An entry is only as true as the day it was written.
Flags move on the server after a release ships. Anthropic's own notes land days later and their documentation later still. Sometimes an entry turns out to be wrong and gets corrected by hand. All of that is recorded against the entry it happened to, and this is the whole of it in the order it happened.
Nothing here replaces an entry. Every line links to the page its release published, still saying what that release said, because a correction is added and dated rather than swapped in.
| When | Entry | What happened |
|---|---|---|
v2.1.280opus-4-6 |
Documentation arrivedA small documentation edit on fast-mode touched a line naming opus-4-6 after this was published.
the line in the docsFast mode is not available on Claude Opus 4.6. Requests to `claude-opus-4-6` with `speed: "fast"` do not return an error: they run at standard speed and are billed at [standard rates](https://platform.claude.com/docs/en/about-claude/pricin… |
|
v2.1.280check |
Documentation arrivedA small documentation edit on fast-mode touched a line naming check after this was published.
the line in the docsFast mode is not available on Claude Opus 4.6. Requests to `claude-opus-4-6` with `speed: "fast"` do not return an error: they run at standard speed and are billed at [standard rates](https://platform.claude.com/docs/en/about-claude/pricin… |
|
v2.1.268claude-opus-4-6 |
Documentation arrivedA small documentation edit on fast-mode touched a line naming claude-opus-4-6 after this was published.
the line in the docsFast mode is not available on Claude Opus 4.6. Requests to `claude-opus-4-6` with `speed: "fast"` do not return an error: they run at standard speed and are billed at [standard rates](https://platform.claude.com/docs/en/about-claude/pricin… |
|
v2.1.280/fast |
Documentation arrivedA small documentation edit on fast-mode touched a line naming /fast after this was published.
the line in the docsFast mode is not available on Claude Opus 4.6. Requests to `claude-opus-4-6` with `speed: "fast"` do not return an error: they run at standard speed and are billed at [standard rates](https://platform.claude.com/docs/en/about-claude/pricin… |
|
v2.1.280opus-4-7 |
Documentation arrivedA small documentation edit on fast-mode touched a line naming opus-4-7 after this was published.
the line in the docsFast mode is not available on Claude Opus 4.7. Requests to `claude-opus-4-7` with `speed: "fast"` return an error; unlike Claude Opus 4.6 (see the following note), requests do not fall back to standard speed. The model itself remains avail… |
|
v2.1.268claude-opus-4-7 |
Documentation arrivedA small documentation edit on fast-mode touched a line naming claude-opus-4-7 after this was published.
the line in the docsFast mode is not available on Claude Opus 4.7. Requests to `claude-opus-4-7` with `speed: "fast"` return an error; unlike Claude Opus 4.6 (see the following note), requests do not fall back to standard speed. The model itself remains avail… |
|
v2.1.248claude-opus-4-7 |
Documentation arrivedA small documentation edit on fast-mode touched a line naming claude-opus-4-7 after this was published.
the line in the docsFast mode is not available on Claude Opus 4.7. Requests to `claude-opus-4-7` with `speed: "fast"` return an error; unlike Claude Opus 4.6 (see the following note), requests do not fall back to standard speed. The model itself remains avail… |
|
v2.1.280trigger |
Documentation arrivedAnthropic's documentation has since written up trigger, on context-editing.
the line in the docstrigger: |
|
v2.1.257mythos-5-1 |
Documentation arrivedA small documentation edit on claude-on-vertex-ai touched a line naming mythos-5-1 after this was published.
the line in the docs| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5-1` | |
|
v2.1.257claude-mythos-5-1 |
Documentation arrivedA small documentation edit on claude-on-vertex-ai touched a line naming claude-mythos-5-1 after this was published.
the line in the docs| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5-1` | |
|
v2.1.257claude-mythos-5-1 |
Documentation arrivedA small documentation edit on claude-on-vertex-ai touched a line naming claude-mythos-5-1 after this was published.
the line in the docs| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5-1` | |
|
v2.1.280/model |
Documentation arrivedA small documentation edit on Message Batches API touched a line naming /model after this was published.
the line in the docs* **Retired:** May still be available on other cloud platforms. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for more. |
|
v2.1.280/model |
Documentation arrivedA small documentation edit on Message Batches API touched a line naming /model after this was published.
the line in the docs* **Retired:** May still be available on other cloud platforms. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for more. |
|
v2.1.280/model |
Documentation arrivedA small documentation edit on Message Batches API touched a line naming /model after this was published.
the line in the docs* **Retired:** May still be available on other cloud platforms. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for more. |
|
v2.1.277is_active |
Documentation arrivedAnthropic's documentation has since written up is_active, on Compliance API.
the line in the docs- `is_active: optional boolean or null` |
|
v2.1.257Retry-After |
Documentation arrivedAnthropic's documentation has since written up Retry-After, on routines-fire.
the line in the docs| 429 | `rate_limit_error` | An hourly fire limit for the routine or the account has been reached. The response includes a `Retry-After` header indicating when the window resets. | |
|
v2.1.280output_config.effort |
Documentation arrivedAnthropic's documentation has since written up output_config.effort, on Events.
the line in the docsHow hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. |
|
v2.1.280End |
Documentation arrivedAnthropic's documentation has since written up End, on Events.
the line in the docs- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or BetaManagedAgentsSessionBudgetReached` |
|
v2.1.280End |
Documentation arrivedAnthropic's documentation has since written up End, on Events.
the line in the docs- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or BetaManagedAgentsSessionBudgetReached` |
|
v2.1.280End |
Documentation arrivedAnthropic's documentation has since written up End, on Events.
the line in the docs- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or BetaManagedAgentsSessionBudgetReached` |
|
v2.1.280sonnet-4-6 |
Documentation arrivedAnthropic's documentation has since written up sonnet-4-6, on Create a Message Batch.
the line in the docs- `"claude-sonnet-4-6"` |
|
v2.1.280opus-4-6 |
Documentation arrivedAnthropic's documentation has since written up opus-4-6, on Create a Message Batch.
the line in the docs- `"claude-opus-4-6"` |
|
v2.1.280opus-4-7 |
Documentation arrivedAnthropic's documentation has since written up opus-4-7, on Create a Message Batch.
the line in the docs- `"claude-opus-4-7"` |
|
v2.1.280Tab |
Documentation arrivedAnthropic's documentation has since written up Tab, on Create a Message Batch.
the line in the docs- `close_tab: optional BetaBrowserCloseTabConfig or null` |
|
v2.1.280max |
Documentation arrivedAnthropic's documentation has since written up max, on Create a Message Batch.
the line in the docsmaxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$ |
|
v2.1.280opus-4-8 |
Documentation arrivedAnthropic's documentation has since written up opus-4-8, on claude-api-skill.
the line in the docsFor the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Migrating to Claude Op… |
|
v2.1.280claude-opus-5-5 |
Documentation arrivedAnthropic's documentation has since written up claude-opus-5-5, on claude-api-skill.
the line in the docsWhen the scope is ambiguous (for example, a bare `/claude-api migrate to claude-opus-5-5`), the skill asks you to choose between the entire working directory, a specific subdirectory, or an explicit file list before editing any files. This… |
|
v2.1.280claude-opus-5-5 |
Documentation arrivedAnthropic's documentation has since written up claude-opus-5-5, on claude-api-skill.
the line in the docsWhen the scope is ambiguous (for example, a bare `/claude-api migrate to claude-opus-5-5`), the skill asks you to choose between the entire working directory, a specific subdirectory, or an explicit file list before editing any files. This… |
|
v2.1.280claude-opus-5-5 |
Documentation arrivedAnthropic's documentation has since written up claude-opus-5-5, on claude-api-skill.
the line in the docsWhen the scope is ambiguous (for example, a bare `/claude-api migrate to claude-opus-5-5`), the skill asks you to choose between the entire working directory, a specific subdirectory, or an explicit file list before editing any files. This… |
|
v2.1.280claude-opus-5-5 |
Documentation arrivedAnthropic's documentation has since written up claude-opus-5-5, on claude-api-skill.
the line in the docsWhen the scope is ambiguous (for example, a bare `/claude-api migrate to claude-opus-5-5`), the skill asks you to choose between the entire working directory, a specific subdirectory, or an explicit file list before editing any files. This… |
|
v2.1.280/model |
Documentation arrivedAnthropic's documentation has since written up /model, on pricing.
the line in the docs| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok | |
|
v2.1.280/model |
Documentation arrivedAnthropic's documentation has since written up /model, on pricing.
the line in the docs| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok | |
|
v2.1.280/model |
Documentation arrivedAnthropic's documentation has since written up /model, on pricing.
the line in the docs| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok | |
|
v2.1.280check |
Documentation arrivedAnthropic's documentation has since written up check, on Admin controls.
the line in the docs| Organization and access > User provisioning (SCIM directory sync, Enterprise) | Supported in Claude Science | Provisioning and deprovisioning act on claude.ai membership, which Anthropic checks on every request the app makes, so a deprov… |
|
v2.1.280user |
Documentation arrivedAnthropic's documentation has since written up user, on Admin controls.
the line in the docs* **Another company's product**: the company that makes the product usually builds and runs its connector, not Anthropic. Check the [Connectors Directory](/docs/connectors/directory) first. If the company offers a connector that isn't list… |
|
v2.1.280system |
Documentation arrivedAnthropic's documentation has since written up system, on Admin controls.
the line in the docs* **Your own systems and data**, such as an internal database or lab system: have your developers build a connector for it, then add its web address for everyone under **Organization settings > Connectors > Add > Custom** (see [Third party… |
|
v2.1.280preview |
Documentation arrivedAnthropic's documentation has since written up preview, on Admin controls.
the line in the docs* **Your own systems and data**, such as an internal database or lab system: have your developers build a connector for it, then add its web address for everyone under **Organization settings > Connectors > Add > Custom** (see [Third party… |
|
v2.1.275/desktop |
Documentation arrivedA small documentation edit on Connect Claude Desktop to Claude for Government touched a line naming /desktop after this was published.
the line in the docs* New and retired models appear in the model picker without any profile change; model access is controlled through [seat tiers](/docs/government/org-admin/seat-tiers). [Models in Claude Desktop](/docs/government/desktop/models) covers a mo… |
|
v2.1.260inferenceCredentialKind |
Documentation arrivedA small documentation edit on Deploy Claude Desktop on 3P with an LLM gateway touched a line naming inferenceCredentialKind after this was published.
the line in the docsFrom Claude Desktop 2.7032.0, `inferenceCredentialKind: "external-idp"` with [`inferenceIdpOidc`](/docs/third-party/claude-desktop/configuration#inferenceidpoidc) and `inferenceIdpAuthFlow`, the keys [Amazon Bedrock identity provider sign-… |
|
v2.1.275additionalContext |
Documentation arrivedAnthropic's documentation has since written up additionalContext, on Monitoring.
the line in the docs* `additional_context_chars`: Total characters of `additionalContext` returned by the matching hooks. Requires Claude Code v2.1.280 or later |
|
v2.1.277/mcp |
Documentation arrivedA small documentation edit on Environment variables touched a line naming /mcp after this was published.
the line in the docs| `CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH` | Maximum length in characters of each MCP tool description and each MCP server's instructions that Claude Code sends to the model (default: 2048). Claude Code [truncates longer text](/docs/en/mcp… |
|
v2.1.260proactive |
Documentation arrivedAnthropic's documentation has since written up proactive, on Output styles.
the line in the docs| [Proactive](#proactive) | Claude starts work right away and makes reasonable assumptions rather than asking about routine decisions | You want Claude to keep working through routine decisions, and you'll correct course if an assumption i… |
|
v2.1.277claude plugin validate |
Documentation arrivedAnthropic's documentation has since written up claude plugin validate, on Plugins reference.
the line in the docsIf you break any of these rules, the plugin fails to load. Run `claude plugin validate` to see which field breaks which rule. |
|
v2.1.271omitClaudeMd |
Documentation arrivedAnthropic's documentation has since written up omitClaudeMd, on Explore the .claude directory.
the line in the docs| `agents/*.md` | `name`, `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `maxTurns`, `skills`, `mcpServers`, `hooks`, `memory`, `background`, `effort`, `isolation`, `color`, `initialPrompt`, `omitClaudeMd`, `experime… |
|
v2.1.271omitClaudeMd |
Documentation arrivedAnthropic's documentation has since written up omitClaudeMd, on Explore the .claude directory.
the line in the docs| `agents/*.md` | `name`, `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `maxTurns`, `skills`, `mcpServers`, `hooks`, `memory`, `background`, `effort`, `isolation`, `color`, `initialPrompt`, `omitClaudeMd`, `experime… |
|
v2.1.271omitClaudeMd |
Documentation arrivedAnthropic's documentation has since written up omitClaudeMd, on Explore the .claude directory.
the line in the docs| `agents/*.md` | `name`, `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `maxTurns`, `skills`, `mcpServers`, `hooks`, `memory`, `background`, `effort`, `isolation`, `color`, `initialPrompt`, `omitClaudeMd`, `experime… |
|
v2.1.267CLAUDE_CODE_CHILD_SESSION |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_CHILD_SESSION, on Agent SDK reference - TypeScript.
the line in the docsIf your application runs prompts on its own schedule, declare each run so Claude Code frames the turn to the model as a scheduled task rather than as live input from the user. Start the session with `CLAUDE_CODE_HOST_SCHEDULED_RUN` set to … |
|
v2.1.278ANTHROPIC_BASE_URL |
Documentation arrivedA small documentation edit on Escalate hard decisions with the advisor tool touched a line naming ANTHROPIC_BASE_URL after this was published.
the line in the docs* **Anthropic API only**: the advisor is a server-executed tool. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry. Through an [LLM gateway](/docs/en/llm-gateway) configured … |
|
v2.1.277ANTHROPIC_BASE_URL |
Documentation arrivedA small documentation edit on Escalate hard decisions with the advisor tool touched a line naming ANTHROPIC_BASE_URL after this was published.
the line in the docs* **Anthropic API only**: the advisor is a server-executed tool. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry. Through an [LLM gateway](/docs/en/llm-gateway) configured … |
|
v2.1.267SubagentHandback |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming SubagentHandback after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |