistration) to `"disable"` in `settings.json`. To enforce this ac
## Open a Claude Desktop session on an SSH connection
+5 −1 lines
Upstream edited 7 Oct 2026 20:25 UTC Recorded here 7 Oct 2026 20:37 UTC
claude-code
admin-setup
±changed
+1−1
claude-codechanged
admin-setup
If a device still refuses WSL sessions, open **Help > Troubleshooting > Show Logs in Explorer** in Claude Desktop on that device, which saves a copy of its log folder to Downloads.
If a device still refuses WSL sessions, open **Help > Troubleshooting > Show Logs in File Explorer** in Claude Desktop on that device, which saves a copy of its log folder to Downl
+1 −1 lines
Upstream edited 7 Oct 2026 20:25 UTC Recorded here 7 Oct 2026 20:37 UTC
claude-code
agent-sdk/typescript
±changed
+3−0
claude-codechanged
agent-sdk/typescript
subagent_type?: string;
`subagent_type` names the subagent type on entries whose [`task_type`](#sdktaskstartedmessage) is `"local_agent"`, such as `general-purpose` or a custom subagent's name. The field
+3 −0 lines
Upstream edited 7 Oct 2026 20:07 UTC Recorded here 7 Oct 2026 20:37 UTC
claude-code
skills
±changed
+8−3
claude-codechanged
skills
In your terminal, Claude Code syncs those skills in sessions where you sign in with your claude.ai account. When the session starts, Claude Code downloads your account's skills int
The sync never delays startup, because Claude waits for a skill's download only when it invokes that skill. A short [non-interactive](/docs/en/headless) run can therefore finish be
In your terminal, Claude Code syncs those skills in sessions where you sign in with your claude.ai account. When the session starts, Claude Code downloads your account's skills int
+8 −3 lines
Upstream edited 7 Oct 2026 19:55 UTC Recorded here 7 Oct 2026 20:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 7 Oct 2026 19:37 UTC
claude-code
claude-directory
±changed
+0−2
claude-codechanged
claude-directory
In a script, check the output rather than the exit status alone. A run that deletes everything in its plan ends with `Purged N item(s)`. Treat that line as the sign of success.
+0 −2 lines
Upstream edited 7 Oct 2026 19:25 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-code
claude-apps-gateway-config
±changed
+30−12
claude-codechanged
claude-apps-gateway-config
Claude Desktop follows [its own schedule](#claude-desktop-overlay).
Claude Desktop follows [its own schedule](#when-a-policy-change-reaches-claude-desktop).
The gateway derives much of the response from the matched policy's `cli` block and from top-level gateway config:
If you don't deploy Claude Desktop, leave `desktop` out of your policies entirely; the gateway then returns 404 from `/user/bootstrap` for every user.
+30 −12 lines
Upstream edited 7 Oct 2026 19:17 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
| `403` with `This GraphQL query is not enabled for this session` in a cloud session | [GitHub proxy](/docs/en/cloud-environments#github-proxy) |
| `403` with `GitHub GraphQL is not available from Claude Code sessions` in a cloud session | [GitHub proxy](/docs/en/cloud-environments#github-proxy) |
+1 −1 lines
Upstream edited 7 Oct 2026 19:16 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-code
cloud-environments
±changed
+5−7
claude-codechanged
cloud-environments
A network secret is an API key or token you store on a cloud environment so Claude can call that API from any session in the environment without seeing the key. Anthropic's agent p
A network secret is an API key or token you store on a cloud environment so Claude can call that API from any session in the environment without seeing the key. Anthropic's agent p
* **Repository scope**: GitHub API and release-asset requests reach only repositories attached to the session, so a setup script that downloads release assets from an unattached re
* **GraphQL restrictions**: the proxy serves only a pinned set of GraphQL operations for pull-request workflows. The proxy rejects everything else on the GraphQL endpoint with a 40
* **Repository scope**: the proxy serves GitHub API requests for the repositories attached to the session. An API request for another repository gets a 403 whose message starts wit
+5 −7 lines
Upstream edited 7 Oct 2026 19:16 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-docs
claude-science/troubleshooting
±changed
+13−1
claude-docschanged
claude-science/troubleshooting
> Fix errors you see while using Claude Science: being signed out, capacity retries, Agent Failed, environment setup, connectors, and updates.
> Fix errors you see while using Claude Science: being signed out, capacity retries, Agent Failed, environment setup, connectors, dictation, and updates.
## Dictation
You can dictate a message with the microphone button in the composer instead of typing it. The messages in this section appear on the microphone button when dictation can't start.
+13 −1 lines
Upstream edited 7 Oct 2026 19:13 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-code
vs-code
±changed
+15−0
claude-codechanged
vs-code
To run Claude Code inside a dev container, see [Development containers](/docs/en/devcontainer).
Sign-in, network, and launch errors have their own entries on the install troubleshooting and error reference pages. Find what you see in the table, then follow the link.
| What you see | Where to go |
+15 −0 lines
Upstream edited 7 Oct 2026 19:12 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-code
code-review
±changed
+1−1
claude-codechanged
code-review
Pass an [effort level](/docs/en/model-config#adjust-effort-level) to trade coverage for confidence. At `low` and `medium`, the review reports only the findings it's most confident
Pass an [effort level](/docs/en/model-config#adjust-effort-level) to trade coverage for confidence. At `low`, the review reports the findings it's most confident in, so you see few
+1 −1 lines
Upstream edited 7 Oct 2026 19:11 UTC Recorded here 7 Oct 2026 19:37 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
* When a subagent stops at its [`maxTurns`](#supported-frontmatter-fields) limit, Claude Code marks the returned output as partial. For subagents that return an agent ID, Claude Co
* When a subagent stops at its [`maxTurns`](#supported-frontmatter-fields) limit, Claude Code marks the returned output as partial, and Claude can resume the subagent to continue i
+1 −1 lines
Upstream edited 7 Oct 2026 19:08 UTC Recorded here 7 Oct 2026 19:37 UTC
api
test-and-evaluate/strengthen-guardrails/reduce-latency
±changed
+70−37
apichanged
test-and-evaluate/strengthen-guardrails/reduce-latency
description: Reduce Claude's response latency by choosing a faster model like Claude Haiku 4.5, trimming prompt and output tokens, and streaming responses.
description: Reduce Claude's response latency by choosing a faster model like Claude Haiku 5.5, trimming prompt and output tokens, and streaming responses.
For speed-critical applications, **Claude Haiku 4.5** offers the fastest response times while maintaining high intelligence:
For speed-critical applications, **Claude Haiku 5.5** offers the fastest response times while maintaining high intelligence. [Effort](https://platform.claude.com/docs/en/build-with
# For time-sensitive applications, use Claude Haiku 4.5
+70 −37 lines
Recorded here 7 Oct 2026 19:07 UTC
api
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
±changed
+3−3
apichanged
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
* **Harmlessness screens:** Use a lightweight model like Claude Haiku 4.5 to pre-screen user input before it reaches your main conversation. Use [structured outputs](https://platfo
* **Harmlessness screens:** Use a lightweight model like Claude Haiku 5.5 to pre-screen user input before it reaches your main conversation. Use [structured outputs](https://platfo
* **Screen tool outputs before Claude acts on them.** Apply the same lightweight-model screening pattern you use for user input to the content your tools return. Run each tool, pas
* **Screen tool outputs before Claude acts on them.** Apply the same lightweight-model screening pattern you use for user input to the content your tools return. Run each tool, pas
If `injection_suspected` is `true`, return an error or a stripped summary in the `tool_result` block instead of the raw content, and consider surfacing the attempt to the user.
+3 −3 lines
Recorded here 7 Oct 2026 19:07 UTC
api
test-and-evaluate/develop-tests
±changed
+3−1
apichanged
test-and-evaluate/develop-tests
![Flowchart of prompt engineering: test cases, preliminary prompt, iterative testing and refinement, final validation, ship](https://platform.claude.com/docs/images/how-to-prompt-e
<Frame>
![Flowchart of prompt engineering: test cases, preliminary prompt, iterative testing and refinement, final validation, ship](https://platform.claude.com/docs/images/how-to-prompt
</Frame>
+3 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
resources/overview
±changed
+4−0
apichanged
resources/overview
<Card title="Claude Haiku 5.5 System Card" icon="file" href="https://www.anthropic.com/document/claude-haiku-5-5-system-card">
Detailed documentation of Claude Haiku 5.5.
</Card>
+4 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
release-notes/system-prompts/overview
±changed
+2−0
apichanged
release-notes/system-prompts/overview
<Card id="claude-haiku-5-5" title="Claude Haiku 5.5" icon="file" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-haiku-5-5" />
+2 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
release-notes/overview
±changed
+30−0
apichanged
release-notes/overview
### October 8, 2026
* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) chat endpoints now also return chats from the unified Claude experience, in beta for Claude
+30 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/sonnet-5/overview
±changed
+8−8
apichanged
models/sonnet-5/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/sonnet-5-5/whats-new-sonnet-5-5
±changed
+1−1
apichanged
models/sonnet-5-5/whats-new-sonnet-5-5
Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, including prompt caching and batch processing rates. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricin
Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Pricing](https
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/sonnet-5-5/overview
±changed
+7−7
apichanged
models/sonnet-5-5/overview
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowl
| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :----
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2
| **Claude Sonnet 5.5** (this model) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2
+7 −7 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/sonnet-5-5/migration-guide
±changed
+1−1
apichanged
models/sonnet-5-5/migration-guide
Claude Sonnet 5.5 has the same prices as Claude Sonnet 5. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits,
Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/sonnet-4-6/overview
±changed
+8−8
apichanged
models/sonnet-4-6/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Know
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :----------------------------- | :------------- | :---
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun
| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/sonnet-4-5/overview
±changed
+8−8
apichanged
models/sonnet-4-5/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/overview
±changed
+25−21
apichanged
models/overview
| Feature | Claude Fable 5.1
| :-------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------
| Description | For demanding reasoning and long-horizon agentic work
| Model page | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-
| Comparative latency | Slower
+25 −21 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/opus-5/overview
±changed
+8−8
apichanged
models/opus-5/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
| **Claude Opus 5** (this model) | 1M | 128K | $5 / $25 | Adaptive | `high` | May 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/opus-5-5/overview
±changed
+7−7
apichanged
models/opus-5-5/overview
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Kno
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun
| **Claude Opus 5.5** (this model) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun
| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun
+7 −7 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/opus-4-8/overview
±changed
+8−8
apichanged
models/opus-4-8/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
| **Claude Opus 4.8** (this model) | 1M | 128K | $5 / $25 | Adaptive | `high` | Jan 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/opus-4-7/overview
±changed
+8−8
apichanged
models/opus-4-7/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
| **Claude Opus 4.7** (this model) | 1M | 128K | $5 / $25 | Adaptive | `high` | Jan 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/opus-4-6/overview
±changed
+8−8
apichanged
models/opus-4-6/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Know
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :----------------------------- | :------------- | :---
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun
| **Claude Opus 4.6** (this model) | 1M | 128K | $5 / $25 | Adaptive (extended deprecated) | `high` | May
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/opus-4-5/overview
±changed
+8−8
apichanged
models/opus-4-5/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
| **Claude Opus 4.5** (this model) | 200K | 64K | $5 / $25 | Extended | `high` | May 2025
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/mythos-5/overview
±changed
+8−8
apichanged
models/mythos-5/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| **Claude Mythos 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/mythos-5-1/overview
±changed
+8−8
apichanged
models/mythos-5-1/overview
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Kno
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun
| **Claude Mythos 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/haiku-4-5/overview
±changed
+23−14
apichanged
models/haiku-4-5/overview
description: "Claude Haiku 4.5 at a glance: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for build
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
**Latest.** Released October 15, 2025.
**Legacy.** Released October 15, 2025.
+23 −14 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/fable-5/overview
±changed
+8−8
apichanged
models/fable-5/overview
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cuto
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :-------------
| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026
| **Claude Fable 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026
+8 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
models/fable-5-1/overview
±changed
+7−7
apichanged
models/fable-5-1/overview
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Kno
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--
| **Claude Fable 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun
| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun
| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun
+7 −7 lines
Recorded here 7 Oct 2026 19:07 UTC
api
managed-agents/self-hosted-sandboxes-workers
±changed
+1−1
apichanged
managed-agents/self-hosted-sandboxes-workers
ARG ANT_VERSION=1.38.0
ARG ANT_VERSION=1.39.0
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
managed-agents/reference
±changed
+3−3
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
| ---------------- | -----------------------------------------------------------------------------------------------------------------------------------------------------------
+3 −3 lines
Recorded here 7 Oct 2026 19:07 UTC
api
managed-agents/quickstart
±changed
+2−2
apichanged
managed-agents/quickstart
VERSION=1.38.0
VERSION=1.39.0
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
+2 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
managed-agents/events-and-streaming
±changed
+1−1
apichanged
managed-agents/events-and-streaming
`system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Sonnet 5.5. If
`system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Sonnet 5.5, and Cla
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+35−17
apichanged
manage-claude/inference-hooks-endpoint
Host your AI security server where Anthropic can reach it: an `https://` URL on port 443, on a publicly routable host (private, loopback, and carrier-grade NAT ranges are refused a
Host your AI security server where Anthropic can reach it: an `https://` URL on port 443, on a publicly routable host (private, loopback, and carrier-grade NAT ranges are refused a
| Block `type` | Fields
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------
| `text` | `text`: the text content.
+35 −17 lines
Recorded here 7 Oct 2026 19:07 UTC
api
manage-claude/inference-hooks-configuration
±changed
+1−1
apichanged
manage-claude/inference-hooks-configuration
Inference hooks activity is recorded in your organization's [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed): configuration changes, deni
Inference hooks activity is recorded in your organization's [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed): configuration changes, deni
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
manage-claude/inference-hooks
±changed
+3−1
apichanged
manage-claude/inference-hooks
 also deletes the sessions in the cloud that were st
+4 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
intro
±changed
+1−1
apichanged
intro
* [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (`claude-haiku-4-5`) — *The fastest model with near-frontier intelligence* — Fastest · Lowest co
* [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) (`claude-haiku-5-5`) — New — *For high-volume, latency-sensitive tasks such as classification, e
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
home
±changed
+1−1
apichanged
home
* [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (`claude-haiku-4-5`) — *The fastest model with near-frontier intelligence* — Fastest · Lowes
* [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) (`claude-haiku-5-5`) — New — *For high-volume, latency-sensitive tasks such as classificatio
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
get-started
±changed
+2−2
apichanged
get-started
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
<version>2.68.0</version>
<version>2.69.0</version>
+2 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
cli-sdks-libraries/sdks/typescript
±changed
+1−1
apichanged
cli-sdks-libraries/sdks/typescript
For more details on tool use, see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
For more details on tool use, see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). To run the browser use tool or the computer use to
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
cli-sdks-libraries/sdks/python
±changed
+2−0
apichanged
cli-sdks-libraries/sdks/python
To run the browser use tool or the computer use tool with this SDK, see [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-u
+2 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
cli-sdks-libraries/sdks/java
±changed
+2−2
apichanged
cli-sdks-libraries/sdks/java
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
<version>2.68.0</version>
<version>2.69.0</version>
+2 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
cli-sdks-libraries/cli/quickstart
±changed
+1−1
apichanged
cli-sdks-libraries/cli/quickstart
VERSION=1.38.0
VERSION=1.39.0
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
claude_api_primer
±changed
+3−1
apichanged
claude_api_primer
For fast, cost-effective tasks: Claude Haiku 4.5: claude-haiku-4-5-20251001
For fast, cost-effective tasks: Claude Haiku 5.5: claude-haiku-5-5
Previous Haiku model: Claude Haiku 4.5: claude-haiku-4-5-20251001
* Claude Haiku 5.5 (`claude-haiku-5-5`, adaptive thinking only, on by default)
+3 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/working-with-messages
±changed
+1−1
apichanged
build-with-claude/working-with-messages
On Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/mode
On Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/mode
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/thinking-troubleshooting
±changed
+10−5
apichanged
build-with-claude/thinking-troubleshooting
| Claude Haiku 5.5 | Adaptive only | On | `"enabled"`, `"disabled"`2 |
*2 Claude Opus 5 accepts `"disabled"` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below; combining it with effort `xhigh` or `max` returns a
*2 Claude Opus 5 and Claude Haiku 5.5 accept `"disabled"` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below; combining it with effort `xhigh
Models marked `Always on` cannot turn thinking off. Models marked `On` default to thinking. Claude Opus 5 and Claude Sonnet 5 accept `thinking: {type: "disabled"}`. On Claude Sonne
Models marked `Always on` cannot turn thinking off. Models marked `On` default to thinking. Claude Opus 5, Claude Sonnet 5, and Claude Haiku 5.5 accept `thinking: {type: "disabled"
+10 −5 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/thinking-steering-and-cost
±changed
+7−7
apichanged
build-with-claude/thinking-steering-and-cost
| Effort level | Thinking behavior |
| ------------------------------------- | ------------------------------------------------------------------------------------------------ |
| `max` | Claude thinks the most readily and at the greatest depth, with no constraint on thinking length. |
| `xhigh` | Claude thinks more readily and at greater depth than at `high`, suited to extended exploration. |
| `high` (default on most models) | Claude thinks on most requests that benefit from it. Provides deep reasoning on complex tasks. |
+7 −7 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/thinking
±changed
+16−8
apichanged
build-with-claude/thinking
| Claude Haiku 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | Thinking off at `high` effo
On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview, thinking is
On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, and Claude Haiku
Claude Haiku 5.5 also has thinking on by default and accepts `thinking: {type: "disabled"}` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or belo
+16 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/task-budgets
±changed
+2−0
apichanged
build-with-claude/task-budgets
- claude-haiku-5-5
| Claude Haiku 5.5 | Beta (set `task-budgets-2026-03-13` header) |
+2 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/structured-outputs
±changed
+1−0
apichanged
build-with-claude/structured-outputs
- claude-haiku-5-5
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/refusals-and-fallback
±changed
+4−4
apichanged
build-with-claude/refusals-and-fallback
description: How Claude Fable models, Claude Opus models, and Claude Sonnet 5.5 return classifier refusals and how to retry refused requests on a fallback model.
description: How Claude Fable models, Claude Opus models, Claude Sonnet 5.5, and Claude Haiku 5.5 return classifier refusals and how to retry refused requests on a fallback model.
Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5 include safety classifiers that can decline a request. When that happens, you receive a norm
Claude 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,
Server-side fallback is in beta on the Claude API. The `fallbacks` parameter is not supported on the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/b
+4 −4 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+9−4
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opu
This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opu
For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [Wha
For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [Wha
| Claude Haiku 5.5 | [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5) | Dif
+9 −4 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/prompt-caching
±changed
+15−9
apichanged
build-with-claude/prompt-caching
| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.10 / MTok | $0.125 / MTok | $0.2
| Claude Haiku 5.5 (for prompts over 100,000 tokens) | $0.50 / MTok | $0.625 / MTok | $1 /
* **Cache reads:** When cached content is used (10% of base input token price, or 2.5% on Claude Fable 5.1 and Claude Mythos 5.1, and 5% on Claude Opus 5.5)
* **Cache reads:** When cached content is used (10% of base input token price, or 2.5% on Claude Fable 5.1 and Claude Mythos 5.1, and 5% on Claude Opus 5.5 and Claude Sonnet 5.5)
* 512 tokens for Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Fa
+15 −9 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/preserved-thinking
±changed
+18−18
apichanged
build-with-claude/preserved-thinking
Claude Sonnet 5.5's thinking blocks are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs
Thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://
Also check your integration if it sends Claude Sonnet 5.5 thinking blocks from one account in a request made by a different account. See [Thinking blocks stay with the account that
Also check your integration if it sends Claude Sonnet 5.5 or Claude Haiku 5.5 thinking blocks from one account in a request made by a different account. See [Thinking blocks stay w
Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Google Cloud, from Claude Sonnet 5.5, but not from
+18 −18 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+5−5
apichanged
build-with-claude/mid-conversation-system-messages
This feature is available on Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://plat
This feature is available on Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://plat
A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level partway through a conver
A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level partway through a conver
The main use is a per-turn reminder in a tool loop. Append the reminder after the `tool_result` message each time you want the model to see it, and leave every earlier copy where i
+5 −5 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/handling-stop-reasons
±changed
+1−1
apichanged
build-with-claude/handling-stop-reasons
A refused request on Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5 can usually be served by retrying on another Claude model. [Refusals and
A refused request on Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, or Claude Haiku 5.5 can usually be served by retrying on another Claude mo
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/extended-thinking
±changed
+1−1
apichanged
build-with-claude/extended-thinking
* You use Claude 4.7 or a later model, such as Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5, or Claude Fable 5.1, where `type: "enabled"` returns a 400 error.
* You use Claude 4.7 or a later model, such as Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5, Claude Fable 5.1, or Claude Haiku 5.5, where `type: "enabled"` returns a 400 err
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/effort
±changed
+23−14
apichanged
build-with-claude/effort
- claude-haiku-5-5
Most Claude models default to high effort, spending as many tokens as needed for excellent results; Claude Opus 5.5 defaults to medium. You can raise the effort level to `max` for
Most Claude models default to high effort, spending as many tokens as needed for excellent results; Claude Opus 5.5 and Claude Haiku 5.5 default to medium. You can raise the effort
Setting `effort` to the model's default (`"medium"` on Claude Opus 5.5, `"high"` on other models) produces exactly the same behavior as omitting the `effort` parameter entirely.
Setting `effort` to the model's default (`"medium"` on Claude Opus 5.5 and Claude Haiku 5.5, `"high"` on other models) produces exactly the same behavior as omitting the `effort`
+23 −14 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/context-windows
±changed
+13−7
apichanged
build-with-claude/context-windows
<Frame>
</Frame>
Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude S
+13 −7 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/context-editing
±changed
+5−5
apichanged
build-with-claude/context-editing
| Haiku | (none) | All models through Claude Haiku 4.5 |
| Haiku | Claude Haiku 5.5 and later | Claude Haiku 4.5 and earlier |
On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, server-side context management never invalidates thinking blocks. Client-side edits to earlier turns can invalidate the
On Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, server-side context management never invalidates thinking blocks. Client-side edits to earlier turns
| Configuration option | Default | Description
+5 −5 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/compaction-threshold
±changed
+3−2
apichanged
build-with-claude/compaction-threshold
- claude-haiku-5-5
On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, thinking blocks from before a `compaction` block aren't carried forward, so the summary is all the m
On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, thinking blocks from before a `compaction` block aren't carried forward, so the su
On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, remove the `thinking` and `redacted_thinking` blocks from any assistant turn you re-insert after the compaction block,
On Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, remove the `thinking` and `redacted_thinking` blocks from any assistant turn you re-insert after the
+3 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/compaction-thinking-blocks
±changed
+1−0
apichanged
build-with-claude/compaction-thinking-blocks
- claude-haiku-5-5
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/compaction-on-demand
±changed
+1−0
apichanged
build-with-claude/compaction-on-demand
- claude-haiku-5-5
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/compaction-keep-recent-turns
±changed
+1−0
apichanged
build-with-claude/compaction-keep-recent-turns
- claude-haiku-5-5
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/compaction-background
±changed
+1−0
apichanged
build-with-claude/compaction-background
- claude-haiku-5-5
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+5−4
apichanged
build-with-claude/claude-platform-on-aws
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java-aws:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-aws:2.69.0")
<version>2.68.0</version>
+5 −4 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+6−5
apichanged
build-with-claude/claude-on-vertex-ai
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java-vertex:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-vertex:2.69.0")
<version>2.68.0</version>
+6 −5 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+7−7
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java-bedrock:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-bedrock:2.69.0")
<version>2.68.0</version>
+7 −7 lines
Recorded here 7 Oct 2026 19:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.