api-20260901T180808Z / documentation capture

build-with-claude/thinking-troubleshooting Changed · +25 / -7 lines

## Thinking support, defaults, and rejected configurations by model ## A 400 error says a thinking block signature is invalid ## Configurations each model rejects

from line 10

1010

1111This page covers the most common failures when configuring thinking or round-tripping thinking blocks (sending returned thinking blocks back in later requests). The first section maps each model to its supported thinking configurations and the ones it rejects; the sections after it each start from a symptom you observe, so you can match an error message or unexpected response directly to its cause and fix. To learn how thinking works, see the [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) overview.

1212

13## Configurations each model rejects

13## Thinking support, defaults, and rejected configurations by model

1414

15Most 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: "adaptive"}`, and on the newest it is on by default. Some earlier models instead use [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking), a legacy manual mode configured as `thinking: {type: "enabled", budget_tokens: N}`.

15Most 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: "adaptive"}`, and many have it on by default. Some earlier models instead use [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking), a legacy manual mode configured as `thinking: {type: "enabled", budget_tokens: N}`.

1616

1717Extended thinking (`thinking.type: "enabled"` with `budget_tokens`) is deprecated on the Claude 4.6 models (requests using it still succeed). Claude 4.7 and later models do not support it and reject requests that use it, returning a 400 error. On Claude 4.5 and earlier models that support thinking, extended thinking is the only available thinking mode. Claude Mythos Preview supports both modes. Where both modes are available, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) instead.

1818

from line 20

2020

2222| --------------------- | -------------------------------- | --------- | -------------------------- |

from line 40

3840

3941Models marked `Always on` cannot turn thinking off. Models marked `On` default to thinking but accept `thinking: {type: "disabled"}`.

4042

41Earlier Claude 4 models (Claude Opus 4.1, Claude Sonnet 4, and Claude Opus 4) support extended thinking only; see [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for their availability. Claude Fable 5 and Claude Mythos 5 are not available under [zero data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

43Earlier Claude 4 models (Claude Opus 4.1, Claude Sonnet 4, and Claude Opus 4) support extended thinking only. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for their availability. Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5 are not available under [zero data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements) unless expressly authorized by Anthropic.

4244

4345## A 400 error says `"thinking.type.enabled"` is not supported

4446

from line 50

4850"thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.

4951```

5052

51This happens because the model you requested has removed extended thinking (see [Configurations each model rejects](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#rejected-configurations)).

53This happens because the model you requested has removed extended thinking (see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#rejected-configurations)).

5254

5355Switch the request to `thinking: {type: "adaptive"}` and steer thinking depth with `effort` instead of `budget_tokens`. [Migrating to adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#migrating-to-adaptive-thinking) walks through the conversion.

5456

from line 62

6062"thinking.type.disabled" is not supported for this model. Thinking defaults to adaptive mode when not specified; use "thinking.type.enabled" with "budget_tokens" for extended thinking.

6163```

6264

63This happens on models where thinking is always on: Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview reject `"disabled"`. On Claude Fable 5 and Claude Mythos 5, the error text's suggestion of `"thinking.type.enabled"` does not apply either: those models reject it too.

65This happens on models where thinking is always on: Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview reject `"disabled"`. All of these except Claude Mythos Preview also reject the error text's suggested `"thinking.type.enabled"`.

6466

6567Omit the `thinking` parameter; these models think without any configuration. If your goal was to keep thinking text out of responses, use `display: "omitted"` instead of disabling thinking; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).

6668

from line 76

7476adaptive thinking is not supported on this model

7577```

7678

77This happens because the model supports only extended thinking (see [Configurations each model rejects](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#rejected-configurations)).

79This happens because the model supports only extended thinking (see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#rejected-configurations)).

7880

7981Use `thinking: {type: "enabled", budget_tokens: N}` instead; see [Extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for the configuration.

8082

from line 92

9092

9193Echo the assistant turn back verbatim, thinking blocks included. See [Preserving thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks) for the rules, and the worked round trip in [Thinking in tool and multi-turn workflows](https://platform.claude.com/docs/en/build-with-claude/thinking-tool-workflows#two-turn-tool-use-round-trip) for correct code in every SDK.

9294

95## A 400 error says a thinking block signature is invalid

96

97A request to Claude Fable 5.1 that replays earlier thinking blocks fails with a 400 `invalid_request_error` whose message reads:

98

99```text wrap

100messages.{i}.content.{j}: Invalid `signature` in `thinking` block. The block is bound to a different conversation. Remove the block, or set `thinking.block_binding.prefix_mismatch_behavior` to "drop_block".

101```

102

103If the request didn't send the `thinking-binding-controls-2026-08-01` beta header, the message adds ``That setting requires the `thinking-binding-controls-2026-08-01` value in the `anthropic-beta` header.`` The message can also end with a sentence naming the first message that changed. If the message has no reason clause at all, the block's content was modified. See [A 400 error says thinking blocks cannot be modified](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-blocks-modified).

104

105On Claude Fable 5.1, the API accepts a replayed thinking block [only while the `system` prompt, `tools`, and messages that preceded it are unchanged](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation). The error means something earlier in the conversation changed between requests: an edited, reordered, or removed turn, a per-turn reminder that was injected and later removed, a rebuilt `system` prompt or `tools` array, or client-side compaction that kept recent turns and their thinking verbatim. The check is enforced for new accounts created on or after August 31, 2026, and for any request that sets `thinking.block_binding.prefix_mismatch_behavior`. Server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) and [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) never trigger it.

106

107To fix it, keep the history append-only: pass earlier turns back exactly as sent and received, add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) instead of editing `system` or `tools`, and let server-side [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) or [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) do any trimming. Retrying the same request body doesn't clear the error. To continue this request without the invalidated reasoning, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. Alternatively, strip every `thinking` and `redacted_thinking` block from the history (at minimum the named block and every one after it, in that turn and all later turns), leave each turn's other blocks in place, and retry once.

108

109A block from a model the target model can't read never produces this error: the API drops it and, under the beta header, reports it in `input_transformations`.

110

93111## The thinking field is empty in the response

94112

95113The response contains `thinking` blocks, but their `thinking` field is an empty string and only the `signature` field is populated.

from line 114

96114

97115This happens because `display` defaults to `"omitted"` on newer models, which returns thinking blocks without their text.

98116

99Set `display: "summarized"` in your thinking configuration to receive the summarized thinking text; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display) for the defaults per model.

117Set `display: "summarized"` in your thinking configuration to receive the summarized thinking text. See [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display) for the defaults per model. If you only want the short status lines some models write between tool calls, and not the reasoning, set `display: "updates"` (beta) instead. See [Progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates).

100118

101119## No thinking block appears on some turns

102120

build-with-claude/token-counting Changed · +5 / -5 lines

## Token counts on Claude Fable and Claude Mythos models ## Token counts on Claude Fable 5 and Claude Mythos 5

from line 28

2828

2929### Supported models

3030

31All [active models](https://platform.claude.com/docs/en/models/overview) support token counting, including Claude Opus 5 and Claude Sonnet 5.

31All [active models](https://platform.claude.com/docs/en/models/overview) support token counting.

3232

3333<Note>

3434 Claude 4.7 and later models and Claude Mythos Preview use a newer tokenizer. The same input text produces approximately 30 percent more tokens than on earlier models. The exact increase depends on the content and workload shape. Recount prompts against the model you plan to use rather than reusing counts measured against earlier models.

from line 1394

13941394

13951395***

13961396

1397## Token counts on Claude Fable 5 and Claude Mythos 5

1397## Token counts on Claude Fable and Claude Mythos models

13981398

1399Claude 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 text. The exact increase depends on the content and workload shape. The token counting endpoint returns the count under the tokenizer of the `model` you pass, so to measure the difference for your workload, count the same request twice: once with your current model and once with `model: "claude-fable-5"` (or `"claude-mythos-5"`), and compare the two `input_tokens` values.

1399Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5 share the tokenizer introduced with Claude Opus 4.7. A prompt counts the same on all four, and roughly 30 percent higher than on models before Claude Opus 4.7 (the exact increase depends on the content). The token counting endpoint counts under the tokenizer of the `model` you pass. To measure the difference for your workload, count the same request twice, once with your current model and once with the model you plan to move to, and compare the two `input_tokens` values.

14001400

14011401<Note>

1402 **Billing and migration:** Usage and billing on Claude Fable 5 and Claude Mythos 5 reflect this tokenizer's counts. If you're migrating from a model before Claude Opus 4.7, the same content consumes roughly 30 percent more tokens. The exact increase depends on the content and workload shape. When migrating a workload to Claude Fable 5 and Claude Mythos 5, don't reuse token counts measured on a model before Claude Opus 4.7 to estimate costs or context window fit. Count your prompts with `model: "claude-fable-5"` (or `"claude-mythos-5"`).

1402 **Billing and migration:** Usage and billing on these models reflect this tokenizer's counts. When migrating from a model before Claude Opus 4.7, don't reuse token counts measured on the older model to estimate costs or context window fit. Count your prompts with the `model` ID you plan to use (for example, `"claude-fable-5-1"`).

14031403</Note>

14041404

14051405***

claude_api_primer Changed · +4 / -1 lines

from line 11

1111## Models

1212

1313```text wrap

14For complex agentic coding and enterprise work: Claude Opus 5: claude-opus-5

14Recommended default for most work, including complex agentic coding: Claude Opus 5: claude-opus-5

15Step up for the hardest long-running agentic and research tasks, at 2x Claude Opus 5 pricing: Claude Fable 5.1: claude-fable-5-1

1516Previous Opus model: Claude Opus 4.8: claude-opus-4-8

1617Smart model: Claude Sonnet 5: claude-sonnet-5

1718For fast, cost-effective tasks: Claude Haiku 4.5: claude-haiku-4-5-20251001

from line 621

620621* `any` tells Claude that it must use one of the provided tools.

621622* `tool` forces Claude to always use a particular tool.

622623* `none` prevents Claude from using any tools.

624

625On 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 call Claude makes matches the tool's `input_schema`. See [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use).

623626

624627### JSON output

625628

home Changed · +3 / -3 lines

from line 241

241241 <HomeSection>

242242 <HomeSectionHeader label="Models" title="The Claude model family" description="Choose the right model for your use case." />

243243

244 * [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 · Research · Multi-day tasks

245 * [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 · Agents · Coding

244 * [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 capable · Research · Multi-day tasks

245 * [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 · Coding

246246 * [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) (`claude-sonnet-5`) — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient

247247 * [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 cost · High volume

248248 </HomeSection>

from line 251

251251 <HomeSectionHeader label="Resources" title="Keep learning" />

252252

253253 <CardGroup cols={3}>

254 <Card icon="graduation-cap" title="Courses" href="https://anthropic.skilljar.com/">

254 <Card icon="graduation-cap" title="Courses" href="https://academy.claude.com/courses">

255255 Interactive courses to master Claude.

256256 </Card>

257257

manage-claude/api-and-data-retention Changed · +4 / -4 lines

from line 35

3535* **Claude consumer products:** Claude Free, Pro, and Max plans, including when customers on those plans use Claude's web, desktop, or mobile apps or Claude Code.

3636* **Claude Teams and Claude Enterprise product interfaces:** These interfaces are not ZDR-eligible. The exception is Claude Code used through Claude Enterprise with ZDR enabled; see [What ZDR covers](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#what-zdr-covers).

3737* **Claude for Excel:** Not currently ZDR-eligible.

38* **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://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

38* **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 authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

3939* **Third-party integrations:** Data processed by third-party websites, tools, or other integrations is not covered, though some may have similar offerings. Review each service's data handling practices.

4040* **Cross-Origin Resource Sharing (CORS):** CORS is not supported for organizations with ZDR arrangements. To make API calls from browser-based applications, route requests through a backend proxy server. See the [API security guidance](https://platform.claude.com/docs/en/api/overview) for proxy patterns and API-key handling.

4141* **Flagged content and legal holds:** See [Retention regardless of arrangement](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#retention-regardless-of-arrangement).

from line 123

123123

124124## Model-specific data retention requirements

125125

126Claude 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 retention; ZDR is therefore not available for either model. On the Claude API, requests to Claude Fable 5 from an organization whose data retention configuration does not meet this requirement return a `400 invalid_request_error`:

126Claude 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/articles/15425695)) and require 30-day data retention; ZDR is therefore not available for any of them unless expressly authorized by Anthropic. On the Claude API, requests to Claude Fable 5 from an organization whose data retention configuration does not meet this requirement return a `400 invalid_request_error`:

127127

128128```json

129129{

from line 139

139139

140140### Enable 30-day retention for a workspace

141141

142Organizations 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 workspaces in the organization keep zero data retention.

142Organizations with a ZDR arrangement can make these models available in a specific workspace by enabling 30-day retention for that workspace only. Other workspaces in the organization keep zero data retention.

143143

144144<Steps>

145145 <Step title="Open the workspace's privacy controls">

from line 151

151151 </Step>

152152

153153 <Step title="Verify">

154 Requests to Claude Fable 5 and Claude Mythos 5 from this workspace now succeed. Workspaces without an override continue to follow the organization default.

154 Requests to Covered Models from this workspace now succeed. Workspaces without an override continue to follow the organization default.

155155 </Step>

156156</Steps>

157157

manage-claude/cmek Changed · +13 / -13 lines

from line 114

114114

115115The following Claude Platform APIs and tools store data at rest under your key when CMEK is enabled:

116116

117| APIs | Tools and features |

118| --------------------- | --------------------------------------------------------------------------------------------------- |

119| Messages | Web search |

120| Models | Web fetch |

121| Files | Code execution |

122| Batch | Bash tool |

123| Skills | Text editor tool |

124| Claude Managed Agents | MCP connector |

125| | Structured outputs (not available for Claude Fable 5 or Claude Mythos models in CMEK organizations) |

126| | Advisor tool |

127| | Computer use |

128| | Browser use |

129| | Context management |

117| APIs | Tools and features |

118| --------------------- | ------------------------------------------------------------------------------------------------- |

119| Messages | Web search |

120| Models | Web fetch |

121| Files | Code execution |

122| Batch | Bash tool |

123| Skills | Text editor tool |

124| Claude Managed Agents | MCP connector |

125| | Structured outputs (not available for Claude Fable or Claude Mythos models in CMEK organizations) |

126| | Advisor tool |

127| | Computer use |

128| | Browser use |

129| | Context management |

130130

131131## Limited preservation outside your key

132132

managed-agents/reference Changed · +3 / -3 lines

from line 74

7474 </Tab>

7575

7676 <Tab title="System events">

77 | Type | Description |

78 | ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

79 | `system.message` | Append privileged system-level context that applies to the accompanying turn and all subsequent turns. Supported on Claude Opus 4.8, Claude Fable 5, Claude Mythos 5, and Claude Opus 5; on an unsupported primary model the event is rejected with `model_does_not_support_mid_conversation_system`. |

77 | Type | Description |

78 | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

79 | `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, Claude Fable 5, Claude Mythos 5, Claude Opus 5, and Claude Opus 4.8. On an unsupported primary model the event is rejected with `model_does_not_support_mid_conversation_system`. |

8080 </Tab>

8181

8282 <Tab title="Event deltas">

models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 Changed · +11 / -15 lines

## Prompting ## Working with Claude Fable 5 and Claude Mythos 5 ### Prompting

from line 4

44description: Claude Fable 5 and Claude Mythos 5 capabilities, API changes, and availability.

55---

66

7<Note>

8 Claude Fable 5.1 and Claude Mythos 5.1 build on these models. See [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1).

9</Note>

10

711<Tip>

812 Access to Claude Fable 5 and Claude Mythos 5 has been restored. See [our statement](https://www.anthropic.com/news/redeploying-fable-5) for more information.

913</Tip>

1014

11Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Claude Mythos 5 shares the same capabilities and is available only in limited release through [Project Glasswing](https://anthropic.com/glasswing).

15Claude Fable 5 is built for demanding reasoning and long-horizon agentic work. Claude Mythos 5 shares the same capabilities and is available only in limited release through [Project Glasswing](https://anthropic.com/glasswing).

1216

1317The headline change for integrations: Claude Fable 5 includes safety classifiers that can decline requests. Claude Mythos 5 does not include these classifiers. If your integration calls Claude Fable 5, plan for three changes: new response handling for refusals, fallback options for retrying on another Claude model, and new billing rules. [Refusals, fallback, and billing on Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5#refusals-fallback-and-billing-on-claude-fable-5) summarizes all three.

1418

from line 20

1620

1721| Model | API model ID | Description |

1822| --------------- | ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |

19| Claude Fable 5 | `claude-fable-5` | Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work |

23| Claude Fable 5 | `claude-fable-5` | Built for demanding reasoning and long-horizon agentic work |

2024| Claude Mythos 5 | `claude-mythos-5` | Shares Claude Fable 5's capabilities without the safety classifiers. Available through Project Glasswing. Successor to Claude Mythos Preview. |

2125

2226Claude Fable 5 and Claude Mythos 5 share the same specs and pricing:

from line 32

2832

2933## Refusals, fallback, and billing on Claude Fable 5

3034

31Claude Fable 5 includes safety classifiers that can decline certain requests. Claude Mythos 5 does not include these classifiers, so this section applies to Claude Fable 5 only. The following sections summarize what refusals mean for your integration; each links to the full guide.

35Claude Fable 5 includes safety classifiers that can decline certain requests. Claude Mythos 5 does not include these classifiers, so this section applies to Claude Fable 5 only. The following sections summarize what refusals mean for your integration. Each links to the full guide.

3236

3337### Refusals

3438

from line 52

4852

4953## Availability

5054

51Claude Fable 5 and Claude Mythos 5 both become available on June 9, 2026:

52

5355* **Claude Fable 5** is available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry).

5456* **Claude Mythos 5** is offered only to approved customers in [Project Glasswing](https://anthropic.com/glasswing). For access, contact your Anthropic, AWS, or Google Cloud account team. Customers without access to Claude Mythos 5 can use Claude Fable 5, which does not require access approval and offers the same capabilities.

5557

56Claude Fable 5 and Claude Mythos 5 carry 30-day data retention and are not available under zero data retention: both are designated [Covered Models](https://support.claude.com/en/articles/15425695). See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

58Claude Fable 5 and Claude Mythos 5 carry 30-day data retention and are not available under zero data retention unless expressly authorized by Anthropic. Both are designated [Covered Models](https://support.claude.com/en/articles/15425695). See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

5759

58## Working with Claude Fable 5 and Claude Mythos 5

60## Prompting

5961

60### Prompting

61

6262Claude Fable 5 responds to the same prompting techniques as other Claude models, with a few differences in how to structure long-context prompts and reasoning instructions. See [Prompting Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5).

6363

6464## Messages API on Claude Fable 5 and Claude Mythos 5

from line 65

6565

6666### Adaptive thinking is always on

6767

68Claude Fable 5 and Claude Mythos 5 always have thinking enabled; passing `thinking: {"type": "disabled"}` is not supported. To reduce or otherwise control thinking depth, use the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) parameter.

68Claude Fable 5 and Claude Mythos 5 always have thinking enabled. Passing `thinking: {"type": "disabled"}` is not supported. To reduce or otherwise control thinking depth, use the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) parameter.

6969

7070### Raw thinking content is never returned

7171

from line 78

7878

7979## Supported features

8080

81At launch, Claude Fable 5 and Claude Mythos 5 support:

81Claude Fable 5 and Claude Mythos 5 support:

8282

8383* [Effort](https://platform.claude.com/docs/en/build-with-claude/effort)

8484* [Task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta: set the `task-budgets-2026-03-13` header)

from line 99

9999## Next steps

100100

101101<CardGroup>

102 <Card title="Migration guide" icon="arrow-right" href="https://platform.claude.com/docs/en/models/fable-5/migration-guide">

103 Step-by-step upgrade instructions from Claude Opus 4.8 and Claude Mythos Preview.

104 </Card>

105

106102 <Card title="Models overview" icon="settings" href="https://platform.claude.com/docs/en/models/overview">

107103 Specs and comparison for all current Claude models.

108104 </Card>

models/fable-5/migration-guide Changed · +11 / -11 lines

from line 18

1818 The skill applies the model ID swap and, as needed, breaking parameter changes, prefill replacement, and effort calibration for your target model across your code base, then produces a checklist of items to verify manually. It asks you to confirm the migration scope (entire working directory, a subdirectory, or a specific file list) before editing any files. The skill also detects Amazon Bedrock and Claude Platform on AWS clients and adjusts model ID formats and feature changes for those platforms.

1919</Tip>

2020

21[Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) is Anthropic's most capable widely released model, available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). [Claude Mythos 5](https://anthropic.com/glasswing) shares the same capabilities and is offered only to approved customers in Project Glasswing.

21[Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) is built for demanding reasoning and long-horizon agentic work. [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide) builds on it. Claude Fable 5 is available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). [Claude Mythos 5](https://anthropic.com/glasswing) shares the same capabilities and is offered only to approved customers in Project Glasswing.

2222

2323The baseline settings shared by `claude-fable-5` and `claude-mythos-5`:

2424

from line 26

2626* **Prefill:** Prefilling the assistant message returns a 400 error. Use system prompt instructions instead.

2727* **Context window and output:** A [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, and up to 128k output tokens per request.

2828* **Pricing:** $10 USD per million input tokens and $50 USD per million output tokens. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing).

29* **Data retention:** Both models require 30-day data retention and are not available under zero data retention (ZDR) arrangements; both are designated Covered Models. On the Claude API, a request to Claude Fable 5 from an organization whose data retention configuration does not meet this requirement returns a 400 `invalid_request_error`. Organizations with a ZDR arrangement should contact their Anthropic account team to discuss data retention configuration. Alternatively, you can configure data retention per workspace. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements) for per-platform details.

29* **Data retention:** Both models require 30-day data retention and are not available under zero data retention (ZDR) arrangements unless expressly authorized by Anthropic. Both are designated Covered Models. On the Claude API, a request to Claude Fable 5 from an organization whose data retention configuration does not meet this requirement returns a 400 `invalid_request_error`. Organizations with a ZDR arrangement should contact their Anthropic account team to discuss data retention configuration, or configure data retention per workspace. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements) for per-platform details.

3030

3131Where the two models diverge:

3232

from line 307

307307

3083082. **Assistant prefill:** Prefilling the assistant message is not supported on `claude-mythos-5` or `claude-fable-5` and returns a 400 error, the same as on Claude Mythos Preview. Use system prompt instructions instead.

309309

3103. **Thinking output:** On `claude-mythos-5` and `claude-fable-5`, the raw chain of thought is never returned, but thinking blocks still carry readable summarized text when `thinking.display` is set to `summarized`. Pass thinking blocks back unchanged when continuing a conversation on the same model. See [Thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

3103. **Thinking output:** On `claude-mythos-5` and `claude-fable-5`, the raw chain of thought is never returned, but thinking blocks still carry readable summarized text when `thinking.display` is set to `summarized`. Pass thinking blocks back unchanged when continuing a conversation on the same model. See [Thinking output on Claude Fable and Claude Mythos models](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

311311

312312### Token counting and billing

313313

from line 321

321321* Remove manual extended thinking configuration (`thinking: {type: "enabled", budget_tokens: N}`). Adaptive thinking is always on, and no `thinking` field is required.

322322* Remove any `thinking: {type: "disabled"}` configuration. Disabling thinking returns an error on `claude-mythos-5` and `claude-fable-5`.

323323* Remove `budget_tokens`. It has no direct replacement: thinking is adaptive, and the `effort` parameter is a separate output-level control, not a thinking budget.

324* Verify any code that parses the `thinking` field treats it as display text only and passes thinking blocks back unchanged when continuing on the same model. `thinking.display` defaults to `"omitted"` on `claude-mythos-5` and `claude-fable-5`, the same as on Claude Mythos Preview; set `display: "summarized"` to receive readable summaries. See [Thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

325* If you replay conversation history on another model, strip `thinking` and `redacted_thinking` blocks from prior assistant turns first. Thinking blocks from `claude-mythos-5` and `claude-fable-5` are tied to the model that produced them, and models other than Claude Fable 5 and Claude Mythos 5 silently ignore them. Stripping keeps cross-model requests minimal and uniform.

324* Verify any code that parses the `thinking` field treats it as display text only and passes thinking blocks back unchanged when continuing on the same model. `thinking.display` defaults to `"omitted"` on `claude-mythos-5` and `claude-fable-5`, the same as on Claude Mythos Preview. Set `display: "summarized"` to receive readable summaries. See [Thinking output on Claude Fable and Claude Mythos models](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

325* If you replay conversation history on an earlier model, strip `thinking` and `redacted_thinking` blocks from prior assistant turns first. Thinking blocks from `claude-fable-5` and `claude-mythos-5` are readable only by the model that produced them or a newer one: earlier models silently ignore them, while Claude Fable 5.1 and Claude Mythos 5.1 read them, so keep them when you move a conversation up to those models (see [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model)). Stripping keeps requests to earlier models minimal and uniform.

326326* If you migrate to Claude Fable 5, handle `stop_reason: "refusal"` and read the `stop_details.category` field. Claude Fable 5 runs safety classifiers that Claude Mythos Preview and Claude Mythos 5 do not have. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

327327* Re-baseline token counts and costs on your own workloads. Token counts are roughly unchanged when migrating from `claude-mythos-preview`.

328328

from line 350

350350

3513513. **Priority Tier:** [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not supported on Claude Opus 5, so no existing traffic is affected. If your organization has a Priority Tier commitment, Claude Fable 5 supports it; Claude Mythos 5 does not.

352352

3534. **Data retention:** Claude Fable 5 and Claude Mythos 5 require 30-day data retention and are not available under zero data retention (ZDR) arrangements; both are designated Covered Models. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

3534. **Data retention:** Claude Fable 5 and Claude Mythos 5 require 30-day data retention and are not available under zero data retention (ZDR) arrangements unless expressly authorized by Anthropic. Both are designated Covered Models. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

354354

355355### Migration checklist

356356

from line 357

357357* Update the model name from `claude-opus-5` to `claude-fable-5` (or `claude-mythos-5`).

358358* Remove any `thinking: {type: "disabled"}` configuration; it returns a 400 error on `claude-fable-5` and `claude-mythos-5`. Use lower [effort](https://platform.claude.com/docs/en/build-with-claude/effort) levels to control token spend instead, and revisit `max_tokens` for workloads that ran with thinking disabled on Claude Opus 5.

359359* If those workloads read content by position, such as `content[0].text`, update them to select content blocks by `type`: `thinking` blocks now arrive before `text` blocks. Pass `thinking` blocks back complete and unmodified in tool-use loops; modified blocks return a 400 error.

360* If your organization has a zero data retention (ZDR) arrangement, confirm eligibility before migrating. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

360* If your organization has a zero data retention (ZDR) arrangement, confirm eligibility before migrating: these models are not available under ZDR unless expressly authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

361361* Re-baseline cost on your own workloads. Token counts are roughly unchanged; per-token pricing differs, and workloads that ran with thinking disabled now produce thinking tokens, which are billed as output tokens.

362362

363363## Migrating to Claude Mythos 5 and Claude Fable 5 from Claude Opus 4.8

from line 676

676676

6776773. **Assistant prefill (unchanged):** Prefilling the assistant message is not supported on `claude-fable-5` or `claude-mythos-5` and returns a 400 error, the same as on Claude Opus 4.8. Use system prompt instructions instead.

678678

6794. **Thinking output:** On `claude-fable-5` and `claude-mythos-5`, the raw chain of thought is never returned, but thinking blocks still carry readable summarized text when `thinking.display` is set to `summarized`. Pass thinking blocks back unchanged when continuing a conversation on the same model. See [Thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

6794. **Thinking output:** On `claude-fable-5` and `claude-mythos-5`, the raw chain of thought is never returned, but thinking blocks still carry readable summarized text when `thinking.display` is set to `summarized`. Pass thinking blocks back unchanged when continuing a conversation on the same model. See [Thinking output on Claude Fable and Claude Mythos models](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

680680

6816815. **Safety classifiers and the `refusal` stop reason (Claude Fable 5 only):** `claude-fable-5` runs safety classifiers on requests and during response generation. Claude Mythos 5 does not include these classifiers. When a classifier declines a request, the Messages API returns `stop_reason: "refusal"` as a successful HTTP 200 response, not an error. The `stop_details.category` field reports which classifier fired, with categories such as `"cyber"`, `"bio"`, and `"reasoning_extraction"`, or `null` when the refusal maps to no named category. See the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the full set.

682682

from line 690

690690

691691### Migration checklist

692692

693* If your organization has a zero data retention (ZDR) arrangement, confirm eligibility before migrating. `claude-fable-5` and `claude-mythos-5` require 30-day data retention; on the Claude API, requests to `claude-fable-5` that do not meet this requirement return a 400 `invalid_request_error`. Claude Opus 4.8 remains available under ZDR. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

693* If your organization has a zero data retention (ZDR) arrangement, confirm eligibility before migrating. `claude-fable-5` and `claude-mythos-5` require 30-day data retention and are not available under ZDR unless expressly authorized by Anthropic. On the Claude API, requests to `claude-fable-5` that don't meet this requirement return a 400 `invalid_request_error`. Claude Opus 4.8 is available under ZDR. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

694694* Update the model name from `claude-opus-4-8` to `claude-fable-5` (or `claude-mythos-5`).

695695* Remove any `thinking: {type: "disabled"}` configuration. Disabling thinking returns an error on `claude-fable-5` and `claude-mythos-5`, and requests without a `thinking` field run with adaptive thinking.

696696* Update response parsing that reads content by position, such as `content[0].text`: with adaptive thinking always on, `thinking` blocks arrive before `text` blocks. Select content blocks by `type` instead, and pass `thinking` blocks back complete and unmodified in tool-use loops; modified blocks return a 400 error. See [Preserving thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks).

697697* If you removed manual extended thinking and assistant prefills during earlier migrations, no action is needed: both remain unsupported on `claude-fable-5` and `claude-mythos-5`.

698* Verify any code that parses the `thinking` field treats it as display text only and passes thinking blocks back unchanged when continuing on the same model. `thinking.display` defaults to `"omitted"` on `claude-fable-5` and `claude-mythos-5`, the same as on Claude Opus 4.8; set `display: "summarized"` to receive readable summaries. See [Thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

699* If you replay conversation history on another model, strip `thinking` and `redacted_thinking` blocks from prior assistant turns first. Thinking blocks from `claude-fable-5` and `claude-mythos-5` are tied to the model that produced them, and models other than Claude Fable 5 and Claude Mythos 5 silently ignore them. Stripping keeps cross-model requests minimal and uniform. The exception is redeeming a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit), which requires the request body echoed under that feature's exact rules.

698* Verify any code that parses the `thinking` field treats it as display text only and passes thinking blocks back unchanged when continuing on the same model. `thinking.display` defaults to `"omitted"` on `claude-fable-5` and `claude-mythos-5`, the same as on Claude Opus 4.8. Set `display: "summarized"` to receive readable summaries. See [Thinking output on Claude Fable and Claude Mythos models](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).

699* If you replay conversation history on an earlier model, strip `thinking` and `redacted_thinking` blocks from prior assistant turns first. Thinking blocks from `claude-fable-5` and `claude-mythos-5` are readable only by the model that produced them or a newer one: earlier models silently ignore them, while Claude Fable 5.1 and Claude Mythos 5.1 read them, so keep them when you move a conversation up to those models (see [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model)). Stripping keeps requests to earlier models minimal and uniform. The exception is redeeming a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit), which requires the request body echoed under that feature's exact rules.

700700* If you migrate to Claude Fable 5, handle `stop_reason: "refusal"` and read the `stop_details.category` field. To re-run refused requests on another model automatically, consider the opt-in `fallbacks` parameter (beta). See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

701701* Re-evaluate your `effort` setting. Start at `high` for most tasks, including workloads that ran at `xhigh` on Claude Opus 4.8.

702702* Re-baseline cost and latency on your own workloads. Token counts are roughly unchanged when migrating from `claude-opus-4-8`; per-token pricing differs, and thinking tokens are billed as output tokens, so workloads that ran without thinking produce more output tokens per request.

models/fable-5/overview Changed · +25 / -26 lines

## How it compares to the current lineup ## Overview ## How it compares

from line 1

11---

22title: Claude Fable 5

33url: https://platform.claude.com/docs/en/models/fable-5/overview

4description: "Claude Fable 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 building with it."

4description: "Claude Fable 5 reference: lifecycle status, model IDs on every platform, context window, output limits, pricing, and migration resources. Claude Fable 5 is a legacy model, and Claude Fable 5.1 is the current Fable model."

55---

66

7**Latest.** Released June 9, 2026.

7**Legacy.** Released June 9, 2026.

88

9Next-generation intelligence for long-running agents

9Although Claude Fable 5 is still available, you should consider migrating to Claude Fable 5.1 for improved performance. [See Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) · [Migrate to Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-fable-5-to-claude-fable-5-1)

1010

1111Model ID: `claude-fable-5`

1212

1313Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok

1414

15[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [What’s new](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) · [Migration guide](https://platform.claude.com/docs/en/models/fable-5/migration-guide)

15[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [What’s new](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5)

1616

17## Overview

18

19Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Claude Mythos 5 shares the same capabilities and is available only in limited release through [Project Glasswing](https://anthropic.com/glasswing).

20

21The headline change for integrations: Claude Fable 5 includes safety classifiers that can decline requests. Claude Mythos 5 does not include these classifiers. If your integration calls Claude Fable 5, plan for three changes: new response handling for refusals, fallback options for retrying on another Claude model, and new billing rules. [Refusals, fallback, and billing on Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5#refusals-fallback-and-billing-on-claude-fable-5) summarizes all three.

22

23[Introducing Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5)

24

2517## Fable vs. Mythos

2618

2719[Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview) is offered separately, by invitation only, for defensive cybersecurity workflows as part of [Project Glasswing](https://anthropic.com/glasswing). It shares Claude Fable 5's specifications and pricing; Claude Fable 5 includes safety classifiers that can decline requests, and Claude Mythos 5 does not. For access, contact your Anthropic, AWS, or Google Cloud account team.

2820

29## How it compares

21## How it compares to the current lineup

3022

32| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |

33| **Claude Fable 5** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jan 2026 |

34| [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | 1M | 128K | $5 / $25 | Moderate | Adaptive | `high` | May 2026 |

35| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |

36| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |

24| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |

25| [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 |

26| **Claude Fable 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026 |

27| [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | 1M | 128K | $5 / $25 | Adaptive | `high` | May 2026 |

28| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jan 2026 |

29| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |

3730

3831* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.

3932* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.

4033* **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. See Pricing for the full list.

41* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.

4234* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.

4335* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.

4436* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.

from line 67

7567| Max output | 128K tokens |

7668| [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) | Adaptive (always on) |

7769| [Default effort](https://platform.claude.com/docs/en/build-with-claude/effort) | `high` |

78| Comparative latency | Slower |

7970| Input → output | Text and images → text |

8071| Reliable knowledge cutoff | Jan 2026 |

8172| Training data cutoff | Jan 2026 |

from line 75

8475

8576| Feature | Value |

8677| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

87| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (latest) |

78| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (legacy) |

8879| Released | June 9, 2026 |

8980| Retirement | Not sooner than June 9, 2027 |

9081| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |

from line 83

9283## Resources

9384

9485<CardGroup cols={3}>

86 <Card title="Migrate to Claude Fable 5.1" icon="arrows-left-right" href="https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-fable-5-to-claude-fable-5-1">

87 What changes when moving from Claude Fable 5 to Claude Fable 5.1.

88 </Card>

89

90 <Card title="Claude Fable 5.1" icon="arrow-right" href="https://platform.claude.com/docs/en/models/fable-5-1/overview">

91 The current Fable model: overview, specs, and resources.

92 </Card>

93

94 <Card title="Introducing Claude Fable 5 and Claude Mythos 5" icon="star" href="https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5">

95 Capabilities, API changes, and availability for Claude Fable 5.

96 </Card>

97

9598 <Card title="Prompting Claude Fable 5" icon="lightbulb" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5">

9699 Model-specific prompting guidance for long-horizon and agentic work.

97100 </Card>

from line 101

98101

99102 <Card title="Refusals and fallback" icon="shield" href="https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback">

100103 Handle classifier refusals and retry on another Claude model with the `fallbacks` parameter.

101 </Card>

102

103 <Card title="Adaptive thinking" icon="brain" href="https://platform.claude.com/docs/en/build-with-claude/thinking">

104 The only thinking mode on Claude Fable 5. Steer depth with `effort`.

105104 </Card>

106105</CardGroup>

107106

models/haiku-4-5/overview Changed · +6 / -6 lines

from line 16

1616

1717## How it compares

1818

20| :------------------------------------------------------------------------------ | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |

21| [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jan 2026 |

22| [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | 1M | 128K | $5 / $25 | Moderate | Adaptive | `high` | May 2026 |

23| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |

24| **Claude Haiku 4.5** (this model) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |

20| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |

21| [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 2026 |

22| [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | 1M | 128K | $5 / $25 | Moderate | Adaptive | `high` | May 2026 |

23| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |

24| **Claude Haiku 4.5** (this model) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |

2525

2626* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.

2727* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.

models/mythos-5/overview Changed · +22 / -12 lines

## Resources

from line 1

11---

22title: Claude Mythos 5

33url: https://platform.claude.com/docs/en/models/mythos-5/overview

4description: "Claude Mythos 5 at a glance: Claude Fable 5 offered by invitation only through Project Glasswing for defensive cybersecurity workflows — model IDs, specifications, pricing, and how to request access."

4description: "Claude Mythos 5 reference: the same model as Claude Fable 5, offered by invitation only through Project Glasswing for defensive cybersecurity work. Model IDs, specifications, pricing, and migration resources. Claude Mythos 5.1 is the current Mythos model."

55---

66

77**Invite only.** Released June 9, 2026.

from line 12

1212

1313Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok

1414

15[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [What’s new](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) · [Migration guide](https://platform.claude.com/docs/en/models/fable-5/migration-guide)

15[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [What’s new](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) · [Migration guide](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-mythos-5-to-claude-mythos-5-1)

1616

17Claude Mythos 5 is offered separately, by invitation only, for defensive cybersecurity workflows as part of Project Glasswing. It shares Claude Fable 5’s specifications and pricing. Claude Fable 5 includes safety classifiers that can decline requests; Claude Mythos 5 does not include these classifiers. For access, contact your Anthropic, AWS, or Google Cloud account team. [See Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) · [Project Glasswing](https://anthropic.com/glasswing)

17Claude Mythos 5 is offered separately, by invitation only, as part of Project Glasswing. It shares Claude Fable 5’s specifications and pricing. For access, contact your Anthropic, AWS, or Google Cloud account team. [See Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) · [Project Glasswing](https://anthropic.com/glasswing)

1818

1919## How it compares

2020

22| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |

23| [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jan 2026 |

24| **Claude Mythos 5** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jan 2026 |

25| [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | 1M | 128K | $5 / $25 | Moderate | Adaptive | `high` | May 2026 |

26| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |

27| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |

22| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |

23| [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 |

24| **Claude Mythos 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026 |

25| [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | 1M | 128K | $5 / $25 | Adaptive | `high` | May 2026 |

26| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jan 2026 |

27| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |

2828

2929* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.

3030* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.

3131* **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. See Pricing for the full list.

32* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.

3332* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.

3433* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.

3534* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.

from line 64

6564| Max output | 128K tokens |

6665| [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) | Adaptive (always on) |

6766| [Default effort](https://platform.claude.com/docs/en/build-with-claude/effort) | `high` |

68| Comparative latency | Slower |

6967| Input → output | Text and images → text |

7068| Reliable knowledge cutoff | Jan 2026 |

7169| Training data cutoff | Jan 2026 |

from line 76

7876| Released | June 9, 2026 |

7977| Retirement | Not sooner than June 9, 2027 |

8078| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |

79

80## Resources

81

82<CardGroup cols={3}>

83 <Card title="Migrate to Claude Mythos 5.1" icon="arrows-left-right" href="https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-mythos-5-to-claude-mythos-5-1">

84 What changes when moving from Claude Mythos 5 to Claude Mythos 5.1.

85 </Card>

86

87 <Card title="Claude Mythos 5.1" icon="arrow-right" href="https://platform.claude.com/docs/en/models/mythos-5-1/overview">

88 The current Mythos model: overview, specs, and resources.

89 </Card>

90</CardGroup>

8191

8292## Reference

8393

models/overview Changed · +21 / -21 lines

from line 22

2222

2323## Compare models

2424

25If you're unsure which model to use, start with [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for complex agentic coding and enterprise work; for the highest available capability, use [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview). All current models support text and image input, text output, multilingual capabilities, vision, and tool use; each model's page lists the platforms it is available on.

25If you're unsure which model to use, start with [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for most workloads. Use [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5 at higher effort still fall short. All current models support text and image input, text output, multilingual capabilities, vision, and tool use. Each model's page lists the platforms it's available on.

2626

28| :-------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------- | :-------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------- |

30| Model page | [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) | [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) |

38| Reliable knowledge cutoff | Jan 2026 | May 2026 | Jan 2026 | Feb 2025 |

39| Training data cutoff | Jan 2026 | May 2026 | Jan 2026 | Jul 2025 |

28| :-------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------- | :-------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------- |

30| Model page | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) | [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) |

38| Reliable knowledge cutoff | Jun 2026 | May 2026 | Jan 2026 | Feb 2025 |

39| Training data cutoff | Jun 2026 | May 2026 | Jan 2026 | Jul 2025 |

4646

4747* **Comparative latency:** Relative to the current lineup. Actual latency depends on prompt length, output length, and thinking effort.

4848* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price. See Pricing for cache writes, long-context, and per-platform pricing.

from line 61

6161

6262See [Model IDs and versioning](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions) and [Pricing](https://platform.claude.com/docs/en/about-claude/pricing).

6363

64Legacy models (still available): [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview).

64Legacy models (still available): [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview).

6565

6666Once you've picked a model, [learn how to make your first API call](https://platform.claude.com/docs/en/get-started). To understand how model IDs, aliases, and snapshots work, see [Model IDs and versioning](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions); for the reliable-knowledge and training-data cutoffs behind each model, see [Anthropic's Transparency Hub](https://www.anthropic.com/transparency).

6767

release-notes/overview Changed · +12 / -0 lines

### September 1, 2026

from line 12

1212 For updates to Claude Code, see the [complete CHANGELOG.md](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md) in the `claude-code` repository.

1313</Tip>

1414

15### September 1, 2026

16

17* We've launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside **Claude Mythos 5.1** (`claude-mythos-5-1`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) for capabilities, API changes, and migration guidance.

18* Prompt cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost $0.25 USD per million tokens: 0.025x the base input price, compared with 0.1x on other models. Cache writes are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).

19* On Claude Fable 5.1 and Claude Mythos 5.1, `tool_choice` types `any` and `tool` aren't supported and return a 400 error. `auto` and `none` are unchanged. To guarantee schema-conformant tool inputs, use [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs).

20* Thinking blocks produced by Claude Fable 5.1 and Claude Mythos 5.1 are preserved only for the model that produced them or a newer one: earlier models can't read them, and the API drops one replayed to an earlier model. Claude Fable 5.1 accepts thinking blocks from Claude Opus 5, Claude Fable 5, Claude Mythos 5, and earlier Claude models. On Claude Fable 5.1, the API also [checks that nothing before a block has changed](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): for new accounts created on or after August 31, 2026, replaying one after the `system` prompt, `tools`, or an earlier message changed returns a 400 error. With the `thinking-binding-controls-2026-08-01` beta header, dropped blocks are reported in an `input_transformations` response field, and `thinking.block_binding.prefix_mismatch_behavior` chooses between rejecting and dropping blocks whose history changed. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking).

21* Per-message effort changes are in beta on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5 on the Claude API. Add a `role: "system"` message with `output_config.effort` inside `messages` to change effort for later turns while preserving the prompt cache. Include the `mid-conversation-output-config-2026-07-01` beta header in your requests. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).

22* [Turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) are in beta (`mid-conversation-system-clear-at-2026-08-21` header). Set `clear_at: "next_user_message"` on a mid-conversation `role: "system"` message and it renders for the current turn only, then stays in the history at no token cost. Per-turn reminders don't accumulate and don't invalidate the prompt cache or later thinking blocks.

23* `thinking.display` accepts a third value, `"updates"`, in beta (`thinking-display-updates-2026-08-18` header). Reasoning comes back with an empty `thinking` field, as under `"omitted"`, and the short progress updates that Claude Fable 5.1, Claude Mythos 5.1, and Claude Fable 5 write between tool calls come back as text, at most one `thinking` block before a tool call. See [Progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates).

24* Text generated by Claude Fable 5.1 and Claude Mythos 5.1 carries Anthropic's text watermark, and supported image and video files that Claude produces through the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) carry C2PA Content Credentials when you retrieve them through the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) on the Claude API. Marking requires no changes to your requests or response handling.

25* Like Claude Fable 5, both models require 30-day data retention and aren't available under zero data retention unless expressly authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

26

1527### August 27, 2026

1628

1729* In Python SDK 1.2.0, TypeScript SDK 0.122.0, Go SDK 1.68.0, Java SDK 2.59.0, Ruby SDK 1.67.0, and C# SDK 12.44.0, `client.beta.files` and `client.beta.skills` no longer send the `files-api-2025-04-14` and `skills-2025-10-02` beta headers and return the same shapes as `client.files` and `client.skills`. With this change, `client.beta.skills.delete()` deletes a Skill together with all of its versions, and the beta Messages type `BetaSkill` (the container Skill reference) is renamed `BetaContainerSkill`. Requests that still send the beta headers keep receiving the beta shapes. See [Migrate from `files-api-2025-04-14`](https://platform.claude.com/docs/en/build-with-claude/files#migrate-from-files-api-2025-04-14) and [Migrate from `skills-2025-10-02`](https://platform.claude.com/docs/en/build-with-claude/skills-guide#migrate-from-skills-2025-10-02).

about-claude/additional-resources Changed · +1 / -1 lines

from line 11

1111 Deployable applications built with the API.

1212 </Card>

1313

14 <Card title="Courses" icon="graduation-cap" href="https://anthropic.skilljar.com/">

14 <Card title="Courses" icon="graduation-cap" href="https://academy.claude.com/courses">

1515 Step-by-step lessons on building with Claude.

1616 </Card>

1717

about-claude/model-deprecations Changed · +1 / -0 lines

from line 72

7272

7474| -------------------------- | ------------- | ----------------- | ---------------------------------- |

agents-and-tools/tool-use/browser-use-tool Changed · +1 / -1 lines

from line 6

66

77## Compatibility

88- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))

9- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`

9- 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`

1010- Platforms: Claude API, Google Cloud; not available on Claude Platform on AWS, Amazon Bedrock, Microsoft Foundry

1111

1212The browser use tool lets Claude navigate, read, and interact with webpages in a browser that your application runs. It works with the page both through its structure (the accessibility tree, elements, forms, and tabs) and through pixels (screenshots and viewport coordinates), whereas the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) works with a whole desktop through screenshots and coordinates alone. It's an Anthropic-defined [client toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference#client-toolsets): one `browser_toolset_20260801` entry in your `tools` array gives Claude 27 member tools by default, such as `navigate`, `read_page`, `left_click`, and `screenshot`, plus four more (`javascript_exec`, `file_upload`, `read_console`, and `read_network`) when you [enable them](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#enable-optional-member-tools). Your application runs every call against its own browser automation; nothing runs on Anthropic's side. It isn't currently available in [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/tools). This page says "your application" for the agent loop that calls the Messages API and "your executor" for the part of it that drives the browser and produces tool results.

agents-and-tools/tool-use/programmatic-tool-calling Changed · +1 / -1 lines

from line 6

66

77## Compatibility

88- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible

9- 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`, `claude-sonnet-4-6`, `claude-sonnet-4-5-20250929`

9- 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-opus-4-5-20251101`, `claude-sonnet-5`, `claude-sonnet-4-6`, `claude-sonnet-4-5-20250929`

1010- Platforms: Claude API, Claude Platform on AWS, Microsoft Foundry [1]; not available on Amazon Bedrock, Google Cloud

1111- Programmatic tool calling requires the code execution tool with the `code_execution_20260120` or later [tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions).

1212- Claude Haiku 4.5 accepts the `code_execution_20260120` and later tool versions but doesn't support programmatic tool calling.

agents-and-tools/tool-use/tool-search-tool Changed · +2 / -0 lines

from line 41

4141

4242| Model | Tool versions |

4343| ---------------------------------------------- | ------------------------------------------------------------------- |

44| Claude Fable 5.1 (claude-fable-5-1) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

45| Claude Mythos 5.1 (claude-mythos-5-1) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

4446| Claude Fable 5 (claude-fable-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

4547| Claude Mythos 5 (claude-mythos-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

4648| Claude Opus 5 (claude-opus-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

agents-and-tools/tool-use/web-fetch-tool Changed · +1 / -1 lines

from line 10

1010

1111The web fetch tool allows Claude to retrieve full content from specified web pages and PDF documents.

1212

13The 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://anthropic.com/glasswing), Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6. Claude can write and execute code to filter fetched content before it reaches the context window, keeping only relevant information and discarding the rest. This reduces token consumption while maintaining response quality. `web_fetch_20260318` also adds [response inclusion](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#response-inclusion) control for agentic workflows. The previous versions (`web_fetch_20260309` for dynamic filtering and [cache bypass](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#cache-bypass), `web_fetch_20260209` for dynamic filtering only, `web_fetch_20250910` for basic fetch) remain available.

13The 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 window, keeping only relevant information and discarding the rest. This reduces token consumption while maintaining response quality. Dynamic filtering is available with Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, [Claude Mythos Preview](https://anthropic.com/glasswing), Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6. `web_fetch_20260318` also adds [response inclusion](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#response-inclusion) control for agentic workflows. The previous versions (`web_fetch_20260309` for dynamic filtering and [cache bypass](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#cache-bypass), `web_fetch_20260209` for dynamic filtering only, `web_fetch_20250910` for basic fetch) remain available.

1414

1515Web fetch (with and without dynamic filtering) is available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). On Microsoft Foundry, deployments [hosted on Azure](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure) support only the basic web fetch tool (`web_fetch_20250910`, without dynamic filtering). Deployments hosted on Anthropic support all versions. Web fetch is not currently available on Amazon Bedrock or Google Cloud.

1616

api/service-tiers Changed · +1 / -1 lines

from line 227

227227

228228### Supported models

229229

230Priority 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.

230Priority 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), Claude Opus 5, and Claude Sonnet 5.

231231

232232Check the [Models overview](https://platform.claude.com/docs/en/models/overview) for more details on available models.

233233

build-with-claude/batch-processing Changed · +2 / -0 lines

from line 86

8686

8787| Model | Batch input | Batch output |

8888| ------------------------------------------------------------------------------------------------------------------------------------- | ------------ | ------------- |

89| Claude Fable 5.1 | $5 / MTok | $25 / MTok |

90| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | $5 / MTok | $25 / MTok |

8991| Claude Fable 5 | $5 / MTok | $25 / MTok |

9092| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | $5 / MTok | $25 / MTok |

9193| Claude Opus 5 | $2.50 / MTok | $12.50 / MTok |

build-with-claude/claude-on-vertex-ai Changed · +2 / -1 lines

from line 117

117117

118118| Model | Agent Platform API model ID |

119119| ---------------------------- | --------------------------- |

120| Claude Fable 5.1 | claude-fable-5-1 |

120121| Claude Fable 5 | claude-fable-5 |

121122| Claude Opus 5 | claude-opus-5 |

122123| Claude Opus 4.8 | claude-opus-4-8 |

from line 366

365366

366367### Context window

367368

368Claude 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.com/docs/en/build-with-claude/context-windows) on Agent Platform. Other Claude models, including Sonnet 4.5 and Sonnet 4 (deprecated), have a 200k-token context window.

369Claude 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.com/docs/en/build-with-claude/context-windows) on Agent Platform. Other Claude models, including Sonnet 4.5 and Sonnet 4 (deprecated), have a 200k-token context window.

369370

370371Agent Platform limits request payloads to 30 MB. When sending large documents or many images, you might reach this limit before the token limit.

371372

build-with-claude/claude-platform-on-aws Changed · +1 / -0 lines

from line 340

340340

341341| Model | Model ID |

342342| ----------------- | ----------------- |

343| Claude Fable 5.1 | claude-fable-5-1 |

343344| Claude Fable 5 | claude-fable-5 |

344345| Claude Opus 5 | claude-opus-5 |

345346| Claude Opus 4.8 | claude-opus-4-8 |

build-with-claude/extended-thinking Changed · +1 / -1 lines

from line 352

352352You need to migrate off `type: "enabled"` if:

353353

354354* You use Claude Opus 4.6 or Claude Sonnet 4.6, where `budget_tokens` is deprecated.

355* 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.

355* 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"` returns a 400 error.

356356

357357The mapping is small: remove `budget_tokens`, set `thinking: {type: "adaptive"}`, and control reasoning depth with `output_config: {effort: ...}` instead of a token budget.

358358

One read of Claude Developer Platform

What this read moved

build-with-claude/thinking-troubleshooting Changed · +25 / -7 lines

build-with-claude/token-counting Changed · +5 / -5 lines

claude_api_primer Changed · +4 / -1 lines

home Changed · +3 / -3 lines

manage-claude/api-and-data-retention Changed · +4 / -4 lines

manage-claude/cmek Changed · +13 / -13 lines

managed-agents/reference Changed · +3 / -3 lines

models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 Changed · +11 / -15 lines

models/fable-5/migration-guide Changed · +11 / -11 lines

models/fable-5/overview Changed · +25 / -26 lines

models/haiku-4-5/overview Changed · +6 / -6 lines

models/mythos-5/overview Changed · +22 / -12 lines

models/overview Changed · +21 / -21 lines

release-notes/overview Changed · +12 / -0 lines

about-claude/additional-resources Changed · +1 / -1 lines

about-claude/model-deprecations Changed · +1 / -0 lines

agents-and-tools/tool-use/browser-use-tool Changed · +1 / -1 lines

agents-and-tools/tool-use/programmatic-tool-calling Changed · +1 / -1 lines

agents-and-tools/tool-use/tool-search-tool Changed · +2 / -0 lines

agents-and-tools/tool-use/web-fetch-tool Changed · +1 / -1 lines

api/service-tiers Changed · +1 / -1 lines

build-with-claude/batch-processing Changed · +2 / -0 lines

build-with-claude/claude-on-vertex-ai Changed · +2 / -1 lines

build-with-claude/claude-platform-on-aws Changed · +1 / -0 lines

build-with-claude/extended-thinking Changed · +1 / -1 lines