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
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
ReadSourcePageWhatLines
1 Sep 2026
343 pages
+14764 −2864 lines
api
managed-agents/events-and-streaming
±changed
+1−1
apichanged
managed-agents/events-and-streaming
`system.message` is currently supported by Claude Opus 4.8, Claude Fable 5, Claude Mythos 5, and Claude Opus 5. If the agent's primary model does not support mid-conversation sys
`system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, and Claude Opus 4.8. If the agent's primary model does not s
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
managed-agents/dreams
±changed
+1−1
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`, `claude
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
manage-claude/cmek
±changed
+13−13
apichanged
manage-claude/cmek
| APIs | Tools and features |
| --------------------- | --------------------------------------------------------------------------------------------------- |
| Messages | Web search |
| Models | Web fetch |
| Files | Code execution |
+13 −13 lines
Recorded here 1 Sep 2026 18:08 UTC
api
manage-claude/api-and-data-retention
±changed
+4−4
apichanged
manage-claude/api-and-data-retention
* **Claude Fable 5 and Claude Mythos 5:** These models require 30-day data retention and are not available under ZDR. See [Model-specific data retention requirements](https://platf
* **Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5:** These models require 30-day data retention and are not available under ZDR unless expressly authoriz
Claude Fable 5 and Claude Mythos 5 are designated Covered Models (see the [Covered Models support article](https://support.claude.com/en/articles/15425695)) and require 30-day data
Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5 are designated Covered Models (see the [Covered Models support article](https://support.claude.com/en/artic
Organizations with a ZDR arrangement can make Claude Fable 5 and Claude Mythos 5 available in a specific workspace by enabling 30-day retention for that workspace only. Other works
+4 −4 lines
Recorded here 1 Sep 2026 18:08 UTC
api
intro
±changed
+2−2
apichanged
intro
**Claude Fable 5** - Next-generation intelligence for long-running agents. Read the [Claude Fable 5 and Claude Mythos 5 announcement](https://www.anthropic.com/news/claude-fable-
**Claude Fable 5.1** - For demanding reasoning and long-horizon agentic work. Read the [Claude Fable 5.1 announcement](https://www.anthropic.com/claude/fable/5-1).
**Claude Mythos 5** - Shares Claude Fable 5's capabilities without the safety classifiers. Available in limited release through [Project Glasswing](https://anthropic.com/glasswin
**Claude Mythos 5.1** - Offers Claude Fable 5.1's capabilities by invitation through [Project Glasswing](https://anthropic.com/glasswing).
+2 −2 lines
Recorded here 1 Sep 2026 18:08 UTC
api
home
±changed
+3−3
apichanged
home
* [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) (`claude-fable-5`) — *Next-generation intelligence for long-running agents* — Most capable · Res
* [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) (`claude-opus-5`) — New — *For complex agentic coding and enterprise work* — Complex projects · Ag
* [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) (`claude-fable-5-1`) — New — *For demanding reasoning and long-horizon agentic work* — Most
* [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) (`claude-opus-5`) — *For complex agentic coding and enterprise work* — Complex projects · Agents ·
<Card icon="graduation-cap" title="Courses" href="https://anthropic.skilljar.com/">
+3 −3 lines
Recorded here 1 Sep 2026 18:08 UTC
api
claude_api_primer
±changed
+4−1
apichanged
claude_api_primer
For complex agentic coding and enterprise work: Claude Opus 5: claude-opus-5
Recommended default for most work, including complex agentic coding: Claude Opus 5: claude-opus-5
Step up for the hardest long-running agentic and research tasks, at 2x Claude Opus 5 pricing: Claude Fable 5.1: claude-fable-5-1
On Claude Fable 5.1 and Claude Mythos 5.1, `any` and `tool` return a 400 error. Leave `tool_choice` at `auto` and set `"strict": true` on the tool definition to guarantee that any
+4 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/working-with-messages
±changed
+1−1
apichanged
build-with-claude/working-with-messages
On Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, and Claude Opus 5, you can include messages with `"role": "system"` after a user turn (subje
On Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, and Claude Opus 5, y
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/token-counting
±changed
+5−5
apichanged
build-with-claude/token-counting
All [active models](https://platform.claude.com/docs/en/models/overview) support token counting, including Claude Opus 5 and Claude Sonnet 5.
All [active models](https://platform.claude.com/docs/en/models/overview) support token counting.
## Token counts on Claude Fable 5 and Claude Mythos 5
Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7, which produces roughly 30 percent more tokens than models before Claude Opus 4.7 for the same
+5 −5 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/thinking-troubleshooting
±changed
+25−7
apichanged
build-with-claude/thinking-troubleshooting
## Configurations each model rejects
## Thinking support, defaults, and rejected configurations by model
Most thinking configuration errors are a mismatch between the `thinking.type` value in the request and what the model supports. On current models, thinking runs as `thinking: {type
Most thinking configuration errors are a mismatch between the `thinking.type` value in the request and what the model supports. On most models, thinking runs as `thinking: {type: "
| Claude Fable 5.1 | Adaptive only | Always on | `"enabled"`, `"disabled"` |
+25 −7 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/thinking
±changed
+504−37
apichanged
build-with-claude/thinking
You don't always see this text, and what you see is never the raw chain of thought: the text in a thinking block is a [summary of Claude's reasoning](https://platform.claude.com/do
You don't always see this text, and what you see is never the raw chain of thought: the text in a thinking block is a [summary of Claude's reasoning](https://platform.claude.com/do
On current models, thinking is on by default or one parameter away. Which configuration each model accepts, and what it defaults to, is listed in the [per-model configuration table
On Claude Opus 5, Claude Sonnet 5, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview, thinking is already on: no configuration needed. The first thing most developers need
+504 −37 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/task-budgets
±changed
+5−3
apichanged
build-with-claude/task-budgets
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`
The minimum accepted `task_budget.total` is model-specific; on every model that currently supports task budgets (see [Feature support](https://platform.claude.com/docs/en/build-wit
The minimum accepted `task_budget.total` is model-specific. On every model that supports task budgets (see [Feature support](https://platform.claude.com/docs/en/build-with-claude/t
* **[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking):** Task budgets include thinking tokens in the count, so adaptive thinking naturally scales
+5 −3 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/structured-outputs
±changed
+1−1
apichanged
build-with-claude/structured-outputs
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `clau
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `c
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/streaming
±changed
+2−2
apichanged
build-with-claude/streaming
1. `message_start`: contains a `Message` object with empty `content`.
1. `message_start`: contains a `Message` object with empty `content`. Under the [`thinking-binding-controls-2026-08-01`](https://platform.claude.com/docs/en/build-with-claude/think
When `display: "omitted"` is set on the thinking configuration, no `thinking_delta` events are sent. The thinking block opens, receives a single `signature_delta`, and closes. See
When `display: "omitted"` is set on the thinking configuration, no `thinking_delta` events are sent. The thinking block opens, receives a single `signature_delta`, and closes. With
+2 −2 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/refusals-and-fallback
±changed
+65−67
apichanged
build-with-claude/refusals-and-fallback
description: How Claude Fable 5 and Claude Opus 5 return classifier refusals and how to retry refused requests on a fallback model.
description: How Claude Fable and Claude Opus models return classifier refusals and how to retry refused requests on a fallback model.
Claude Fable 5 and Claude Opus 5 include safety classifiers that can decline a request. When that happens, you receive a normal response, not an error, with `stop_reason: "refusal"
Read this page when you build on Claude Fable 5 or Claude Opus 5 and want declined requests to fall through to another model automatically. It also applies when you have just seen
+65 −67 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+33−27
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
This is the reference for prompt engineering with Claude's latest models, including Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.
* **Model-specific guidance** first: where [Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5), [Claude Sonnet 5](ht
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, Claude Opus
+33 −27 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/prompt-caching
±changed
+40−35
apichanged
build-with-claude/prompt-caching
| Model | Base Input Tokens | 5m Cache Writes | 1h C
| ------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | --------------- | ----
| Claude Fable 5 | $10 / MTok | $12.50 / MTok | $20
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | $10 / MTok | $12.50 / MTok | $20
| Claude Opus 5 | $5 / MTok | $6.25 / MTok | $10
+40 −35 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/overview
±changed
+1−1
apichanged
build-with-claude/overview
\* **Structured outputs:** Your prompts and Claude's outputs are not stored. Only JSON schemas are cached, for up to 24 hours since last use. **Web search and web fetch:** ZDR-elig
\* **Structured outputs:** Your prompts and Claude's outputs are not stored. Only JSON schemas are cached, for up to 24 hours since last use. **Web search and web fetch:** ZDR-elig
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+357−11
apichanged
build-with-claude/mid-conversation-system-messages
This page covers two features: mid-conversation system messages, and [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-m
This feature is available on Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, and Claude Opus 5. No beta header is required for mid-conversati
Mid-conversation tool changes are in beta and require the `mid-conversation-tool-changes-2026-07-01` beta header. They are available on Claude Fable 5, Claude Mythos 5, Claude Op
+357 −11 lines
Recorded here 1 Sep 2026 18:08 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 or Claude Opus 5 can usually be served by retrying on another Claude model, and [Refusals and fallback](https://platform.claude.com/docs/en/buil
A refused request on Claude Fable 5.1, Claude Fable 5, or Claude Opus 5 can usually be served by retrying on another Claude model. [Refusals and fallback](https://platform.claude.c
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/files
±changed
+2−0
apichanged
build-with-claude/files
On the Claude API, supported image and video files that Claude produces with the code execution tool, including files created by skills, carry signed C2PA Content Credentials when
+2 −0 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/fallback-credit
±changed
+7−7
apichanged
build-with-claude/fallback-credit
description: Avoid paying the prompt-cache cost twice when you retry a refused Claude Fable 5 request on another model.
description: Avoid paying the prompt-cache cost twice when you retry a refused request on another model.
Prompt caches are per-model. When Claude Fable 5 declines a request and you retry on another model, the conversation prefix that was already cached for Claude Fable 5 must be writt
Prompt caches are per-model. When a model declines a request and you retry on another model, the conversation prefix already cached for the first model must be written into the new
Start from the refused request body. Set `model` to the fallback model and add the token as the top-level `fallback_credit_token` parameter. Pick the body shape from the table
+7 −7 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/extended-thinking
±changed
+1−1
apichanged
build-with-claude/extended-thinking
* You are moving to Claude Opus 4.7, Claude Opus 4.8, Claude Opus 5, Claude Sonnet 5, Claude Fable 5, or Claude Mythos 5, where `type: "enabled"` returns a 400 error.
* You are moving to Claude Opus 4.7, Claude Opus 4.8, Claude Opus 5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, or Claude Mythos 5, where `type: "enabled
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/effort
±changed
+399−115
apichanged
build-with-claude/effort
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `clau
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `c
The effort parameter lets you control how many tokens Claude spends when responding to requests. You can trade off between response thoroughness and token efficiency with a single
The effort parameter lets you control how many tokens Claude spends when responding to requests. You can trade off between response thoroughness and token efficiency with a single
## How effort works
+399 −115 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/context-windows
±changed
+4−6
apichanged
build-with-claude/context-windows
Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a 1M-token context window on the Claude API, Amazon Bedrock, Google Cl
Claude Fable 5 and Claude Mythos 5 (claude-fable-5 and claude-mythos-5) also have a 1M-token context window. A single request to any model with a 1M-token context window can genera
Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and [Cla
Whether thinking blocks from previous assistant turns stay in the context window depends on the model. On Claude Opus 4.5 and later Opus models, Claude Sonnet 4.6 and later Sonnet
+4 −6 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/context-editing
±changed
+11−8
apichanged
build-with-claude/context-editing
| Model class | Keep all prior thinking | Keep only the last turn's thinking |
| ----------- | --------------------------- | ----------------------------------- |
| Opus | Claude Opus 4.5 and later | Claude Opus 4.1 and earlier |
| Sonnet | Claude Sonnet 4.6 and later | Claude Sonnet 4.5 and earlier |
| Haiku | (none) | All models through Claude Haiku 4.5 |
+11 −8 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/compaction
±changed
+7−1
apichanged
build-with-claude/compaction
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `clau
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `c
On Claude Fable 5.1 and Claude Mythos 5.1, a request with custom `instructions` summarizes from the visible conversation only: earlier thinking blocks are not part of the summarize
+7 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+1−0
apichanged
build-with-claude/claude-platform-on-aws
| Claude Fable 5.1 | claude-fable-5-1 |
+1 −0 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+2−1
apichanged
build-with-claude/claude-on-vertex-ai
| Claude Fable 5.1 | claude-fable-5-1 |
Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.co
Claude Fable 5.1, Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://
+2 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+3−3
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
Claude Opus 5, Claude Sonnet 5, Claude Fable 5, Claude Opus 4.8, and Claude Opus 4.7 are reachable through `InvokeModel` on `bedrock-runtime`. These requests are served by the sa
Claude Fable 5.1, Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, and Claude Opus 4.7 are reachable through `InvokeModel` on `bedrock-runtime`. These requests ar
[Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available through the InvokeModel API for Claude Fabl
[Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available through the InvokeModel API for Claude Fabl
Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.co
+3 −3 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+3−2
apichanged
build-with-claude/claude-in-microsoft-foundry
This guide shows you how to set up and make API calls to Claude in Microsoft Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you access Claude in Microso
This guide shows you how to set up and make API calls to Claude in Microsoft Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you access Claude in Microso
Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.co
Claude Fable 5.1, Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://
| Claude Fable 5.1 | claude-fable-5-1 | | ✓ |
+3 −2 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+6−3
apichanged
build-with-claude/claude-in-amazon-bedrock
Amazon Bedrock sets access criteria for each Claude model individually. Claude Fable 5, Claude Opus 4.8, Claude Sonnet 5, Claude Opus 4.7, and Claude Haiku 4.5 are open to all Amaz
Amazon Bedrock sets access criteria for each Claude model individually. Claude Fable 5.1, Claude Fable 5, Claude Opus 4.8, Claude Sonnet 5, Claude Opus 4.7, and Claude Haiku 4.5 ar
| Claude Fable 5.1 | anthropic.claude-fable-5-1 | Open |
Use Claude Code 2.1.255 or later with Claude Fable 5.1 on Amazon Bedrock; run `claude update` to upgrade.
+6 −3 lines
Recorded here 1 Sep 2026 18:08 UTC
api
build-with-claude/batch-processing
±changed
+2−0
apichanged
build-with-claude/batch-processing
| Claude Fable 5.1 | $5 / MTok | $25 / MTok |
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | $5 / MTok | $25 / MTok |
+2 −0 lines
Recorded here 1 Sep 2026 18:08 UTC
api
api/service-tiers
±changed
+1−1
apichanged
api/service-tiers
Priority Tier is supported on all available Claude models except Claude Mythos 5, [Claude Mythos Preview](https://anthropic.com/glasswing), Claude Opus 5, and Claude Sonnet 5.
Priority Tier is supported on all available Claude models except Claude Fable 5.1, Claude Mythos 5.1, Claude Mythos 5, [Claude Mythos Preview](https://anthropic.com/glasswing), Cla
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
api/rate-limits
±changed
+22−20
apichanged
api/rate-limits
Claude Haiku 3.5 (marked with † in the following rate limit tables) also counts `cache_read_input_tokens` toward ITPM rate limits.
For all models without the † marker, cached input tokens do not count toward rate limits and are billed at a reduced rate (10% of base input token price). This means you can achi
Claude Haiku 3.5 (marked with footnote 4 in the following rate limit tables) also counts `cache_read_input_tokens` toward ITPM rate limits.
+22 −20 lines
Recorded here 1 Sep 2026 18:08 UTC
api
api/errors
±changed
+33−5
apichanged
api/errors
With tool use, every `thinking` and `redacted_thinking` block from the assistant turn must be passed back exactly as received, including blocks whose `thinking` field is empty. Pas
With tool use, every `thinking` and `redacted_thinking` block from the assistant turn must be passed back exactly as received, including blocks whose `thinking` field is empty. Pas
On Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), and [Claude Mythos Preview](https://anthropic.com/glasswing), thinking is always on. Sending `thinking: {"typ
On Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), and [Claude Mythos Preview](https://a
On Claude Fable 5 and Claude Mythos 5, the error message's own suggestion of `"thinking.type.enabled"` is also rejected. Omit the `thinking` parameter and the request runs with ada
+33 −5 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/web-fetch-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/web-fetch-tool
The latest web fetch tool version (`web_fetch_20260318`) supports **dynamic filtering** with Claude Fable 5, Claude Opus 4.8, Claude Mythos 5, [Claude Mythos Preview](https://anthr
The latest web fetch tool version (`web_fetch_20260318`) supports **dynamic filtering**: Claude can write and execute code to filter fetched content before it reaches the context w
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/tool-search-tool
±changed
+2−0
apichanged
agents-and-tools/tool-use/tool-search-tool
| Claude Fable 5.1 (claude-fable-5-1) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |
| Claude Mythos 5.1 (claude-mythos-5-1) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |
+2 −0 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/programmatic-tool-calling
±changed
+1−1
apichanged
agents-and-tools/tool-use/programmatic-tool-calling
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `c
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/parallel-tool-use
±changed
+7−1
apichanged
agents-and-tools/tool-use/parallel-tool-use
<Note>
**Claude Fable 5.1 in long agent loops**
Claude Fable 5.1 may issue fewer parallel tool calls than earlier models, most noticeably in long agent loops where the next reads are only implied (custom coding agents, bash an
</Note>
+7 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+11−16
apichanged
agents-and-tools/tool-use/define-tools
## Choosing a model
Use the latest Claude Opus model, Claude Opus 5, for complex tools and ambiguous queries; it handles multiple tools better and seeks clarification when needed.
+11 −16 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/computer-use-tool
±changed
+3−2
apichanged
agents-and-tools/tool-use/computer-use-tool
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`
* On Claude Fable 5.1, avoid pruning on the client: removing an earlier screenshot [invalidates every later thinking block](https://platform.claude.com/docs/en/build-with-claude/th
| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonne
| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Op
+3 −2 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+9−1
apichanged
agents-and-tools/tool-use/code-execution-tool
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `c
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-
### Content Credentials on generated files
On the Claude API, supported image and video files that Claude produces in the code execution sandbox carry [C2PA](https://c2pa.org/) Content Credentials when you download them thr
+9 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/browser-use-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/browser-use-tool
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`
- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+15−13
apichanged
agents-and-tools/tool-use/advisor-tool
Currently, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 advisors return the encrypted `advisor_redacted_result`. Every other advisor model in the [compatibility table](http
Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 advisors return the encrypted `advisor_redacted_result`. Every other advisor model in the
To force a consult on a specific request instead of nudging, set `tool_choice` to `{"type": "tool", "name": "advisor"}`, subject to the constraints in [Forcing tool use](https://pl
To force a consult on a specific request instead of nudging, set `tool_choice` to `{"type": "tool", "name": "advisor"}`, subject to the constraints in [Forcing tool use](https://pl
| Executor models | Advisor models
+15 −13 lines
Recorded here 1 Sep 2026 18:08 UTC
api
agents-and-tools/agent-skills/claude-api-skill
±changed
+3−3
apichanged
agents-and-tools/agent-skills/claude-api-skill
* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5](https://platform.claude.com
* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5](https://platform.claude.com
* **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.com/do
* **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.com/do
For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5/migration-gui
+3 −3 lines
Recorded here 1 Sep 2026 18:08 UTC
api
about-claude/pricing
±changed
+30−24
apichanged
about-claude/pricing
| Model | Base Input Tokens | 5m Cache Writes | 1h C
| ------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | --------------- | ----
| Claude Fable 5 | $10 / MTok | $12.50 / MTok | $20
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | $10 / MTok | $12.50 / MTok | $20
| Claude Opus 5 | $5 / MTok | $6.25 / MTok | $10
+30 −24 lines
Recorded here 1 Sep 2026 18:08 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+190−161
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
Each lever comes with measured results and the rule for when it pays. In Anthropic's measurements, prompt caching was the largest lever by a wide margin: it cut agent-loop cost by
Each lever comes with measured results and the rule for when it pays. In Anthropic's measurements, prompt caching was the largest lever by a wide margin: it cut agent-loop cost by
| Your situation | Do this
| ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------
| Any workload, any model | Turn on prompt caching and trim unneeded tokens; both are free
+190 −161 lines
Recorded here 1 Sep 2026 18:08 UTC
api
about-claude/models/choosing-a-model
±changed
+20−19
apichanged
about-claude/models/choosing-a-model
description: "Selecting the optimal Claude model for your application involves balancing three key considerations: capabilities, speed, and cost. This guide helps you make an infor
description: Choosing a Claude model means balancing capabilities, speed, and cost. This guide covers the questions to ask, two ways to pick a starting model, and how to test the c
* **Effort:** Recent Opus and Sonnet models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cos
Knowing these answers in advance will make narrowing down and deciding which model to use much easier.
+20 −19 lines
Recorded here 1 Sep 2026 18:08 UTC
api
about-claude/model-deprecations
±changed
+1−0
apichanged
about-claude/model-deprecations
| claude-fable-5-1 | Active | N/A | Not sooner than September 1, 2027 |
+1 −0 lines
Recorded here 1 Sep 2026 18:08 UTC
api
about-claude/additional-resources
±changed
+1−1
apichanged
about-claude/additional-resources
<Card title="Courses" icon="graduation-cap" href="https://anthropic.skilljar.com/">
<Card title="Courses" icon="graduation-cap" href="https://academy.claude.com/courses">
+1 −1 lines
Recorded here 1 Sep 2026 18:08 UTC
claude-docs
claude-tag/users/use-cases/create-artifacts
±changed
+13−1
claude-docschanged
claude-tag/users/use-cases/create-artifacts
> Claude Tag turns a Slack discussion into the artifact you name. See replies you can send, decision docs, status memos, filed tickets, hosted web pages, and a capture-channel patt
> Claude Tag turns a Slack discussion into the artifact you name. See replies you can send, decision docs, status memos, filed tickets, hosted web pages, page comments that reach C
### Comment on the page to ask for changes
After Claude publishes a page from a channel or a thread, it keeps watching that page for comments. Open the page, start a comment on the part you want changed, and send the commen
+13 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+1−1
claude-docschanged
claude-tag/concepts/security-and-data
A session can publish an artifact, a web page hosted on claude.ai with the link posted in the thread, and the page stays available after the sandbox is released. Anyone with access
A session can publish an artifact, a web page hosted on claude.ai with the link posted in the thread, and the page stays available after the sandbox is released. Anyone with access
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
zero-data-retention
±changed
+3−3
claude-codechanged
zero-data-retention
ZDR covers model inference calls made through Claude Code on Claude for Enterprise. When you use Claude Code in your terminal, the prompts you send and the responses Claude generat
ZDR covers model inference calls made through Claude Code on Claude for Enterprise. When you use Claude Code in your terminal, the prompts you send and the responses Claude generat
Claude Fable 5 is not available for organizations with zero data retention enabled. This model class [requires data retention](https://platform.claude.com/docs/en/manage-claude/api
Claude Fable 5.1 and Fable 5 are [Covered Models](https://support.claude.com/en/articles/15425695-covered-models) that [require data retention](https://platform.claude.com/docs/en/
Other models remain available under ZDR. Fable 5 is not the default model, and the `best` alias, which resolves to Fable 5 where it is available, resolves to Opus for organizations
+3 −3 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
vs-code
±changed
+1−1
claude-codechanged
vs-code
* **Errors and model prompts**: the extension announces errors in the conversation, and announces when the [usage-credits consent prompt](/docs/en/model-config#fable-5-and-usage-cr
* **Errors and model prompts**: the extension announces errors in the conversation, and announces when the [usage-credits consent prompt](/docs/en/model-config#fable-and-usage-cred
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
settings-reference
±changed
+4−4
claude-codechanged
settings-reference
To pick Fable, first accept the [usage-credits consent](/docs/en/advisor#fable-advisor-and-usage-credits) by running `/model fable`. Until you do, picking Fable in `/advisor` saves
If your account requires the [usage-credits consent](/docs/en/advisor#fable-advisor-and-usage-credits), accept it first by running `/model fable`. Until you do, picking Fable in `/
The key has no effect on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. `"fable"` requires [Fable 5 access](/docs/en/advisor#choose-an-advisor-model).
The key has no effect on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. `"fable"` requires [Fable access](/docs/en/advisor#choose-an-advisor-model).
On models that always think, such as Fable 5, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instea
+4 −4 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **Forwarded dialogs expire**: Claude Code keeps permission prompts and `AskUserQuestion` questions open until you answer them. When Claude Code forwards another kind of dialog to
* **Forwarded dialogs expire**: Claude Code keeps permission prompts and `AskUserQuestion` questions open until you answer them. When Claude Code forwards another kind of dialog to
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable 5 and Opus 5 is also a model switch. When a safety classifier flags a request and the flagged ca
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable 5.1, Fable 5, and Opus 5 is also a model switch. When a safety classifier flags a request and th
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
permission-modes
±changed
+3−3
claude-codechanged
permission-modes
* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or [Fable 5](/docs/en/model-config#w
* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-co
On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), [Microsoft Foundry](/docs/en/microsoft-foundry), and signed-in [Claude app
On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), [Microsoft Foundry](/docs/en/microsoft-foundry), and signed-in [Claude app
The classifier runs on Claude Sonnet 5 by default rather than on your `/model` selection. A classifier model that Anthropic configures server-side takes precedence over that de
+3 −3 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
model-config
±changed
+60−51
claude-codechanged
model-config
| **`best`** | Uses Fable 5 where your organization has access to it, otherwise the latest Opus model
| **`fable`** | Uses Claude Fable 5 for your hardest and longest-running tasks
| **`best`** | Uses the latest Fable model where it's available to you, otherwise the same model as `opus`
| **`fable`** | Uses the latest Fable model for your hardest and longest-running tasks
Unless you set `ANTHROPIC_DEFAULT_FABLE_MODEL`, the `fable` alias resolves to Fable 5.1. Before v2.1.255, it resolved to Fable 5.
+60 −51 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
A discovered ID is skipped when it exactly matches a row already in the picker, or when both the discovered and existing IDs resolve to [Fable](/docs/en/model-config#work-with-fabl
A discovered ID is skipped when it exactly matches a row already in the picker, or when the discovered and existing IDs are spellings of the same [Fable](/docs/en/model-config#work
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is
A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
feature-availability
±changed
+4−4
claude-codechanged
feature-availability
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and Fa
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and th
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable 5 only
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable models only
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable 5 only
+4 −4 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
errors
±changed
+24−8
claude-codechanged
errors
| `Claude Code ... does not support this model; version ... or newer is required`
On plans where Fable 5 usage [bills to usage credits](/docs/en/model-config#fable-5-and-usage-credits), Claude Code asks you to confirm before a request bills them. When nobody ans
```text theme={null}
Fable 5 limit reached · continuing on Fable 5 uses usage credits, and the prompt to confirm went unanswered — nothing was sent · answer it where this session is running, or /model
+24 −8 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
env-vars
±changed
+8−7
claude-codechanged
env-vars
| `ANTHROPIC_DEFAULT_FABLE_MODEL` | Model ID that the `fable` alias resolves to, and the ID Claude Code recognizes as Fable 5 for [automatic model fallback]
| `ANTHROPIC_DEFAULT_FABLE_MODEL` | Model ID that the `fable` alias resolves to, and the ID Claude Code recognizes as a Fable model for [automatic model fal
| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/docs/en/model-config#extended-context) support. When set, 1M model variants a
| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/docs/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fal
| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/docs/en/model-config#extended-context) support. When set, 1M model variants a
+8 −7 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
desktop
±changed
+4−4
claude-codechanged
desktop
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or Fable 5. Organization administrators can turn auto mode off
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or a Fable model. Organization administrators can turn auto mod
[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthrop
On models with [adaptive reasoning](/docs/en/model-config#adjust-effort-level), `MAX_THINKING_TOKENS` values other than `0` are ignored because adaptive reasoning controls thinking
+4 −4 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the
Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
If you need a larger window rather than a smaller conversation, Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended contex
If you need a larger window rather than a smaller conversation, Fable 5.1, Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Exte
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
communications-kit
±changed
+7−7
claude-codechanged
communications-kit
formatting, and mechanical edits where speed wins. *Fable 5* is the most
formatting, and mechanical edits where speed wins. *Fable* is the most
| Model | Best for
| ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| Fable 5 | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content [falls back to Opus](/docs/en/model-config#automatic-mo
+7 −7 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/advisor [model\|off]` | Enable or disable the [advisor tool](/docs/en/advisor), which consults a second mo
| `/advisor [model\|off]` | Enable or disable the [advisor tool](/docs/en/advisor), which consults a second mo
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
cli-reference
±changed
+2−2
claude-codechanged
cli-reference
| `--advisor <model>` | Enable the server-side [advisor tool](/docs/en/advisor) for this session with a model alias, `fable`, `opus`, or `sonnet`, or a
| `--advisor <model>` | Enable the server-side [advisor tool](/docs/en/advisor) for this session with a model alias, `fable`, `opus`, or `sonnet`, or a
| `--model` | Sets the model for the current session with an alias for the latest model (`sonnet`, `opus`, `haiku`, or `fable`) or a model's f
| `--model` | Sets the model for the current session with a [model alias](/docs/en/model-config#model-aliases) such as `sonnet`, `opus`, `haik
+2 −2 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
claude-security
±changed
+1−1
claude-codechanged
claude-security
**You may see "Fable 5's safeguards flagged this message" when using Fable 5.** Due to Fable 5's cybersecurity safety classifiers, certain model activities will be blocked and auto
**You may see "Fable 5.1's safeguards flagged this message" or "Fable 5's safeguards flagged this message" when using a Fable model.** Due to Fable's cybersecurity safety classifie
+1 −1 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
changelog
±changed
+107−0
claude-codechanged
changelog
<Update label="2.1.257" description="September 1, 2026">
* Added Claude Fable 5.1 (`claude-fable-5-1`), now the default Fable model — 1M context, $10/$50 per Mtok with \$0.25/Mtok cache reads
* Added "Time format" (`timeFormat`) and `timeZone` settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps
* Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment ma
+107 −0 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-code
advisor
±changed
+23−23
claude-codechanged
advisor
On some plans, Fable as the advisor also needs your one-time [consent to bill Fable 5 usage to usage credits](/docs/en/model-config#fable-5-and-usage-credits). For what happens bef
On some plans, Fable as the advisor also needs your one-time [consent to bill Fable usage to usage credits](/docs/en/model-config#fable-and-usage-credits). For what happens before
On some plans, Fable as the advisor also needs your one-time [consent to bill Fable 5 usage to usage credits](/docs/en/model-config#fable-5-and-usage-credits). For what `/advisor f
On some plans, Fable as the advisor also needs your one-time [consent to bill Fable usage to usage credits](/docs/en/model-config#fable-and-usage-credits). For what `/advisor fable
| Main model | Accepted advisors | Notes
+23 −23 lines
Recorded here 1 Sep 2026 18:07 UTC
claude-docs
claude-tag/users/use-cases/create-artifacts
±changed
+4−4
claude-docschanged
claude-tag/users/use-cases/create-artifacts
Check that the channel has the connections below. Ask `@Claude what can you access from this channel?` to check; an admin can [add a connection](/docs/claude-tag/admins/add-connect
Check that the channel has the connections below. Ask `@Claude what can you access from this channel?` to check; an admin can [add a connection](/docs/claude-tag/admins/add-connect
Anyone with access to this channel can open the page; [artifact visibility](/docs/claude-tag/concepts/security-and-data#artifact-visibility) covers the access model.
Anyone with access to this channel can open the page; [artifact visibility](/docs/claude-tag/concepts/security-and-data.md#artifact-visibility) covers the access model.
> **[Catch up](/docs/claude-tag/users/use-cases/catch-up)**
+4 −4 lines
Upstream edited 1 Sep 2026 18:04 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-tag/users/use-cases/create-artifacts
±changed
+9−11
claude-docschanged
claude-tag/users/use-cases/create-artifacts
export const BetaNote = () => <Info>Claude Tag is in public beta. Features and behavior described here may change before general availability.</Info>;
<BetaNote />
> [!NOTE]
>
+9 −11 lines
Upstream edited 1 Sep 2026 18:04 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-tag/users/use-cases/create-artifacts
±changed
+3−3
claude-docschanged
claude-tag/users/use-cases/create-artifacts
| Connection | Examples | Why it matters here |
| :------------- | :------------------ | :------------------------------------- |
| None | — | Works on Slack content alone |
| Connection | Examples | Why it matters here |
| :- | :- | :- |
+3 −3 lines
Upstream edited 1 Sep 2026 18:04 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-code
sandboxing
±changed
+4−2
claude-codechanged
sandboxing
There is no built-in credential deny list, so only the files and variables you list are restricted. The setting affects sandboxed Bash commands only. To strip Anthropic and cloud p
There is no built-in credential deny list, so only the files and variables you list are restricted.
`sandbox.credentials` affects sandboxed Bash commands only. To strip credentials from all subprocesses regardless of sandboxing, set [`CLAUDE_CODE_SUBPROCESS_ENV_SCRUB`](/docs/en/e
* **Environment variables**: sandboxed Bash commands inherit the parent process environment by default, including any credentials set there. Use [`sandbox.credentials`](#protect-cr
+4 −2 lines
Recorded here 1 Sep 2026 15:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
Apart from Git's `GIT_CONFIG_KEY_<n>` variables, Claude Code removes every variable from your environment whose name has `TOKEN`, `SECRET`, `PASSWORD`, `PASSWD`, `PASSPHRASE`, `KEY
Apart from Git's `GIT_CONFIG_KEY_<n>` variables, Claude Code removes every variable from your environment whose name looks like a credential, such as a name with `TOKEN`, `SECRET`,
+1 −1 lines
Recorded here 1 Sep 2026 15:07 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` | Set to `1` to strip Anthropic and cloud provider credentials from subprocess environments (Bash tool, hooks, MCP stdio s
| `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` | Set to `1` to strip credentials from subprocess environments (Bash tool, hooks, MCP stdio servers): Anthropic and cloud
+1 −1 lines
Recorded here 1 Sep 2026 15:07 UTC
claude-code
ultrareview
±changed
+12−2
claude-codechanged
ultrareview
Use `/tasks` to see running and completed reviews, open the detail view for a review, or stop a review that is in progress. If you stop a review, Claude Code archives the cloud ses
Use `/tasks` to see running and completed reviews, open the detail view for a review, or stop a review that is in progress. If you stop a review, Claude Code archives the cloud ses
When the review finishes, Claude Code shows the verified findings as a notification in your session. Each finding includes the file location and an explanation of the issue so you
Running `claude ultrareview` requires the same authentication and usage credit configuration as `/code-review ultra`. The subcommand exits with code 0 when the review completes wit
+12 −2 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
| `RemoteTrigger` | Creates, updates, runs, and lists [Routines](/docs/en/routines) on claude.ai. Backs the `/schedule` command. The [`RemoteTrigger` input reference](/docs/
| `RemoteTrigger` | Creates, updates, runs, and lists [Routines](/docs/en/routines) on claude.ai. Backs the `/schedule` command. The [`RemoteTrigger` input reference](/docs/
+1 −1 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
sub-agents
±changed
+28−23
claude-codechanged
sub-agents
The frontmatter defines the subagent's metadata and configuration. The body becomes the system prompt that guides the subagent's behavior. Subagents receive only this system prompt
The frontmatter defines the subagent's metadata and configuration. The body becomes the system prompt that guides the subagent's behavior. Subagents receive only this system prompt
| Field | Required | Description
| :---------------- | :------- | :--------------------------------------------------------------------------------------------------------------------------------------------------
| `name` | Yes | Unique identifier using lowercase letters and hyphens. [Hooks](/docs/en/hooks#subagentstart) receive this value as `agent_type`. The filename doesn
+28 −23 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
settings-reference
±changed
+5−3
claude-codechanged
settings-reference
Redaction only changes what you see, not what the model generates: to reduce thinking spend, [lower the budget or disable thinking](/docs/en/model-config#extended-thinking) instead
Redaction changes only what you see, not what the model generates. To reduce thinking spend, [lower the budget or disable thinking](/docs/en/model-config#extended-thinking) instead
Place a `.` entry in project settings: it resolves to the project root there and to `~/.claude` in user settings. Claude Code merges entries across every settings file the session
Claude Code resolves a `.` entry to the project root in project settings and to `~/.claude` in user settings. Claude Code merges entries across every settings file the session load
An empty array in a managed source blocks every login with a misconfiguration message, and so does a value Claude Code can't parse. See [Restrict login to your organization](/docs/
+5 −3 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
server-managed-settings
±changed
+12−4
claude-codechanged
server-managed-settings
* **The `env` block**: apart from the telemetry unit and routing variables paired with a credential key, both covered below, it merges per key across the admin-controlled sources.
* **Telemetry unit**: the `OTEL_EXPORTER_OTLP_*` exporter keys, the `OTEL_LOG_*` content-capture toggles, `OTEL_LOGS_EXPORTER`, and the beta tracing variables `ENABLE_BETA_TRACIN
* **Credential-paired routing**: a source that pairs routing variables with a winner-only credential key, such as `apiKeyHelper` or `otelHeadersHelper`, contributes those routing
* **The `env` block**: apart from the telemetry unit and routing variables paired with a credential key, both covered below, it merges per key across the admin-controlled sources.
* **Telemetry unit**: the `OTEL_EXPORTER_OTLP_*` exporter keys, the `OTEL_LOG_*` content-capture toggles, `OTEL_LOGS_EXPORTER`, and the beta tracing variables `ENABLE_BETA_TRACIN
+12 −4 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
sandboxing
±changed
+17−5
claude-codechanged
sandboxing
When you define the same filesystem array in multiple [settings scopes](/docs/en/settings#settings-precedence), Claude Code merges them, combining paths from every scope rather tha
When you define the same filesystem array in multiple [settings scopes](/docs/en/settings#settings-precedence), Claude Code merges them, combining paths from every scope rather tha
If you exclude a source with [`--setting-sources`](/docs/en/cli-reference) on the CLI or [`settingSources`](/docs/en/agent-sdk/claude-code-features#control-filesystem-settings-with
* Sandboxed commands inherit your shell's `$TMPDIR` instead of the session temp directory, because every temp directory is writable and Claude Code no longer redirects commands to
+17 −5 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
routines
±changed
+0−5
claude-codechanged
routines
<Note>
One-off scheduling from the CLI is rolling out gradually and may not be available on your account yet. If `/schedule` only offers recurring schedules, create the one-off run from
</Note>
* `DISABLE_TELEMETRY`, `DO_NOT_TRACK`, `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, or `DISABLE_GROWTHBOOK` is set in your shell environment or in the `env` block of a [`settings.js
+0 −5 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
monitoring-usage
±changed
+2−0
claude-codechanged
monitoring-usage
When a `PreToolUse` hook [defers a tool call](/docs/en/hooks#defer-a-tool-call-for-later), Claude Code saves the trace context of the turn that deferred it. When you resume the ses
+2 −0 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
llm-gateway-connect
±changed
+2−0
claude-codechanged
llm-gateway-connect
Routing and tenant header names like these count as [headers that need approval](/docs/en/server-managed-settings#environment-variables-and-the-approval-dialog). When the headers c
+2 −0 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
| `StopFailure` | error type
| `StopFailure` | error type
+1 −1 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
hooks
±changed
+2−2
claude-codechanged
hooks
| `StopFailure` | error type
| `StopFailure` | error type
| `error` | Error type: `rate_limit`, `overloaded`, `authentication_failed`, `oauth_org_not_allowed`, `billing_error`, `invalid_request`, `model_not_found`, `serve
| `error` | Error type: `rate_limit`, `overloaded`, `authentication_failed`, `oauth_org_not_allowed`, `account_on_hold`, `billing_error`, `invalid_request`, `model
+2 −2 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
errors
±changed
+27−7
claude-codechanged
errors
| `Your account is on hold and can't use Claude Code. View details or appeal: https://claude.ai/restricted`
| `Your account is on hold and can't sign in to Claude Code. View details or appeal: https://claude.ai/restricted`
* Run `/usage-credits` to turn on metered billing for the 1M variant on Pro and Max, or to request it from your admin on Team and Enterprise
* Where the message names `/usage-credits`, run it to turn on metered billing for the 1M variant on Pro and Max, or to request usage credits from your admin on Team and Enterprise
Claude Code tried to renew your saved claude.ai or Claude Console login and the OAuth service rejected the stored refresh token, so Claude Code cleared the saved credentials. After
+27 −7 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
env-vars
±changed
+4−4
claude-codechanged
env-vars
| `ANTHROPIC_CUSTOM_HEADERS` | Custom headers to add to requests (`Name: Value` format, newline-separated for multiple headers). If a name or value con
| `ANTHROPIC_CUSTOM_HEADERS` | Custom headers to add to requests (`Name: Value` format, newline-separated for multiple headers). If a name or value con
| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) in tokens, from `100000` to `1000000`.
| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) in tokens, from `100000` to `1000000`.
| `DISABLE_TELEMETRY` | Set to any non-empty value, such as `1`, to opt out of telemetry. **Setting it to `0` or `false` still opts out**, unlik
+4 −4 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
[Usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) let you keep working past your plan's usage limit. To manage them, run `/usage-cr
[Usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) let you keep working past your plan's usage limit. To manage them, run `/usage-cr
+1 −1 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
context-window
±changed
+2−2
claude-codechanged
context-window
tip: 'Output JSON with `additionalContext` to send info to Claude. For PostToolUse hooks, exit code 2 surfaces stderr as an error but cannot block since the tool already ran. K
tip: 'Output JSON with `additionalContext` to send info to Claude. For PostToolUse hooks, exit code 2 surfaces stderr as an error but cannot block since the tool already ran. O
link: '/en/interactive-mode#bash-mode-with-prefix'
link: '/en/interactive-mode#shell-mode-with-prefix'
+2 −2 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
claude-apps-gateway-config
±changed
+1−0
claude-codechanged
claude-apps-gateway-config
* Sandbox settings that intercept traffic, inject credentials, or weaken isolation, such as `sandbox.network.tlsTerminate` and the proxy port settings. [Security approval dialogs](
+1 −0 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
When the certificate rotates, every developer sees the trust prompt again, so treat rotations as a planned event and republish the fingerprint.
When the certificate rotates, every developer sees the trust prompt again, so treat rotations as a planned event and republish the fingerprint. If your gateway policy includes [set
+1 −1 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
authentication
±changed
+1−1
claude-codechanged
authentication
Once the stored login expires and can't be refreshed, each request fails with [`Login expired · Please run /login`](/docs/en/errors#login-expired) until you sign in again. Before v
Once the stored login expires and can't be refreshed, each model request fails with [`Login expired · Please run /login`](/docs/en/errors#login-expired) until you sign in again. Be
+1 −1 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-code
amazon-bedrock
±changed
+2−0
claude-codechanged
amazon-bedrock
If your organization delivers the guardrail headers through a [Claude apps gateway](/docs/en/claude-apps-gateway) policy instead, they count as [settings that need approval](/docs/
+2 −0 lines
Recorded here 1 Sep 2026 03:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.