api-20261111T173709Z / page 4 of 6 / documentation capture

manage-claude/opentelemetry Changed · +4 / -4 lines

from line 1

11---

22title: OpenTelemetry tracing for the Claude API

33url: https://platform.claude.com/docs/en/manage-claude/opentelemetry

4description: Trace your Messages API requests, tool uses, and Managed Agents sessions with OpenTelemetry spans from the Claude SDK and the Claude API.

4description: Trace your Messages API requests, tool uses, and Managed Agents sessions with OpenTelemetry spans from the Anthropic SDK and the Claude API.

55featureMetadata:

66 topic:

77 title: OpenTelemetry

from line 29

2929 - claude-sonnet-4-5-20250929

3030 supportedPlatforms:

3131 Claude API: beta

32 Amazon Bedrock: beta

33 Amazon Bedrock (bedrock-runtime): beta

3234 Claude Platform on AWS: beta

3335 Claude Models on Google Cloud (Anthropic managed): beta

34 Amazon Bedrock: beta

35 Amazon Bedrock (InvokeModel): beta

3636 Claude Models on Google Cloud (Google managed): beta

3737 Microsoft Foundry: beta

3838---

from line 58

5858Let Claude Code set up this feature for you

5959

6060```text

61Set up OpenTelemetry tracing with the Claude API and Claude SDK

61Set up OpenTelemetry tracing with the Claude API and Anthropic SDK

6262```

6363

6464<CardGroup cols={3}>

manage-claude/opentelemetry/sdk Changed · +10 / -10 lines

from line 1

11---

2title: Set up OpenTelemetry with the Claude SDK

2title: Set up OpenTelemetry with the Anthropic SDK

33url: https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk

4description: Trace the Claude SDK's requests and tool uses in Python, TypeScript, C#, Go, Java, PHP, or Ruby, and send the spans to your observability platform.

4description: Trace the Anthropic SDK's requests and tool uses in Python, TypeScript, C#, Go, Java, PHP, or Ruby, and send the spans to your observability platform.

55featureMetadata:

66 topic:

77 title: OpenTelemetry

from line 29

2929 - claude-sonnet-4-5-20250929

3030 supportedPlatforms:

3131 Claude API: beta

32 Claude Platform on AWS: beta

3332 Amazon Bedrock: beta

34 Amazon Bedrock (InvokeModel): beta

33 Amazon Bedrock (bedrock-runtime): beta

34 Claude Platform on AWS: beta

3535 Claude Models on Google Cloud (Google managed): beta

3636 Microsoft Foundry: beta

3737---

3838

39With OpenTelemetry, the Claude SDK can emit a span for each request that it sends and each tool use that the [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) runs. You can view these spans in your observability platform, nested in your own traces.

39With OpenTelemetry, the Anthropic SDK can emit a span for each request that it sends and each tool use that the [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) runs. You can view these spans in your observability platform, nested in your own traces.

4040

4141The SDK emits spans in your application. Your application’s OpenTelemetry exporter sends them to your observability platform.

4242

from line 46

4646

4747## 1. Install the SDK

4848

49Install or upgrade to the latest version of the Claude SDK:

49Install or upgrade to the latest version of the Anthropic SDK:

5050

5151<Tabs>

5252 <Tab title="Python">

from line 98

9898 </Tab>

9999

100100 <Tab title="Java">

101 Add the Claude SDK to your dependencies, or update it to at least the following version if your build file already declares it:

101 Add the Anthropic SDK to your dependencies, or update it to at least the following version if your build file already declares it:

102102

103103 <Tabs>

104104 <Tab title="Gradle">

from line 837

837837

838838* Availability: Available

839839

840| Status | Cloud platforms |

841| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

842| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |

840| Status | Cloud platforms |

841| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

842| Beta | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |

843843

844844#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)

845845

manage-claude/wif-providers/spiffe Changed · +5 / -2 lines

from line 171

171171

172172## Acquire and use the token

173173

174The SDK can read the JWT-SVID from the file that spiffe-helper maintains or, except in Java, call the SPIFFE Workload API directly through a token provider. The file path takes the least code, and the SDK supports it in every language. The token-provider path removes the sidecar but requires a SPIFFE Workload API client in your application’s language.

174The SDK can get the JWT-SVID in two ways:

175175

176* **From a file.** spiffe-helper keeps the JWT-SVID in a file, and the SDK reads that file. This takes the least code and works in every SDK language.

177* **From a token provider.** You pass the SDK a token provider that fetches the JWT-SVID from the SPIFFE Workload API, so you don’t need spiffe-helper. This needs a SPIFFE Workload API client library in your application’s language; Python and Go have mature ones. The Java SDK doesn’t accept a token provider, so in Java, use the file.

178

176179<Tabs>

177180 <Tab title="File-based with spiffe-helper">

178181 With spiffe-helper writing a fresh JWT-SVID to `/var/run/secrets/anthropic.com/token`, set `ANTHROPIC_IDENTITY_TOKEN_FILE` to that path. Also set the other federation environment variables that the following sample reads. The SDK reads the file on every token exchange, so it always picks up the most recently rotated SVID. It also refreshes the Anthropic access token automatically before it expires. See [Environment variables](https://platform.claude.com/docs/en/manage-claude/wif-reference#environment-variables) for where each value comes from.

from line 353

350353 </Tab>

351354

352355 <Tab title="Token provider through the SPIFFE Workload API">

353 Except in Java, workloads that link a SPIFFE Workload API client directly can skip spiffe-helper. They pass the SDK a token provider that fetches a fresh JWT-SVID from the agent socket. The SDK calls the provider before each token exchange, so the workload always presents an unexpired SVID. Python ([py-spiffe](https://github.com/HewlettPackard/py-spiffe)) and Go ([go-spiffe](https://github.com/spiffe/go-spiffe)) have mature Workload API clients.

356 Workloads that use a SPIFFE Workload API client library can skip spiffe-helper, in every SDK language except Java. They pass the SDK a token provider that fetches a fresh JWT-SVID from the agent socket. The SDK calls the provider before each token exchange, so the workload always presents an unexpired SVID. Python ([py-spiffe](https://github.com/HewlettPackard/py-spiffe)) and Go ([go-spiffe](https://github.com/spiffe/go-spiffe)) have mature Workload API clients.

354357

355358 <CodeGroup exclude="shell, typescript, java, csharp, php, ruby">

356359 ```python Python

managed-agents/agent-setup Changed · +28 / -19 lines

from line 59

5959

6060## Create an agent

6161

62The following example defines a coding agent that uses the newest Claude Opus model with access to the pre-built agent toolset. The toolset lets the agent write code, read files, search the web, and more. See the [agent tools reference](https://platform.claude.com/docs/en/managed-agents/tools) for the full list of supported tools.

62The following example defines a coding agent that uses the newest Claude Opus model with access to the pre-built agent toolset. The toolset lets the agent write code, read files, search the web, and more. See [Tools](https://platform.claude.com/docs/en/managed-agents/tools) for the full list of supported tools.

6363

64The examples use curl, the `ant` CLI, or the SDK. If you haven’t set one up, the [quickstart](https://platform.claude.com/docs/en/managed-agents/quickstart#before-you-begin) covers installation and client setup.

64The examples use curl, the `ant` CLI, or the SDK. If you haven’t set one up, [Get started with Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/quickstart#before-you-begin) covers installation and client setup.

6565

6666<CodeGroup defaultLanguage="CLI">

6767 ```bash cURL

from line 213

213213The `default_config` on the toolset shows its default [permission policy](https://platform.claude.com/docs/en/managed-agents/permission-policies), `always_allow`, which applies unless you configure one.

214214

215215<Tip>

216 To use Claude Opus 5.5, Claude Opus 5, or Claude Opus 4.8 with [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode), pass `model` as an object, for example: `{"id": "claude-opus-5-5", "speed": "fast"}`. See the fast mode page’s [supported models](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).

216 To use [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode), pass `model` (csharp, go: `Model`) as an object, for example: `{"id": "claude-opus-5-5", "speed": "fast"}`. Fast mode on Claude Opus 4.8 is deprecated. See the fast mode page’s [supported models](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models) for the models that support it on Claude Managed Agents.

217217</Tip>

218218

219219<Tip>

220 To set the model’s effort level, pass `model` as an object, for example: `{"id": "claude-opus-5-5", "effort": "high"}`. The `effort` field accepts a level string (`low`, `medium`, `high`, `xhigh`, or `max`) or an object such as `{"type": "high"}`. See [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels) for what each level does.

220 To set the model’s effort level, pass `model` (csharp, go: `Model`) as an object, for example: `{"id": "claude-opus-5-5", "effort": "high"}`. The `effort` (csharp, go: `Effort`) field accepts a level string (`low`, `medium`, `high`, `xhigh`, or `max`) or an object such as `{"type": "high"}`. See [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels) for what each level does.

221221</Tip>

222222

223223### Pin the inference geo

from line 354

354354 ```

355355</CodeGroup>

356356

357An `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) pin is validated against the workspace’s [`allowed_inference_geos`](https://platform.claude.com/docs/en/manage-claude/data-residency#workspace-level-restrictions) when the agent is saved, when a session is created from it, and on every turn the session serves. If the workspace allowlist narrows so a pin is no longer allowed, new sessions can’t be created from the agent and running sessions refuse further turns; pins are never exempted, because workspaces rely on them for compliance and data residency.

357To change or clear the pin later, update the agent’s `model` (csharp, go: `Model`) object. Supplying `model` (csharp, go: `Model`) without `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) clears the pin, as described under [Update semantics](https://platform.claude.com/docs/en/managed-agents/agent-setup#update-semantics).

358358

359Setting `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) on a model that doesn’t support geographic inference pinning returns a 400 error; see [Model availability](https://platform.claude.com/docs/en/manage-claude/data-residency#model-availability) for the models that do. In a `multiagent` (csharp, go: `Multiagent`) configuration, the agent’s pin and the pin of every agent listed in the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list of `subagents` (csharp, go: `Subagents`) or `workflows` (csharp, go: `Workflows`) must all be set to the same value or all be unset; see [Multiagent orchestration](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration). To change or clear the pin later, update the agent’s `model` (csharp, go: `Model`) object; supplying `model` (csharp, go: `Model`) without `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) clears it, as described under [Update semantics](https://platform.claude.com/docs/en/managed-agents/agent-setup#update-semantics).

359Setting `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) on a model that doesn’t support it returns a 400 error. See [Model availability](https://platform.claude.com/docs/en/manage-claude/data-residency#model-availability) for the models that do.

360360

361## Update an agent

361In a `multiagent` (csharp, go: `Multiagent`) configuration, `subagents` (csharp, go: `Subagents`) and `workflows` (csharp, go: `Workflows`) each have a `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list. The agent and every agent in those lists must all pin the same geo, or all have no pin. See [Multiagent orchestration](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration).

362362

363Updating an agent generates a new version when the configuration changes. The `version` (csharp, go: `Version`) field is optional: supply it for optimistic concurrency (a mismatch returns a 409), or omit it to apply the update unconditionally (last write wins). Updates to archived agents are rejected.

363The API checks an `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) pin against the workspace’s [`allowed_inference_geos`](https://platform.claude.com/docs/en/manage-claude/data-residency#workspace-level-restrictions) list. The check runs when you set the pin, when you create a session from the agent, and on every turn of that session. If the list changes and no longer allows the pin, you can’t create new sessions from the agent. Running sessions also refuse further turns. This applies even to a pin that was allowed when you set it, because workspaces rely on these checks for compliance and data residency.

364364

365With the CLI, edit the agent’s file and run `ant apply` again; apply supplies `version` for you.

365## Update an agent

366366

367Updating an agent generates a new version when the configuration changes. The `version` (csharp, go: `Version`) field is optional. Supply the version that you last read, and the update applies only if the agent is still at that version. Otherwise, the request returns a 409 error. Omit `version` (csharp, go: `Version`) to apply the update whatever the agent’s current version. In that case, if two updates set the same field or `metadata` (csharp, go: `Metadata`) key, the last write wins. The API rejects updates to archived agents.

368

367369<CodeGroup defaultLanguage="CLI">

368370 ```bash cURL

369371 curl -fsSL "https://api.anthropic.com/v1/agents/$AGENT_ID" \

from line 396

394396 You are a helpful coding agent. Always write tests.

395397 ```

396398 </File>

399

400 Edit the agent’s file and run `ant apply` again. The command supplies `version` for you.

397401 </CodeGroupItem>

398402

399403 ```python Python

from line 474

470474 ```

471475</CodeGroup>

472476

473The preceding example supplies `version` (csharp, go: `Version`) from the create response, so the update only applies if nothing else has changed the agent since you read it. To apply an update unconditionally, omit `version` (csharp, go: `Version`) from the request:

477The preceding example supplies `version` (csharp, go: `Version`), so the update only applies if the agent is still at that version. To apply an update unconditionally, omit `version` (csharp, go: `Version`) from the request:

474478

475479<CodeGroup>

476480 ```bash cURL

from line 563

559563

560564### Update semantics

561565

562* **`version` (csharp, go: `Version`)** is optional and must be at least 1 when supplied. When supplied, the request returns a 409 if it doesn’t match the agent’s current version, even when the fields you send already match the stored values; re-read the agent and retry. When omitted, the update applies unconditionally and the most recent update silently replaces any concurrent one, with no error to either caller. Supplying `version` (csharp, go: `Version`) is the recommended default for interactive callers, and omitting it fits declarative apply loops, such as a CI job that syncs checked-in agent definitions, where the loop owns the agent.

566* **`version` (csharp, go: `Version`)** is optional and must be at least 1 when supplied. When supplied, it must match the agent’s current version. If it doesn’t, the request returns a 409, even when the fields you send already match the stored values. Reread the agent and retry. When omitted, the update applies unconditionally. If two concurrent updates set the same field or `metadata` (csharp, go: `Metadata`) key, the later value is kept, with no error to either caller. When too many writes reach the agent at once, a request can fail with a 429 error. Supplying `version` (csharp, go: `Version`) is the recommended default for interactive callers. Omitting it fits declarative apply loops where the loop owns the agent, such as a CI job that syncs checked-in agent definitions.

563567

564568* **Omitted fields are preserved.** You only need to include the fields you want to change.

565569

566* **Scalar fields** (`model` (csharp, go: `Model`), `system` (csharp, go: `System`; ruby: `system_`), `name` (csharp, go: `Name`), `description` (csharp, go: `Description`)) are replaced with the new value. `system` (csharp, go: `System`; ruby: `system_`) and `description` (csharp, go: `Description`) can be cleared by passing `null` (python: `None`; ruby: `nil`; java: `Optional.empty()`; go: `param.Null[string]()`; php: `requestOptions: ['extraBodyParams' => ['system' => null, 'description' => null]]`). `model` (csharp, go: `Model`) and `name` (csharp, go: `Name`) are mandatory and cannot be cleared. Within a `model` (csharp, go: `Model`) object you supply, `effort` (csharp, go: `Effort`) is the sole exception: if the model `id` (csharp, go: `ID`) is unchanged, omitting `effort` (csharp, go: `Effort`) leaves the stored effort level unchanged. If you change the model `id` (csharp, go: `ID`), an omitted `effort` (csharp, go: `Effort`) resets to the new model’s default. Other `model` (csharp, go: `Model`) fields are replaced along with the object: supplying `model` (csharp, go: `Model`) without `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) clears the agent’s inference geo pin.

570* **`model` (csharp, go: `Model`), `system` (csharp, go: `System`; ruby: `system_`), `name` (csharp, go: `Name`), and `description` (csharp, go: `Description`)** are replaced with the new value. To clear `system` (csharp, go: `System`; ruby: `system_`) or `description` (csharp, go: `Description`), pass `null` (python: `None`; ruby: `nil`; java: `Optional.empty()`; go: `param.Null[string]()`; php: `requestOptions: ['extraBodyParams' => ['system' => null, 'description' => null]]`). Every agent needs a `model` (csharp, go: `Model`) and a `name` (csharp, go: `Name`), so those two can’t be cleared. When you supply `model` (csharp, go: `Model`), it replaces the stored object as a whole, so `model` (csharp, go: `Model`) fields that you omit aren’t kept. For example, supplying `model` (csharp, go: `Model`) without `inference_geo` (java, php: `inferenceGeo`; csharp, go: `InferenceGeo`) clears the agent’s inference geo pin. The one exception to this rule is `effort` (csharp, go: `Effort`). If the model `id` (csharp, go: `ID`) is unchanged, omitting `effort` (csharp, go: `Effort`) leaves the stored effort level unchanged. If you change the model `id` (csharp, go: `ID`), an omitted `effort` (csharp, go: `Effort`) resets to the new model’s default.

567571

568572* **Array fields** (`tools` (csharp, go: `Tools`), `mcp_servers` (java, php: `mcpServers`; csharp: `McpServers`; go: `MCPServers`), `skills` (csharp, go: `Skills`)) are fully replaced by the new array. To clear an array field entirely, pass `null` (python: `None`; ruby: `nil`; java: `Optional.empty()`; go: `param.NullSlice[[]anthropic.BetaAgentUpdateParamsToolUnion]()`; php: `requestOptions: ['extraBodyParams' => ['mcp_servers' => null]]`) or an empty array.

569573

570* **`multiagent` (csharp, go: `Multiagent`)** is merged into the stored block level by level when the update keeps the `multiagent_20261001` type. A setting that you omit keeps its stored value, and a `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list that you send replaces the stored list. Any other update that sends `multiagent` (csharp, go: `Multiagent`) replaces the stored block as a whole, and the settings that it omits take their defaults. Pass `"multiagent": null` (python: `multiagent=None`; typescript: `multiagent: null`; ruby: `multiagent: nil`; go: `Multiagent: param.NullStruct[anthropic.BetaManagedAgentsMultiagentParamsUnion]()`; java: `.multiagent(Optional.empty())`; csharp: `Multiagent = null`; php: `requestOptions: ['extraBodyParams' => ['multiagent' => null]]`) to clear the whole block. Inside the block, `null` resets a setting to its default, so setting `workflows` (csharp, go: `Workflows`) to `null` turns dynamic workflows on. See [Turn on dynamic workflows](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#turn-on-dynamic-workflows).

574* **`multiagent` (csharp, go: `Multiagent`)** updates merge or replace, depending on the type:

571575

576 * When the stored block and the update both use the `multiagent_20261001` type, the update is merged into the stored block. A setting that you omit keeps its stored value, both at the top of the block and inside `subagents` (csharp, go: `Subagents`) or `workflows` (csharp, go: `Workflows`). A `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list that you send replaces the stored list. A setting that you send with a new `type`, such as `{"type": "disabled"}`, replaces the stored setting. Fields that it omits take their defaults.

577 * If the stored block or the update uses the [`coordinator` type](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#move-from-the-coordinator-type), the update replaces the stored block as a whole. Settings that it omits take their defaults.

578

579 To clear the whole block, pass `"multiagent": null` (python: `multiagent=None`; typescript: `multiagent: null`; ruby: `multiagent: nil`; go: `Multiagent: param.NullStruct[anthropic.BetaManagedAgentsMultiagentParamsUnion]()`; java: `.multiagent(Optional.empty())`; csharp: `Multiagent = null`; php: `requestOptions: ['extraBodyParams' => ['multiagent' => null]]`). To reset one setting to its default, set it to `null` inside the block. For example, setting `workflows` (csharp, go: `Workflows`) to `null` turns dynamic workflows on, because that is its default. See [Turn on dynamic workflows](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#turn-on-dynamic-workflows).

580

572581* **Metadata** is merged at the key level. Keys you provide are added or updated. Keys you omit are preserved. To delete a specific key, set its value to `null`.

573582

574583* **No-op detection.** If the update produces no change relative to the current version, no new version is created and the existing version is returned.

575584

576* **Other agents’ `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) lists are not updated.** Agents that list this agent in the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list of `subagents` (csharp, go: `Subagents`) or `workflows` (csharp, go: `Workflows`) keep the version that was pinned when they were created or when an update last sent that list, even if the reference omits `version` (csharp, go: `Version`). To delegate to the new version, [update the agent that lists it](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#list-the-subagents) so that the list references the new version.

585* **Other agents’ `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) lists are not updated.** Updating this agent doesn’t change any agent that lists it in the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list of `subagents` (csharp, go: `Subagents`) or `workflows` (csharp, go: `Workflows`). A listing agent keeps referencing the same version of this agent. That version is set when the listing agent is created, and again whenever an update to the listing agent includes that list. A reference that omits `version` (csharp, go: `Version`) is set to the latest version at that moment, and it doesn’t follow later versions. To delegate to the new version, [update the agent that lists it](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#list-the-subagents) so that the list references the new version.

577586

578587The following update clears the description, deletes the `team` key from `metadata` (csharp, go: `Metadata`), and sets `workflows` (csharp, go: `Workflows`) to `null`, which turns dynamic workflows on:

579588

from line 623

614623 ```

615624 </File>

616625

617 The file no longer has `description` or the `team` key, so `ant apply` sends `null` for them. Deleting a setting inside `multiagent` keeps its stored value, so the file sets `workflows` to `null`.

626 The stored agent has a `description` and a `team` key in `metadata`, but the file doesn’t, so `ant apply` sends `null` for them. `multiagent` is different: for a setting missing from inside it, `ant apply` sends nothing, so the API keeps the stored value. To reset `workflows`, the file sets it to `null`.

618627 </CodeGroupItem>

619628

620629 ```python Python

from line 734

725734

726735### List versions

727736

728Fetch the full version history to track how an agent has changed over time. Results are paginated, and the SDK examples fetch every page automatically.

737Fetch the full version history to track how an agent has changed over time. Results are paginated, and the SDK can fetch every page for you.

729738

730739<CodeGroup>

731740 ```bash cURL

from line 866

857866 </Card>

858867

859868 <Card title="Start a session" icon="play" href="https://platform.claude.com/docs/en/managed-agents/sessions">

860 Create a session to run your agent and start running tasks.

869 Create a session to start running tasks with your agent.

861870 </Card>

862871

863872 <Card title="Reference" icon="book" href="https://platform.claude.com/docs/en/managed-agents/reference">

managed-agents/dreams Changed · +4 / -3 lines

from line 9

99 eligibility: not-eligible

1010 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.

1111 supportedModels:

12 - claude-fable-5-2

1213 - claude-fable-5-1

1314 - claude-fable-5

1415 - claude-opus-5-5

from line 661

660661

661662* Availability: Available

662663

663| Status | Cloud platforms | Models |

664| ---------------- | --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

665| Research preview | Claude API | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-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 Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) |

664| Status | Cloud platforms | Models |

665| ---------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

666| Research preview | Claude API | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-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 Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview) |

666667

667668### Required beta headers

668669

managed-agents/events-and-streaming Changed · +6 / -6 lines

from line 307

307307

308308<CodeGroup exclude="shell:cURL, shell:CLI">

309309 <CodeGroupItem language="cURL">

310 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

310 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

311311 </CodeGroupItem>

312312

313313 <CodeGroupItem language="CLI">

314 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

314 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

315315 </CodeGroupItem>

316316

317317 ```python Python

from line 697

697697

698698<CodeGroup exclude="shell:cURL, shell:CLI">

699699 <CodeGroupItem language="cURL">

700 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

700 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

701701 </CodeGroupItem>

702702

703703 <CodeGroupItem language="CLI">

704 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

704 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

705705 </CodeGroupItem>

706706

707707 ```python Python

from line 903

903903

904904<CodeGroup exclude="shell:cURL, shell:CLI">

905905 <CodeGroupItem language="cURL">

906 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

906 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

907907 </CodeGroupItem>

908908

909909 <CodeGroupItem language="CLI">

910 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

910 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

911911 </CodeGroupItem>

912912

913913 ```python Python

models/fable-5-1/overview Changed · +2 / -4 lines

from line 6

66

77**Legacy.** Released September 1, 2026.

88

9For demanding reasoning and long-horizon agentic work

9Although Claude Fable 5.1 is still available, you should consider migrating to Claude Fable 5.2. [See Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) · [Migrate to Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#migrating-from-claude-fable-5-1-to-claude-fable-5-2)

1010

11Although Claude Fable 5.1 is still available, you should consider migrating to Claude Fable 5.2. [See Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) · [Migrate to Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide)

12

1311Model ID: `claude-fable-5-1`

1412

1513Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok

from line 101

103101 When this model’s thinking blocks stay usable: across model switches and across changes to the conversation.

104102 </Card>

105103

106 <Card title="Per-message effort" icon="sliders" href="https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta">

104 <Card title="Per-message effort" icon="sliders" href="https://platform.claude.com/docs/en/build-with-claude/effort-per-message">

107105 Change the effort level partway through a conversation without invalidating the prompt cache.

108106 </Card>

109107

models/fable-5-2/migration-guide Changed · +17 / -17 lines

from line 14

1414/claude-api migrate this project to claude-fable-5-2

1515```

1616

17If your Claude Managed Agents agent has an advisor, the advisor’s `model` is a second model name to update: set it to `claude-fable-5-2` or `claude-mythos-5-2` when you change the agent’s model. See [A Claude Fable 5.2 executor needs a Claude Fable 5.2 or Claude Mythos 5.2 advisor](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-advisor-pairs). If the agent’s `model` object sets `speed: "fast"`, remove it too.

17If your Claude Managed Agents agent has an advisor, the advisor’s `model` is a second model name to update: set it to `claude-fable-5-2` or `claude-mythos-5-2` when you change the agent’s model. See [A Claude Fable 5.2 executor needs a Claude Fable 5.2 or Claude Mythos 5.2 advisor](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-advisor-pairs). If the agent’s `model` object sets `speed: "fast"`, remove that setting too.

1818

1919The following sections cover moving to Claude Fable 5.2, or to Claude Mythos 5.2, from Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, or an earlier Claude Fable, Claude Mythos, or Claude Opus model. For the changes themselves, see [What’s new in Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2). For behavioral differences and model-specific prompting patterns, see [Prompting Claude Fable 5.2](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2).

2020

21Claude Fable 5.2 is available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). It’s also available on [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock). It’s also available on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). It’s also available on [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview) has the same capabilities and is available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).

21Claude Fable 5.2 is available on the Claude API, [Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview) has the same capabilities and is available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).

2222

2323The baseline settings shared by `claude-fable-5-2` and `claude-mythos-5-2`:

2424

from line 52

5252model = "claude-fable-5-2" # After

5353```

5454

55The model ID is `claude-fable-5-2` on every platform except Amazon Bedrock, where it’s `anthropic.claude-fable-5-2`. For each platform’s ID, see the [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) model page.

55The model ID is `claude-fable-5-2` on every platform except Amazon Bedrock. There, it’s `global.anthropic.claude-fable-5-2` or `us.anthropic.claude-fable-5-2`, and only the `bedrock-runtime` endpoint serves the model.

5656

5757### Breaking changes

5858

from line 64

6464 messages.5.content.0: 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". That setting requires the `thinking-binding-controls-2026-08-01` value in the `anthropic-beta` header.

6565 ```

6666

67 Retrying the same request body doesn’t clear the error. To find these edits before you switch production traffic, run the check in [Check whether your code edits the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#how-to-tell-whether-your-integration-is-impacted) against the model you use now, Claude Fable 5.1 or Claude Opus 5.5. If you use the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) without [pinning a server’s tool list](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector#pin-mcp-tool-list), also run the check against `claude-fable-5-2`: a tool list that changes between requests is an edit for Claude Fable 5.2 thinking blocks, but not for Claude Fable 5.1 or Claude Opus 5.5 blocks. The check works from any account, because setting `prefix_mismatch_behavior` opts the request into the check. [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) gives the fix for each pattern.

67 Retrying the same request body doesn’t clear the error. To find these edits before you switch production traffic, run the check in [Check whether your code edits the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#how-to-tell-whether-your-integration-is-impacted) against the model you use now, Claude Fable 5.1 or Claude Opus 5.5. If you use the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) without [pinning a server’s tool list](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector#pin-mcp-tool-list), also run the check against `claude-fable-5-2`: a tool list that changes between requests is an edit for Claude Fable 5.2 thinking blocks, but not for Claude Fable 5.1 or Claude Opus 5.5 blocks. You can run this check from any account. [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) gives the fix for each pattern.

6868

6969 In production, leave `prefix_mismatch_behavior` at its default, `"error"`, if a mismatch can only mean a bug in your code. To drop the affected blocks and continue without that reasoning while you fix the edit, set it to `"drop_block"`. Treat that as a stopgap, not a long-term setting: [dropping blocks can raise output tokens](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#drop-block-cost).

7070

71712. **Claude Fable 5.1 can’t read Claude Fable 5.2’s thinking blocks:** On the Claude API and Claude Models on Google Cloud (Google managed), Claude Fable 5.2 reads Claude Fable 5.1’s blocks, so a conversation that moves from `claude-fable-5-1` onto `claude-fable-5-2` keeps its earlier reasoning. In the other direction, Claude Fable 5.1 can’t read Claude Fable 5.2’s blocks. If a router switch, a client-side retry, or a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) moves a conversation from Claude Fable 5.2 to another model, Claude Fable 5.1 included, the API drops the blocks that model can’t read. The request succeeds, and you aren’t billed for the dropped input tokens. The model then works without that reasoning, which can raise cost and latency on the first turn after the switch. With the `thinking-binding-controls-2026-08-01` beta header, `input_transformations` lists each dropped block with `reason: "model_binding_mismatch"`. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

7272

733. **Use the computer use toolset instead of `computer_20251124`:** A `tools` entry of type `computer_20251124` returns a 400 error on every platform except Amazon Bedrock. Declare the `computer_toolset_20260801` toolset instead: drop the beta header and send the entry with no `name` or display dimensions. Then update your agent loop for the toolset, as [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) describes. On Amazon Bedrock, the earlier tool works as it does on Claude Fable 5.1.

733. **Use the computer use toolset instead of `computer_20251124`:** A `tools` entry of type `computer_20251124` returns a 400 error on every platform except Amazon Bedrock. Declare the `computer_toolset_20260801` toolset instead: drop the beta header and send the entry with no `name` or display dimensions. Then update your agent loop for the toolset, as [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) describes. On Amazon Bedrock, Claude Fable 5.2 and Claude Mythos 5.2 accept the earlier tool: with the InvokeModel API, send `computer-use-2025-11-24` in the `anthropic_beta` array of the request body.

7474

75754. **A Claude Fable 5.2 executor needs a Claude Fable 5.2 or Claude Mythos 5.2 advisor:** With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), which is in beta, the advisor must be at least as capable as the executor. A Claude Fable 5.2 or Claude Mythos 5.2 executor accepts only Claude Fable 5.2 or Claude Mythos 5.2 as its advisor, and any other advisor, including Claude Fable 5.1 and Claude Mythos 5.1, returns a 400 `invalid_request_error`. When you change the executor’s model ID, set the `model` in the advisor tool definition to `claude-fable-5-2` or `claude-mythos-5-2`. Changing the advisor’s `model` is an edit to `tools`, so make the change in new conversations. A request that sends earlier thinking blocks back after the change fails the prefix check (see [The prefix check applies to every account](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-preserved-thinking)) and returns a 400 error, unless you set `prefix_mismatch_behavior` to `"drop_block"`. To keep your current executor and change only the advisor, set the advisor’s `model` to `claude-fable-5-2`: every executor model accepts it. A Claude Fable 5.2 advisor returns its advice encrypted, so if your code reads the advice text, see [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants). The same pairs apply to the advisor of a [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) agent, so set that advisor’s `model` to one of these two models when you change the agent’s. See [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) and [Give the session an advisor](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#give-the-session-an-advisor).

7676

from line 93

9393* Keep passing `thinking` blocks back unchanged on every turn, including empty ones. If a router or fallback can move a conversation from Claude Fable 5.2 to Claude Fable 5.1, expect Claude Fable 5.1 to run without Claude Fable 5.2’s blocks.

9494* If you replay stored conversations through a different account, replay each one through the account that produced it, or an account linked to it. The API drops Claude Fable 5.2 thinking blocks that another account produced. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).

9595* Re-run your [effort sweep](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-2) on your own evals, and re-baseline cost and latency.

96* Check the system prompts, skills, and other instructions you carry over against [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

96* Check the system prompts, skills, and other instructions you carry over against [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

9797

9898## Migrating to Claude Mythos 5.2 from Claude Mythos 5.1

9999

from line 126

126126* If your code builds the `messages` array itself, run the check in [Editing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-edited-history) against `claude-mythos-5-2`, fix every `prefix_binding_mismatch` entry, and keep conversation history append-only (see [What counts as an edit](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#what-counts-as-an-edit)). An append-only history also keeps the prompt cache warm.

127127* Handle `stop_reason: "refusal"` and read `stop_details.category` before response content. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

128128* Re-run your effort sweep, and re-baseline cost and latency.

129* Check the system prompts, skills, and other instructions you carry over against [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

129* Check the system prompts, skills, and other instructions you carry over against [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

130130

131131## Migrating to Claude Fable 5.2 from Claude Opus 5.5

132132

from line 143

143143

1441441. **Data retention is required:** Claude Fable 5.2 requires 30-day data retention and isn’t available under a zero data retention (ZDR) arrangement unless expressly authorized by Anthropic. If your organization or workspace runs Claude Opus 5.5 under ZDR, enable 30-day retention for a workspace or contact your Anthropic account team before you switch. Otherwise, on the Claude API, every request to Claude Fable 5.2 returns a 400 `invalid_request_error`. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

145145

1462. **The prefix check applies to every account:** Claude Opus 5.5 enforces the prefix check by default for accounts created on or after August 31, 2026. Claude Fable 5.2 enforces it for every account, whatever its age. If your account is older and your code changes `system`, `tools`, or earlier messages between requests, requests that work on Claude Opus 5.5 fail on Claude Fable 5.2. To test before you switch, see [The prefix check applies to every account](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-preserved-thinking).

1462. **The prefix check applies to every account:** Claude Opus 5.5 enforces the prefix check by default for accounts created on or after August 31, 2026. Claude Fable 5.2 enforces it for every account, whatever its age. If your account is older and your code changes `system`, `tools`, or earlier messages between requests, requests that work on Claude Opus 5.5 can fail on Claude Fable 5.2. To test before you switch, see [The prefix check applies to every account](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-preserved-thinking).

147147

1481483. **Claude Opus 5.5 can’t read Claude Fable 5.2’s thinking blocks:** A conversation that moves from Claude Fable 5.2 to Claude Opus 5.5 keeps its text and tool calls, but the turns after the switch run without Claude Fable 5.2’s reasoning. The API drops those blocks before the model receives them, the request succeeds, and the dropped blocks aren’t billed. Expect higher cost and latency on the first turn after the switch. In the other direction, on the Claude API and Claude Models on Google Cloud (Google managed), Claude Fable 5.2 reads Claude Opus 5.5’s thinking blocks, so a conversation that moves from `claude-opus-5-5` onto `claude-fable-5-2` keeps its earlier reasoning.

149149

from line 157

157157

158158 Claude Fable 5.2 also supports fast mode on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), with the same `speed: "fast"` setting. Google Cloud sets its prices there. See [Cloud platform pricing](https://platform.claude.com/docs/en/about-claude/pricing#cloud-platform-pricing).

159159

160 Claude Fable 5.2 also supports fast mode on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Anthropic. There, fast mode is a separate model: send requests to a `claude-fable-5-2-fast` deployment and leave out `speed`.

160 Claude Fable 5.2 also supports fast mode on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Anthropic. There, fast mode has its own model ID: send requests to a `claude-fable-5-2-fast` deployment and leave out `speed`.

161161

162162 Claude Mythos 5.2 also supports fast mode in Messages API requests on the Claude API, at Claude Fable 5.2’s fast mode prices. [Availability of fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#feature-availability) lists every platform where Claude Mythos 5.2 has fast mode.

163163

from line 182

182182* If you use the advisor tool with Claude Fable 5.2 as the executor, set the advisor’s `model` to `claude-fable-5-2` or `claude-mythos-5-2`.

183183* In an organization with [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), remove `strict: true` and `output_config.format`, and validate the output in your code.

184184* Set `effort` explicitly: Claude Fable 5.2’s default is `high`, where Claude Opus 5.5’s is `medium`, so a request that omits it runs one level higher. Then re-run your [effort sweep](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-2) on your own evals, and re-baseline cost and latency.

185* Check the system prompts, skills, and other instructions you carry over against [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

185* Check the system prompts, skills, and other instructions you carry over against [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

186186

187187## Migrating to Claude Fable 5.2 from Claude Fable 5

188188

from line 219

219219

220220* **Pricing:** $8 USD per million input tokens and $40 USD per million output tokens, compared with $10 USD and $50 USD on Claude Fable 5. Prompt cache reads are $0.20 USD per million tokens, compared with $1 USD. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing).

221221* **Priority Tier:** Claude Fable 5.2 isn’t supported on [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models). Claude Fable 5 is. If your organization has a Priority Tier commitment, plan capacity separately.

222* **Per-message effort (beta):** To change effort partway through a conversation without losing prompt cache hits, send a [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) `role: "system"` message instead of changing `output_config.effort` between requests. That section lists the platforms where it’s available.

222* **Per-message effort (beta):** To change effort partway through a conversation without losing prompt cache hits, send a [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort-per-message) `role: "system"` message instead of changing `output_config.effort` between requests. The Per-message effort page lists the platforms where it’s available.

223223

224224### Migration checklist

225225

from line 237

237237* If your organization has a Priority Tier commitment, plan capacity separately.

238238* Handle `stop_reason: "refusal"` and read `stop_details.category`. Consider `fallbacks: "default"`, in beta on the Claude API and Claude Models on Google Cloud (Anthropic managed).

239239* Re-run your [effort sweep](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-2) on your own evals, and re-baseline cost and latency.

240* Check the system prompts, skills, and other instructions you carry over against [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

240* Check the system prompts, skills, and other instructions you carry over against [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

241241

242242## Migrating to Claude Mythos 5.2 from Claude Mythos 5

243243

from line 270

270270* If your code builds the `messages` array itself, run the check in [Editing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-edited-history) against `claude-mythos-5-2`, fix every `prefix_binding_mismatch` entry, and keep conversation history append-only (see [What counts as an edit](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#what-counts-as-an-edit)). An append-only history also keeps the prompt cache warm.

271271* Handle `stop_reason: "refusal"` and read `stop_details.category` before response content. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

272272* Re-run your effort sweep, and re-baseline cost and latency.

273* Check the system prompts, skills, and other instructions you carry over against [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

273* Check the system prompts, skills, and other instructions you carry over against [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

274274

275275## Migrating to Claude Fable 5.2 from Claude Opus 5

276276

from line 309

309309

310310 Claude Fable 5.2 also supports fast mode on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), with the same `speed: "fast"` setting. Google Cloud sets its prices there. See [Cloud platform pricing](https://platform.claude.com/docs/en/about-claude/pricing#cloud-platform-pricing).

311311

312 Claude Fable 5.2 also supports fast mode on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Anthropic. There, fast mode is a separate model: send requests to a `claude-fable-5-2-fast` deployment and leave out `speed`.

312 Claude Fable 5.2 also supports fast mode on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Anthropic. There, fast mode has its own model ID: send requests to a `claude-fable-5-2-fast` deployment and leave out `speed`.

313313

314314 Claude Mythos 5.2 also supports fast mode in Messages API requests on the Claude API, without the header and at Claude Fable 5.2’s fast mode prices. [Availability of fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#feature-availability) lists every platform where Claude Mythos 5.2 has fast mode.

315315

from line 337

337337* If you use fast mode in Messages API requests on the Claude API, keep `speed: "fast"` only if [Availability of fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#feature-availability) lists the model you move to. If you keep it, re-baseline cost against the [fast mode prices](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing). Remove `speed: "fast"` in Claude Managed Agents. You don’t need the `fast-mode-2026-02-01` beta header, and requests that send it keep working.

338338* In an organization with [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), remove `strict: true` and `output_config.format`, and validate the output in your code.

339339* Re-run your [effort sweep](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-2) on your own evals, and re-baseline cost and latency.

340* Check the system prompts, skills, and other instructions you carry over against [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

340* Check the system prompts, skills, and other instructions you carry over against [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

341341

342342## Migrating to Claude Fable 5.2 from Claude Opus 4.8 or earlier

343343

344344First work through [Migrating to Claude Fable 5.2 from Claude Opus 5](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#migrating-from-claude-opus-5-to-claude-fable-5-2), with `claude-opus-4-8` as the model ID you replace. That section applies to code on Claude Opus 4.8 as written, because Claude Opus 4.8, like Claude Opus 5:

345345

346* Accepts `thinking: {type: "disabled"}`, forced tool choice, the `computer_20251124` tool, and fast mode.

346* Accepts `thinking: {type: "disabled"}`, forced tool choice, the `computer_20251124` tool, and fast mode, which is [deprecated on Claude Opus 4.8](https://platform.claude.com/docs/en/build-with-claude/fast-mode).

347347* Returns the text between tool calls as `text` blocks.

348348* Is available under zero data retention (ZDR) arrangements.

349349* Costs $5 USD per million input tokens and $25 USD per million output tokens, with prompt cache reads at $0.50 USD.

from line 360

360360

3613614. **Advice from the advisor tool comes back encrypted:** With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), which is in beta, a Claude Opus 4.8 executor can pair with an advisor that returns its advice as plaintext, such as Claude Opus 4.8. The only advisors a Claude Fable 5.2 executor accepts, Claude Fable 5.2 and Claude Mythos 5.2, return the advice encrypted, as an `advisor_redacted_result` block, so your client can’t read its text. If your code reads the advice text, remove that dependency. See [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants).

362362

363If your code is on Claude Opus 4.7 or earlier, also apply part of the Claude Opus 5.5 guide’s migration checklist. Start at the group [Claude Opus 4.7 or earlier](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migration-checklist-from-claude-opus-47) and go down to the group that names your model. These groups cover request changes made before Claude Opus 4.8, such as removed sampling parameters and beta headers. Apply that checklist’s fast mode item only if [Availability of fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#feature-availability) lists the model you move to. In an organization with [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), structured outputs aren’t available for Claude Fable 5.2, so don’t apply the `output_config.format` item there. Remove `output_format` from your requests instead, and validate the JSON in your code.

363If your code is on Claude Opus 4.7 or earlier, also apply part of the Claude Opus 5.5 guide’s migration checklist. Start at the group [Claude Opus 4.7 or earlier](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migration-checklist-from-claude-opus-47) and apply each group after it in turn, up to and including the one that names your model. These groups cover request changes made before Claude Opus 4.8, such as removed sampling parameters and beta headers. Apply that checklist’s fast mode item only if [Availability of fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#feature-availability) lists the model you move to. In an organization with [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), structured outputs aren’t available for Claude Fable 5.2, so don’t apply the `output_config.format` item there. Remove `output_format` from your requests instead, and validate the JSON in your code.

364364

365365### Migration checklist

366366

models/fable-5-2/overview Changed · +14 / -14 lines

from line 43

4343

4444### Model IDs

4545

46| Platform | Model ID |

47| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------- |

48| Claude API | `claude-fable-5-2` |

49| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-2` |

50| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-fable-5-2` |

51| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-2` |

52| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5-2` |

53| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-fable-5-2` |

46| Platform | Model ID |

47| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------- |

48| Claude API | `claude-fable-5-2` |

49| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-fable-5-2` |

50| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-fable-5-2` |

51| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-2` |

52| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5-2` |

53| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-fable-5-2` |

5454

5555### Pricing

5656

from line 80

8080

8181### Availability

8282

83| Feature | Value |

84| :---------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

86| Released | November 9, 2026 |

87| Retirement | Not sooner than November 9, 2027 |

88| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

83| Feature | Value |

84| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

86| Released | November 9, 2026 |

87| Retirement | Not sooner than November 9, 2027 |

88| Platforms | Claude API, [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8989

9090## Good to know

9191

models/fable-5-2/whats-new-fable-5-2 Changed · +8 / -13 lines

from line 63

6363

6464### Use the computer use toolset instead of `computer_20251124`

6565

66Claude Fable 5.1 accepts [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) both as the `computer_toolset_20260801` toolset and, with the `computer-use-2025-11-24` beta header, as the earlier `computer_20251124` tool. Claude Fable 5.2 and Claude Mythos 5.2 support computer use through the toolset. A request to either model that declares a `computer_20251124` tool returns a 400 `invalid_request_error` on every platform except Amazon Bedrock, where the earlier tool works as it does on Claude Fable 5.1.

66Claude Fable 5.1 accepts [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) both as the `computer_toolset_20260801` toolset and, with the `computer-use-2025-11-24` beta header, as the earlier `computer_20251124` tool. Claude Fable 5.2 and Claude Mythos 5.2 support computer use through the toolset. A request to either model that declares a `computer_20251124` tool returns a 400 `invalid_request_error` on every platform except Amazon Bedrock. There, both models accept the earlier tool: with the InvokeModel API, send `computer-use-2025-11-24` in the `anthropic_beta` array of the request body.

6767

6868To move an existing integration, follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

6969

from line 87

8787* **Effort:** all five [effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels): `low`, `medium`, `high`, `xhigh`, and `max`. The API default is `high`. Start there, because most of the gain in capability is already present at `high`. Step up to `xhigh` for your hardest long-running coding and agentic work, where you’ve measured a gain. Reserve `max` for measuring the model’s ceiling and for the rare task where time and tokens don’t matter. See [Recommended effort levels for Claude Fable 5.2](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-2).

8888* **Compaction on demand (beta):** with the `compact-2026-09-04` beta header, you choose when to replace older turns with a summary. See [Compaction on demand](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand).

8989* **Mid-conversation tool changes (beta):** you add or remove tools in a `role: "system"` message instead of editing `tools`. On the Claude API, Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed), send the `inline-tools-2026-09-15` beta header. The `mid-conversation-tool-changes-2026-07-01` header works for changes that name a tool by reference, on the platforms that [Mid-conversation system messages and tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) lists. See [Mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes).

90* **Computer use:** through the `computer_toolset_20260801` toolset. The earlier `computer_20251124` tool returns a 400 error on every platform except Amazon Bedrock, where both models also accept the earlier tool (see the [computer use breaking change](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#computer-20251124-is-not-supported)). See [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool).

90* **Computer use:** through the `computer_toolset_20260801` toolset. The earlier `computer_20251124` tool returns a 400 error on every platform except Amazon Bedrock. There, Claude Fable 5.2 and Claude Mythos 5.2 also accept the earlier tool. See the [computer use breaking change](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#computer-20251124-is-not-supported) and [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool).

9191

9292Compaction on demand and mid-conversation tool changes help you keep the history append-only, which the [prefix check](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#editing-earlier-turns-invalidates-thinking-blocks) requires. See each feature’s page for model and platform availability.

9393

94[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Fable 5.2 in Messages API requests on the Claude API.

94[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Fable 5.2 in Messages API requests on the Claude API, [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). On Claude in Microsoft Foundry, it’s available for deployments hosted on Anthropic, with its own model ID, `claude-fable-5-2-fast`.

9595

96Fast mode is also available for Claude Fable 5.2 on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).

97

98Fast mode is also available for Claude Fable 5.2 on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed).

99

100Fast mode is also available for Claude Fable 5.2 on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Anthropic, as a separate model, `claude-fable-5-2-fast`.

101

10296Fast mode is also available for Claude Mythos 5.2 in Messages API requests on the Claude API. [Availability of fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode#feature-availability) lists every platform where Claude Mythos 5.2 has fast mode.

10397

10498### Thinking blocks stay with the account that produced them

from line 108

114108* **What the prompt says about code ownership matters.** In Anthropic’s testing on small coding tasks, when a prompt said nothing about who owns the code, the model tended to add to the existing structure and to report nearby problems instead of fixing them. See [Say who owns the code](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#say-who-owns-the-code).

115109* **Long runs of tool calls can pass with little user-facing text.** The model might also make its first tool call without saying what it’s about to do. See [Keep users informed during long turns](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#keep-users-informed-during-long-turns).

116110* **How much the model delegates to subagents depends on your harness and tasks.** In an agentic coding product whose prompts invite delegation, the model delegates readily. Subagents can account for a large part of what a session costs. See [Set expectations for subagents](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#set-expectations-for-subagents).

117* **The model follows style rules closely.** A hard limit on sentence length can make the model’s prose choppy. See [Review instructions written for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

111* **The model follows style rules closely.** A hard limit on sentence length can make the model’s prose choppy. See [Review prompts and harnesses designed for earlier models](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#review-instructions-written-for-earlier-models).

118112

119113## Refusals, fallback, and billing

120114

from line 126

132126| ---------- | --------------- | --------------- | ------------ | ---------- |

134128

135Input and output cost less than on Claude Fable 5.1 and Claude Mythos 5.1, which cost $10 USD per million input tokens and $50 USD per million output tokens. Cache reads (hits and refreshes) cost 0.025 times the base input price, the same multiplier as on those models. [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) is $4 USD per million input tokens and $20 USD per million output tokens. [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Fable 5.2 costs $16 USD per million input tokens and $80 USD per million output tokens. See [Fast mode pricing](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing). Fast mode for Claude Mythos 5.2 costs $16 USD per million input tokens and $80 USD per million output tokens. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for data residency and tool pricing.

129Input and output cost less than on Claude Fable 5.1 and Claude Mythos 5.1. Claude Fable 5.1 and Claude Mythos 5.1 cost $10 USD per million input tokens and $50 USD per million output tokens. Cache reads (hits and refreshes) cost 0.025 times the base input price, the same multiplier as on those models. [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) is $4 USD per million input tokens and $20 USD per million output tokens. [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Fable 5.2 and Claude Mythos 5.2 costs $16 USD per million input tokens and $80 USD per million output tokens. See [Fast mode pricing](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing). See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for data residency and tool pricing.

136130

137131## Availability

138132

from line 133

139133Claude Fable 5.2 is available on:

140134

141135* **Claude API:** all customers, as `claude-fable-5-2`

142* **AWS:** [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-fable-5-2`, and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), as `claude-fable-5-2`

136* **AWS:** [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), as `claude-fable-5-2`

137* **Amazon Bedrock:** `global.anthropic.claude-fable-5-2` or `us.anthropic.claude-fable-5-2`, on the [`bedrock-runtime` endpoint](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids) only

143138* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `claude-fable-5-2`, and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), as `claude-fable-5-2`

144139* **Microsoft Foundry:** [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), as `claude-fable-5-2`, on Anthropic infrastructure (see [Hosting options](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options))

145140

from line 141

146141Claude Mythos 5.2 is available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). It’s available on:

147142

148143* **Claude API:** as `claude-mythos-5-2`

149* **AWS:** [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-mythos-5-2`

144* **Amazon Bedrock:** `global.anthropic.claude-mythos-5-2` or `us.anthropic.claude-mythos-5-2`, on the [`bedrock-runtime` endpoint](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids) only

150145* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `claude-mythos-5-2`, and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), as `claude-mythos-5-2`

151146* **Microsoft Foundry:** [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), as `claude-mythos-5-2`, on Anthropic infrastructure

152147

models/haiku-4-5/overview Changed · +18 / -18 lines

from line 35

3535

3636### Model IDs

3737

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------- |

40| Claude API | `claude-haiku-4-5-20251001` |

41| Claude API alias | `claude-haiku-4-5` |

42| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-4-5` |

43| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-haiku-4-5-20251001-v1:0` |

44| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-haiku-4-5@20251001` |

45| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-4-5` |

46| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-haiku-4-5` |

47| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-haiku-4-5-20251001` |

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------ |

40| Claude API | `claude-haiku-4-5-20251001` |

41| Claude API alias | `claude-haiku-4-5` |

42| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-4-5` |

43| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-haiku-4-5-20251001-v1:0` |

44| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-haiku-4-5@20251001` |

45| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-4-5` |

46| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-haiku-4-5` |

47| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-haiku-4-5-20251001` |

4848

4949### Pricing

5050

from line 73

7373

7474### Availability

7575

76| Feature | Value |

77| :---------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

79| Released | October 15, 2025 |

80| Retirement | Not sooner than October 15, 2026 |

81| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

76| Feature | Value |

77| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

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

79| Released | October 15, 2025 |

80| Retirement | Not sooner than October 15, 2026 |

81| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8282

8383## Good to know

8484

from line 125

125125 Lifecycle status and retirement commitments for every Claude model.

126126 </Card>

127127

128 <Card title="Amazon Bedrock (Opus 4.6 and earlier)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

129 Claude Haiku 4.5 is also available through the InvokeModel Bedrock integration and Bedrock-style model IDs.

128 <Card title="Amazon Bedrock (bedrock-runtime)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

129 Claude Haiku 4.5 is also on the `bedrock-runtime` endpoint (the InvokeModel and Converse APIs), with Bedrock-style model IDs.

130130 </Card>

131131</CardGroup>

132132

models/haiku-5-5/migration-guide Changed · +11 / -2 lines

from line 109

109109

110110Claude Haiku 5.5 accepts a forced `tool_choice` (`any` or a named tool), but the response starts with the tool call and has no `thinking` block. To let the model think before it calls a tool, use `tool_choice: {"type": "auto"}` and say in the prompt when to use the tool.

111111

112Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models. So a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn’t read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5’s blocks, as do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

112A conversation that you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. For other switches, it depends on the two models:

113113

114| Switch | Keeps its reasoning |

115| ---------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |

116| To Claude Haiku 5.5, from Claude Haiku 4.5 or earlier, Claude Sonnet 5 or earlier, or Claude Opus 4.8 or earlier | Yes |

117| To Claude Haiku 5.5, from any other model | No. The API drops that model’s thinking blocks without an error. |

118| From Claude Haiku 5.5, to Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.2, or Claude Mythos 5.2 | Yes, on the Claude API and Claude Models on Google Cloud (Google managed) only |

119| From Claude Haiku 5.5, to any other model | No |

120

121See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models). For switches that don’t involve Claude Haiku 5.5, see [Which model switches keep the reasoning on the Claude API](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#which-model-switches-keep-reasoning).

122

114123## Remove sampling parameters

115124

116125On Claude Haiku 5.5, omit `temperature`, `top_p`, and `top_k` and use prompting to guide the model’s behavior instead.

from line 149

140149

141150## Keep earlier turns unchanged

142151

143A Claude Haiku 5.5 thinking block stays valid only while everything sent before it is unchanged: the `system` prompt, the `tools`, and every earlier message. Claude Haiku 4.5 doesn’t run the prefix check. Keep conversations append-only. A request that sends a block back after such a change and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. On accounts created before that date, the request gets the error only when it sets the field to `"error"`. For the changes that trigger the error and what to do instead, see [Who the prefix check affects](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#who-is-affected).

152A Claude Haiku 5.5 thinking block stays valid only while everything sent before it is unchanged: the `system` prompt, the `tools`, and every earlier message. Claude Haiku 4.5 doesn’t run the prefix check. Keep conversations append-only. A request that sends a block back after such a change, with `thinking.block_binding.prefix_mismatch_behavior` unset, gets a 400 error. This applies to accounts created on or after August 31, 2026, 00:00 UTC. On accounts created before that date, the request might or might not get the error. For the changes that trigger the error and what to do instead, see [Who the prefix check affects](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#who-is-affected).

144153

145154## Migrating to Claude Haiku 5.5 from Claude Haiku 3.5 and earlier Haiku models

146155

models/mythos-5-2/overview Changed · +13 / -13 lines

from line 38

3838

3939### Model IDs

4040

41| Platform | Model ID |

42| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------- |

43| Claude API | `claude-mythos-5-2` |

44| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-mythos-5-2` |

45| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-mythos-5-2` |

46| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-mythos-5-2` |

47| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-mythos-5-2` |

41| Platform | Model ID |

42| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------- |

43| Claude API | `claude-mythos-5-2` |

44| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-mythos-5-2` |

45| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-mythos-5-2` |

46| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-mythos-5-2` |

47| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-mythos-5-2` |

4848

4949### Pricing

5050

from line 74

7474

7575### Availability

7676

77| Feature | Value |

78| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

80| Released | November 9, 2026 |

81| Retirement | Not sooner than November 9, 2027 |

82| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

77| Feature | Value |

78| :---------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

80| Released | November 9, 2026 |

81| Retirement | Not sooner than November 9, 2027 |

82| Platforms | Claude API, [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8383

8484## Reference

8585

models/opus-4-5/overview Changed · +17 / -17 lines

from line 35

3535

3636### Model IDs

3737

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------- |

40| Claude API | `claude-opus-4-5-20251101` |

41| Claude API alias | `claude-opus-4-5` |

42| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-opus-4-5-20251101-v1:0` |

43| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-opus-4-5@20251101` |

44| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-opus-4-5` |

45| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-opus-4-5` |

46| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-opus-4-5-20251101` |

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------- |

40| Claude API | `claude-opus-4-5-20251101` |

41| Claude API alias | `claude-opus-4-5` |

42| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-opus-4-5-20251101-v1:0` |

43| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-opus-4-5@20251101` |

44| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-opus-4-5` |

45| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-opus-4-5` |

46| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-opus-4-5-20251101` |

4747

4848### Pricing

4949

from line 72

7272

7373### Availability

7474

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

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

78| Released | November 24, 2025 |

79| Retirement | Not sooner than November 24, 2026 |

80| Platforms | Claude API, [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

78| Released | November 24, 2025 |

79| Retirement | Not sooner than November 24, 2026 |

80| Platforms | Claude API, [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8181

8282## Resources

8383

from line 114

114114 Lifecycle status and retirement commitments for every Claude model.

115115 </Card>

116116

117 <Card title="Amazon Bedrock (Opus 4.6 and earlier)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

118 Claude Opus 4.5 uses the InvokeModel Bedrock integration and Bedrock-style model IDs.

117 <Card title="Amazon Bedrock (bedrock-runtime)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

118 Claude Opus 4.5 is on the `bedrock-runtime` endpoint (the InvokeModel and Converse APIs), with Bedrock-style model IDs.

119119 </Card>

120120</CardGroup>

121121

models/opus-4-6/overview Changed · +16 / -16 lines

from line 35

3535

3636### Model IDs

3737

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------- |

40| Claude API | `claude-opus-4-6` |

41| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-opus-4-6-v1` |

42| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-opus-4-6` |

43| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-opus-4-6` |

44| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-opus-4-6` |

45| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-opus-4-6` |

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------ |

40| Claude API | `claude-opus-4-6` |

41| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-opus-4-6-v1` |

42| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-opus-4-6` |

43| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-opus-4-6` |

44| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-opus-4-6` |

45| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-opus-4-6` |

4646

4747### Pricing

4848

from line 72

7272

7373### Availability

7474

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

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

78| Released | February 5, 2026 |

79| Retirement | Not sooner than February 5, 2027 |

80| Platforms | Claude API, [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

78| Released | February 5, 2026 |

79| Retirement | Not sooner than February 5, 2027 |

80| Platforms | Claude API, [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8181

8282## Resources

8383

from line 114

114114 Lifecycle status and retirement commitments for every Claude model.

115115 </Card>

116116

117 <Card title="Amazon Bedrock (Opus 4.6 and earlier)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

118 Claude Opus 4.6 uses the InvokeModel Bedrock integration and Bedrock-style model IDs.

117 <Card title="Amazon Bedrock (bedrock-runtime)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

118 Claude Opus 4.6 is on the `bedrock-runtime` endpoint (the InvokeModel and Converse APIs), with Bedrock-style model IDs.

119119 </Card>

120120</CardGroup>

121121

models/opus-5-5/migration-guide Changed · +59 / -61 lines

from line 16

1616

1717This page lists the code changes for moving to Claude Opus 5.5 from [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-47), [Claude Opus 4.6 and earlier Opus models](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-46), or [Claude Sonnet 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-sonnet-5). Every reader needs [What every request to Claude Opus 5.5 must satisfy](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#request-requirements) and [Handle thinking in every response](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-in-every-response). Then go to the section for your current model: its first sentence names the other sections that apply to you. The [migration checklist](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migration-checklist) lists every change by starting model.

1818

19Claude Opus 5.5 costs less than Claude Opus 5 ($4 / $20 USD per million input / output tokens, compared with $5 / $25 USD; see [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing)). For feature support, see [What’s new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#feature-support). For behavioral differences and model-specific prompting patterns, see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5).

19Claude Opus 5.5 costs less than Claude Opus 5 ($4 / $20 USD per million input / output tokens, compared with $5 / $25 USD; see [Pricing](https://platform.claude.com/docs/en/about-claude/pricing)). For feature support, see [What’s new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#feature-support). For behavioral differences and model-specific prompting patterns, see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5).

2020

2121## What every request to Claude Opus 5.5 must satisfy

2222

from line 29

2929* **Sampling parameters:** Omit `temperature`, `top_p`, and `top_k`. Use prompting to guide the model’s behavior.

3030* **Prefill:** Don’t end `messages` with a prefilled assistant turn: it is rejected. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) or system prompt instructions instead.

3131* **Computer use:** Declare computer use as the `computer_toolset_20260801` toolset. On Amazon Bedrock, `computer_20251124` also works. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).

32* **Context window:** No context-window beta header is needed. The [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is the default, and a header sent for older models has no effect.

32* **Context window:** The [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is the default. A context-window beta header sent for older models has no effect.

3333

3434The following request satisfies every item in the list: effort is set, and there is no `thinking` field. Where the example prints text, it finds the text block by its type, because `thinking` blocks come first.

3535

from line 148

148148 ```

149149

150150 ```java Java

151 import com.anthropic.models.messages.OutputConfig;

151 AnthropicClient client = AnthropicOkHttpClient.fromEnv();

152152

153 void main() {

154 AnthropicClient client = AnthropicOkHttpClient.fromEnv();

153 MessageCreateParams params = MessageCreateParams.builder()

154 .model(Model.CLAUDE_OPUS_5_5)

155 .maxTokens(4096L)

156 .addUserMessage("Analyze the trade-offs between microservices and monolithic architectures")

157 .outputConfig(OutputConfig.builder()

158 .effort(OutputConfig.Effort.MEDIUM)

159 .build())

160 .build();

155161

156 MessageCreateParams params = MessageCreateParams.builder()

157 .model(Model.CLAUDE_OPUS_5_5)

158 .maxTokens(4096L)

159 .addUserMessage("Analyze the trade-offs between microservices and monolithic architectures")

160 .outputConfig(OutputConfig.builder()

161 .effort(OutputConfig.Effort.MEDIUM)

162 .build())

163 .build();

164

165 Message response = client.messages().create(params);

166 response.content().stream()

167 .flatMap(block -> block.text().stream())

168 .forEach(textBlock -> IO.println(textBlock.text()));

169 }

162 Message response = client.messages().create(params);

163 response.content().stream()

164 .flatMap(block -> block.text().stream())

165 .forEach(textBlock -> IO.println(textBlock.text()));

170166 ```

171167

172168 ```php PHP

from line 173

177173 messages: [

178174 ['role' => 'user', 'content' => 'Analyze the trade-offs between microservices and monolithic architectures']

179175 ],

180 model: 'claude-opus-5-5',

176 model: Model::CLAUDE_OPUS_5_5,

181177 outputConfig: ['effort' => 'medium'],

182178 );

183179

184180 foreach ($message->content as $block) {

185 if ($block->type === 'text') {

181 if ($block instanceof \Anthropic\Messages\TextBlock) {

186182 echo $block->text, PHP_EOL;

187183 }

188184 }

from line 199

203199 )

204200

205201 message.content.each do |block|

206 puts block.text if block.type == :text

202 puts block.text if block.is_a?(Anthropic::Models::TextBlock)

207203 end

208204 ```

209205</CodeGroup>

from line 275

279275* Remove `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}`; choose an effort level instead.

280276* Set `effort` explicitly: the default is `medium`, where Claude Opus 5’s is `high`.

281277* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.

282* If you use an earlier computer use tool version, declare `computer_toolset_20260801` (no beta header) instead and update your agent loop for the toolset. On Amazon Bedrock, `computer_20251124` also works.

283* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5’s thinking blocks. Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them. So do Claude Fable 5.2 and Claude Mythos 5.2 there. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. Claude Opus 5.5 itself reads thinking from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads thinking from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read thinking from Claude Fable or Claude Mythos models.

278* If you use an earlier computer use tool version, declare `computer_toolset_20260801` instead, drop that version’s beta header, and update your agent loop for the toolset. On Amazon Bedrock, `computer_20251124` also works. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).

279* If a router or fallback can move a conversation off Claude Opus 5.5, expect the new model to run without Claude Opus 5.5’s thinking blocks. Claude Fable 5.1 and Claude Mythos 5.1 keep them on the Claude API. Claude Fable 5.2 and Claude Mythos 5.2 keep them on the Claude API and Claude Models on Google Cloud (Google managed). Claude Opus 5.5 itself reads thinking from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads thinking from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read thinking from Claude Fable or Claude Mythos models.

284280* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.

285* If your interface renders text between tool calls, set `display: "updates"` (beta) or `"summarized"` and render the non-empty `thinking` blocks.

281* If your interface renders text between tool calls, set `display: "updates"` (in beta) or `"summarized"` and render the non-empty `thinking` blocks.

286282* If your code edits earlier turns, the `system` prompt, or `tools` mid-conversation, follow [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).

287283* Handle `stop_reason: "refusal"` and configure fallback.

288284* Re-baseline cost and latency at your chosen effort level.

from line 291

295291* Review prompts near the caching minimum: prompts of 512 tokens or more can create cache entries.

296292* If your organization has a [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) commitment, plan capacity separately: Priority Tier is not supported on Claude Opus 5.5.

297293* If you run at `xhigh` or `max` effort, raise `max_tokens` to at least 64k as a starting point.

298* For agentic workloads, consider [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta) and mid-conversation tool changes (beta).

294* For agentic workloads, consider [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) and mid-conversation tool changes. Both are in beta.

299295

300296### Claude Opus 4.7 or earlier

301297

from line 299

303299* Remove any context-window beta header.

304300* If you rebuild conversation history to update instructions, consider switching to a mid-conversation system message to preserve prompt cache hits.

305301* Verify your stop-reason handling reads `stop_details` on refusals.

306* If you want fast mode, which Claude Opus 4.7 rejects, set `speed: "fast"` on your Claude API requests. Claude Opus 5.5 doesn’t need a beta header.

302* If you want fast mode, which Claude Opus 4.7 rejects, set `speed: "fast"` on your Claude API requests.

307303

308304### Claude Opus 4.6 or earlier

309305

from line 587

591587 }

592588 }],

593589 "tool_choice": {"type": "tool", "name": "get_weather"},

594 "messages": [{"role": "user", "content": "What'\''s the weather in Paris?"}]

590 "messages": [{"role": "user", "content": "What is the weather in Paris?"}]

595591 }'

596592 ```

597593

from line 722

726722 "tool_choice": {"type": "auto"},

727723 "messages": [{

728724 "role": "user",

729 "content": "What'\''s the weather in Paris? Use the get_weather tool."

725 "content": "What is the weather in Paris? Use the get_weather tool."

730726 }]

731727 }'

732728 ```

from line 872

876872

877873#### Thinking blocks are tied to the model and the conversation

878874

879On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks. So do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. No other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In the other direction, Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads them from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read them from Claude Fable or Claude Mythos models. Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid; Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. On accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms, a request that replays a thinking block after such an edit and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).

875Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks on the Claude API. Claude Fable 5.2 and Claude Mythos 5.2 read them on the Claude API and Claude Models on Google Cloud (Google managed). No other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them.

880876

877In the other direction, Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads them from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read them from Claude Fable or Claude Mythos models.

878

879Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid. Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. If a request replays a thinking block after such an edit, with `thinking.block_binding.prefix_mismatch_behavior` unset, it gets a 400 error. This applies to accounts created on or after August 31, 2026, 00:00 UTC. [Preserved thinking availability](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#feature-availability) lists the platforms where this applies. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).

880

881881#### Some computer use tool versions are not supported

882882

883883Claude Opus 5.5 supports computer use through the `computer_toolset_20260801` toolset. On Amazon Bedrock, Claude Opus 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. Claude Opus 5.5 returns a 400 error for any computer use tool version it doesn’t accept, such as `computer_20251124` on the Claude API. It doesn’t accept `computer_20250124` on any platform. On the Claude API, the error message begins `'claude-opus-5-5' does not support tool types: computer_20251124.` and then lists the tool types the model accepts.

from line 907

907907 ```

908908

909909 ```bash CLI

910 ant beta:messages create \

911 --model claude-opus-5 \

912 --max-tokens 4096 \

913 --beta computer-use-2025-11-24 \

914 --tool '{

915 type: computer_20251124,

916 name: computer,

917 display_width_px: 1024,

910 ant beta:messages create --beta computer-use-2025-11-24 <<'YAML'

911 model: claude-opus-5

912 max_tokens: 4096

913 tools:

914 - type: computer_20251124

915 name: computer

916 display_width_px: 1024

918917 display_height_px: 768

919 }' \

920 --message '{role: user, content: "Open the display settings."}'

918 messages:

919 - role: user

920 content: Open the display settings.

921 YAML

921922 ```

922923

923924 ```python Python

from line 1151

11501151

11511152### Recommended changes

11521153

11531. **Re-run your effort sweep.** Effort is the only thinking control on Claude Opus 5.5, and its default is `medium` where Claude Opus 5’s is `high`, so a request that omits `effort` now runs at `medium`. Step down where quality holds, and step up for the most demanding work. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).

11541. **Re-run your effort sweep.** Effort is the only thinking control on Claude Opus 5.5, and its default is `medium` where Claude Opus 5’s is `high`, so a request that omits `effort` runs at `medium`. Step down where quality holds, and step up for the most demanding work. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).

115411552. **Re-evaluate model-specific prompt instructions.** Instructions tuned for Claude Opus 5’s behavior might no longer be needed; see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5). If you ran with thinking disabled, also see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled).

115511563. **Test in a development environment** before switching production traffic.

11561157

from line 1175

11741175

11751176### Recommended changes

11761177

1177These are not required but will improve your experience:

1178These changes are optional, and they can improve your experience:

11781179

117911801. **Consider task budgets (beta):** For agentic workloads, [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) tell the model how many tokens it has for a full agentic loop. They require the `task-budgets-2026-03-13` beta header.

11801181

from line 1193

11921193

119311941. **Effort levels recalibrated:** The token allocation behind each effort level changes on Claude Opus 5.5 compared to Claude Opus 4.7. The default is `medium`, where Claude Opus 4.7’s is `high`. Run a fresh effort sweep on your own evals rather than carrying over a setting tuned for Claude Opus 4.7. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).

11941195

11952. **1M context window is the default:** Claude Opus 5.5 serves the full 1M token [context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default with no beta header. If your client passes a context-window beta header for compatibility with older models, remove it.

11962. **1M context window is the default:** Claude Opus 5.5 serves the full 1M token [context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default. If your client passes a context-window beta header for compatibility with older models, remove it.

11961197

119711983. **Mid-conversation system messages:** On the Claude API, Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed), and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 accepts `role: "system"` messages immediately after a user turn in the `messages` array (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)). Use the top-level `system` field for instructions that apply from the start. Claude Opus 4.7 rejects `role: "system"` in `messages` with a 400 error. If you maintain code paths that rebuild the full message history to update instructions, you can simplify them and preserve [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) hits on earlier turns.

11981199

11994. **Refusal stop details:** When the model declines a request, Claude Opus 5.5 returns a `stop_details` object that names the category of refusal, alongside the `refusal` stop reason. Claude Opus 4.7 returns the same object, so this matters only if your stop-reason handling does not read it yet. No beta header is required, and there is no opt-out. If your stop-reason handling doesn’t read it yet, see [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons). Claude Opus 5.5 declines in more categories; see [Safety classifiers and fallback](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#safety-classifiers-and-fallback).

12004. **Refusal stop details:** When the model declines a request, Claude Opus 5.5 returns a `stop_details` object that names the category of refusal, alongside the `refusal` stop reason. Claude Opus 4.7 returns the same object, so this matters only if your stop-reason handling does not read it yet; if so, see [Stop reasons and fallback](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons). There is no opt-out. Claude Opus 5.5 declines in more categories; see [Safety classifiers and fallback](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#safety-classifiers-and-fallback).

12001201

12015. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on the Claude API. Fast mode is not available on Claude Opus 4.7, where requests with `speed: "fast"` return an error. Set `speed: "fast"` on your requests. Claude Opus 5.5 doesn’t need a beta header.

12025. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on the Claude API. Fast mode is not available on Claude Opus 4.7, where requests with `speed: "fast"` return an error. Set `speed: "fast"` on your requests.

12021203

120312046. **Computer use toolset and browser use tool:** Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages. Claude Opus 4.7 supports neither. To move a `computer_20251124` integration to the toolset, see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).

12041205

from line 1269

12681269 ```

12691270

12701271 ```csharp C#

1271 using Anthropic;

1272 using Anthropic.Models.Messages;

1273

12741272 AnthropicClient client = new();

12751273

12761274 var parameters = new MessageCreateParams

from line 1320

13221320 $message = $client->messages->create(

13231321 maxTokens: 16000,

13241322 messages: [['role' => 'user', 'content' => '...']],

1325 model: 'claude-opus-4-6',

1326 thinking: ['type' => 'enabled', 'budget_tokens' => 10000],

1323 model: Model::CLAUDE_OPUS_4_6,

1324 thinking: ['type' => 'enabled', 'budgetTokens' => 10000],

13271325 );

13281326 ```

13291327

from line 1329

13311329 client = Anthropic::Client.new

13321330

13331331 message = client.messages.create(

1334 model: "claude-opus-4-6",

1332 model: Anthropic::Model::CLAUDE_OPUS_4_6,

13351333 max_tokens: 16000,

13361334 thinking: {

13371335 type: "enabled",

from line 1403

14051403 ```

14061404

14071405 ```csharp C#

1408 using Anthropic;

1409 using Anthropic.Models.Messages;

1410

14111406 AnthropicClient client = new();

14121407

14131408 var parameters = new MessageCreateParams

from line 1512

15171512

151815133. **High-resolution image support:** Claude Opus 4.7 is the first Claude model with high-resolution image support. Maximum image resolution is 2,576 pixels on the long edge, up from 1,568 pixels on prior models. This unlocks gains on vision-heavy workloads and is particularly valuable for computer use, screenshot understanding, and document analysis.

15191514

1520 High-resolution support is automatic and requires no beta header or client-side opt-in. Two things to plan for:

1515 High-resolution support is automatic. Plan for two things:

15211516

15221517 * Full-resolution images can use up to approximately 3x more image tokens than on prior models (up to 4,784 tokens for each image, compared to the previous cap of roughly 1,600 tokens). Re-budget `max_tokens` and cost expectations for image-heavy workloads, or downsample before sending if you do not need the additional fidelity.

15231518 * Pointing and bounding-box coordinates returned by the model are 1:1 with actual image pixels on Claude Opus 4.7, so no scale-factor conversion is required.

from line 1547

15521547

15531548### Migrating from Claude 4.1 or earlier

15541549

1555If you’re migrating from Claude Opus 4.1 or earlier models directly to Claude Opus 5.5, first apply everything in [Migrating from Claude Opus 4.5 or earlier](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-45). That subsection starts with every earlier section, so in effect you read this page from the top. Then apply the additional changes in this subsection.

1550To migrate from Claude Opus 4.1 or earlier models directly to Claude Opus 5.5:

15561551

15521. Work through this page from the top, in page order, up to and including [Migrating from Claude Opus 4.5 or earlier](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-45).

15532. Apply the additional changes in this subsection.

1554

15571555#### Additional breaking changes

15581556

155915571. **Remove sampling parameters:** Covered in [Sampling parameters removed](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#opus-46-breaking-changes).

from line 1622

16241622

16251623 ```ruby Ruby

16261624 # Before

1627 legacy_tools = [{type: "text_editor_20250124", name: "str_replace_editor"}]

1625 legacy_tools = [{ type: "text_editor_20250124", name: "str_replace_editor" }]

16281626

16291627 # After

1630 tools = [{type: "text_editor_20250728", name: "str_replace_based_edit_tool"}]

1628 tools = [{ type: "text_editor_20250728", name: "str_replace_based_edit_tool" }]

16311629 ```

16321630 </CodeGroup>

16331631

models/opus-5-5/whats-new-opus-5-5 Changed · +22 / -9 lines

from line 19

1919| --------------- | --------------- | -------------------------------------------------- |

2020| Claude Opus 5.5 | claude-opus-5-5 | For long-running agentic coding and knowledge work |

2121

22[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is always on, and the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) controls thinking depth; its default on this model is `medium`. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Opus 5.5 model page](https://platform.claude.com/docs/en/models/opus-5-5/overview); for all current models, see the [models overview](https://platform.claude.com/docs/en/models/overview).

22[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is always on, and the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) controls thinking depth; its default on this model is `medium`. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) model page; for all current models, see [Models overview](https://platform.claude.com/docs/en/models/overview).

2323

2424## Breaking changes

2525

2626### Thinking can’t be disabled

2727

28On Claude Opus 5, thinking is on by default and `thinking: {"type": "disabled"}` is accepted at effort `high` or below. On Claude Opus 5.5, thinking is always on: a request that sets `thinking: {"type": "disabled"}`, or a manual budget with `thinking: {"type": "enabled", "budget_tokens": N}`, returns a 400 `invalid_request_error`. Omit the `thinking` field, or send `thinking: {"type": "adaptive"}`, which is equivalent. No beta header is involved.

28On Claude Opus 5, thinking is on by default and `thinking: {"type": "disabled"}` is accepted at effort `high` or below. On Claude Opus 5.5, thinking is always on: a request that sets `thinking: {"type": "disabled"}`, or one that sets a manual budget with `thinking: {"type": "enabled", "budget_tokens": N}`, returns a 400 `invalid_request_error`. Omit the `thinking` field, or send `thinking: {"type": "adaptive"}`, which is equivalent.

2929

3030The error messages are:

3131

from line 51

5151

5252### Thinking blocks are tied to the model and the conversation

5353

54Every thinking block records which model produced it, and each model reads its own blocks and only some other models’. Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads blocks from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read blocks from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5. So do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. No other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. So does one that moves from Claude Opus 5.5 up to Claude Fable 5.2 or Claude Mythos 5.2 on the Claude API. One that moves from Claude Opus 5.5 to any model other than those four runs the turns after the switch without the previous model’s reasoning. So does one that moves onto Claude Opus 5.5 from a Claude Fable or Claude Mythos model. When a request carries a block the target model can’t read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

54Every thinking block records which model produced it. A conversation that switches models keeps its earlier reasoning only if the model that it switches to can read the earlier model’s thinking blocks:

5555

56The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. Keep the conversation append-only: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. A request that replays a block after such a change and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. This applies on the Claude API and on cloud platforms. On accounts created before that date, the request gets the error only when it sets the field to `"error"`. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set the field to `"drop_block"`. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).

56| Switch | Keeps its reasoning |

57| ------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |

58| To Claude Opus 5.5, from Claude Opus 5 or earlier, Claude Sonnet 5 or earlier, or Claude Haiku 4.5 or earlier | Yes |

59| To Claude Opus 5.5, from Claude Sonnet 5.5 or Claude Haiku 5.5 | Yes, on the Claude API and Claude Models on Google Cloud (Google managed) only |

60| To Claude Opus 5.5, from a Claude Fable or Claude Mythos model | No |

61| From Claude Opus 5.5, to Claude Fable 5.2 or Claude Mythos 5.2 | Yes, on the Claude API and Claude Models on Google Cloud (Google managed) only |

62| From Claude Opus 5.5, to Claude Fable 5.1 or Claude Mythos 5.1 | Yes, on the Claude API only |

63| From Claude Opus 5.5, to any other model | No |

5764

65When a request carries a block the target model can’t read, the API drops it before the model sees it. The request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models). For switches that don’t involve Claude Opus 5.5, see [Which model switches keep the reasoning on the Claude API](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#which-model-switches-keep-reasoning).

66

67The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. Keep the conversation append-only: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits.

68

69A request that replays a block after such a change, with `thinking.block_binding.prefix_mismatch_behavior` unset, gets a 400 error. This applies to accounts created on or after August 31, 2026, 00:00 UTC. [Preserved thinking availability](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#feature-availability) lists the platforms where this applies. On accounts created before that date, the request might or might not get the error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set the field to `"drop_block"`. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).

70

5871### Some computer use tool versions are not supported

5972

6073Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_toolset_20260801` toolset. On Amazon Bedrock, Claude Opus 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. Claude Opus 5.5 returns a 400 error for any computer use tool version it doesn’t accept, such as `computer_20251124` on the Claude API. The Claude API’s `invalid_request_error` message names the rejected type and, after `Did you mean one of`, lists the tool types the model accepts. The message begins:

from line 76

6376'claude-opus-5-5' does not support tool types: computer_20251124.

6477```

6578

66Integrations that use the toolset need no change. To move a `computer_20251124` integration to the toolset, follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). Drop the beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. The migration guide shows the request [before and after](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).

79Integrations that use the toolset need no change. To move a `computer_20251124` integration to the toolset, follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). Drop the beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. The migration guide shows the [before and after for computer use](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).

6780

6881## Feature support

6982

70Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). See each feature’s page for model availability.

83Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort-per-message) (in beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side tools (see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview)). See each feature’s page for model availability.

7184

7285### Fast mode

7386

74[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Opus 5.5 on the Claude API, on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure. On the Claude API and on Claude Models on Google Cloud (Anthropic managed), set `speed: "fast"` on your request. Claude Opus 5.5 doesn’t need a beta header. See [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for supported models, rate limits, and pricing.

87[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Opus 5.5 on the Claude API, on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure. On the Claude API and on Claude Models on Google Cloud (Anthropic managed), set `speed: "fast"` on your request. See [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for supported models, rate limits, and pricing.

7588

7689### Define tools in a message (beta)

7790

from line 119

106119Claude Opus 5.5 is available on:

107120

108121* **Claude API:** all customers, as `claude-opus-5-5`

109* **AWS:** [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-opus-5-5`, and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), as `claude-opus-5-5`

122* **AWS:** [Claude in Amazon Bedrock (`bedrock-mantle`)](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-opus-5-5`, and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), as `claude-opus-5-5`

110123* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `claude-opus-5-5`, and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), as `claude-opus-5-5`

111124* **Microsoft Foundry:** [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), as `claude-opus-5-5`

112125

from line 164

151164 ```

152165</CodeGroup>

153166

154Then remove any `thinking: {"type": "disabled"}` or `thinking: {"type": "enabled", ...}` settings and choose an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level instead. Replace `tool_choice` types `any` and `tool` with `auto` plus [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). If you use computer use through `computer_20251124`, [move to the toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, `computer_20251124` also works. If your interface shows the text between tool calls, also set `thinking.display`; see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls). See the [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide) for step-by-step instructions from Claude Opus 5 and earlier models, and the full checklist.

167Then remove any `thinking: {"type": "disabled"}` or `thinking: {"type": "enabled", ...}` settings and choose an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level instead. Replace `tool_choice` types `any` and `tool` with `auto` plus [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). If you use computer use through `computer_20251124`, [move to the toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, `computer_20251124` also works. If your interface shows the text between tool calls, also set `thinking.display`; see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls). See the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide) for step-by-step instructions from Claude Opus 5 and earlier models, and the full checklist.

155168

156169## Next steps

157170

models/overview Changed · +37 / -7 lines

## Latest models ## All models ## Compare models

from line 20

2020 Migration guide

2121</HomeQuickChip>

2222

23## Compare models

23## Latest models

2424

25If you’re unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 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.

25If you’re unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still fall short. All current models support text and image input, text output, multilingual capabilities, vision, and tool use.

2626

2828| :------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------- |

from line 39

3939| Training data cutoff | Jun 2026 | Jun 2026 | Jun 2026 | Jun 2026 |

from line 46

4747

4848* **Comparative latency:** Relative to the current lineup. Actual latency depends on prompt length, output length, and thinking effort.

49* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for cache writes, long-context, and per-platform pricing.

49* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price (2.5% on Claude Fable 5.2 and Claude Fable 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for cache writes, long-context, and per-platform pricing.

5050* **Claude API ID:** Every Claude model ID is a pinned snapshot, including the dateless IDs used from the 4.6 generation on.

5151* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual thinking.type “enabled” + budget\_tokens mode on earlier models; it is deprecated on Claude Opus 4.6 and Claude Sonnet 4.6 and not accepted on later models.

5252* **Default effort:** The effort parameter’s default on the Claude API. Set effort explicitly to use a different level.

from line 55

5555* **Reliable knowledge cutoff:** The date through which the model’s knowledge is most extensive and reliable. Training data cutoff (under Additional details) is the broader range of data used. See Anthropic’s Transparency Hub for details.

5656* **Retirement:** Anthropic’s commitment for the platforms that Anthropic operates. Partner-operated platforms set their own dates.

5757* **Claude API alias:** For models before the 4.6 generation, the alias is a convenience pointer that resolves to the dated ID. Dateless IDs are their own pinned snapshot; the alias row repeats them.

58* **Amazon Bedrock ID:** The ID on Bedrock’s Messages-API endpoint (Claude Opus 4.7 and later, plus Claude Haiku 4.5); a model offered only through Bedrock’s InvokeModel integration shows that ID instead. Bedrock offers global endpoints (dynamic routing) and regional endpoints (guaranteed data routing) for Claude Sonnet 4.5 and later, and sets its own lifecycle dates.

58* **Amazon Bedrock ID:** The ID on Bedrock’s bedrock-mantle endpoint; a model that Bedrock serves only on its bedrock-runtime endpoint shows its inference profile ID instead. Bedrock offers global endpoints (dynamic routing) and regional endpoints (guaranteed data routing) for Claude Sonnet 4.5 and later, and sets its own lifecycle dates.

5959* **Claude Models on Google Cloud (Google managed) ID:** Claude Models on Google Cloud (Google managed) offers global, multi-region, and regional endpoints, and sets its own lifecycle dates.

6060* **Microsoft Foundry ID:** Foundry deployments default to the Claude API model ID (the alias, where one exists); the deployment name is what you send. Foundry follows the Claude API lifecycle schedule.

6161* **Claude Platform on AWS ID:** Claude Platform on AWS uses the Claude API model IDs (the dateless form where the Claude API has an alias), not Bedrock-style IDs, and follows Anthropic’s first-party model lifecycle.

from line 62

6262

6363See [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).

6464

65Legacy models (still available): [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [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 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 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview).

65Once 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).

6666

67Once 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).

67## All models

68

69Older models might still be available, but where possible, you should default to the [latest models](https://platform.claude.com/docs/en/models/overview#latest-models-comparison). To move to a newer model, see the [migration guides](https://platform.claude.com/docs/en/about-claude/models/migration-guide). For retirement dates, see [model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).

70

72| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------- | :----------------------- | :----------------- | :------------------ |

94

95* **MTok:** Million tokens. $5 / MTok is $5 for every million tokens.

96* **Limited access:** Available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). To request access, apply to the program that covers your use case.

97* **Retired:** May still be available on other cloud platforms. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for more.

6898

6999## Using the Models API

70100

models/sonnet-4-5/overview Changed · +18 / -18 lines

from line 35

3535

3636### Model IDs

3737

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------ |

40| Claude API | `claude-sonnet-4-5-20250929` |

41| Claude API alias | `claude-sonnet-4-5` |

42| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-sonnet-4-5-20250929-v1:0` |

43| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-sonnet-4-5@20250929` |

44| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-4-5` |

45| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-sonnet-4-5` |

46| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-sonnet-4-5-20250929` |

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------- |

40| Claude API | `claude-sonnet-4-5-20250929` |

41| Claude API alias | `claude-sonnet-4-5` |

42| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-sonnet-4-5-20250929-v1:0` |

43| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-sonnet-4-5@20250929` |

44| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-4-5` |

45| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-sonnet-4-5` |

46| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-sonnet-4-5-20250929` |

4747

4848### Pricing

4949

from line 72

7272

7373### Availability

7474

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

77| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Deprecated |

78| Released | September 29, 2025 |

79| Deprecated | September 30, 2026 |

80| Retires | November 30, 2026 |

81| Platforms | Claude API, [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

77| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Deprecated |

78| Released | September 29, 2025 |

79| Deprecated | September 30, 2026 |

80| Retires | November 30, 2026 |

81| Platforms | Claude API, [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8282

8383## Resources

8484

from line 115

115115 Lifecycle status and retirement commitments for every Claude model.

116116 </Card>

117117

118 <Card title="Amazon Bedrock (Opus 4.6 and earlier)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

119 Claude Sonnet 4.5 uses the InvokeModel Bedrock integration and Bedrock-style model IDs.

118 <Card title="Amazon Bedrock (bedrock-runtime)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

119 Claude Sonnet 4.5 is on the `bedrock-runtime` endpoint (the InvokeModel and Converse APIs), with Bedrock-style model IDs.

120120 </Card>

121121</CardGroup>

122122

models/sonnet-4-6/overview Changed · +16 / -16 lines

from line 35

3535

3636### Model IDs

3737

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------- |

40| Claude API | `claude-sonnet-4-6` |

41| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-sonnet-4-6` |

42| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-sonnet-4-6` |

43| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-4-6` |

44| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-sonnet-4-6` |

45| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-sonnet-4-6` |

38| Platform | Model ID |

39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------- |

40| Claude API | `claude-sonnet-4-6` |

41| [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `global.anthropic.claude-sonnet-4-6` |

42| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-sonnet-4-6` |

43| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-4-6` |

44| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-sonnet-4-6` |

45| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-sonnet-4-6` |

4646

4747### Pricing

4848

from line 72

7272

7373### Availability

7474

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

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

78| Released | February 17, 2026 |

79| Retirement | Not sooner than February 17, 2027 |

80| Platforms | Claude API, [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

75| Feature | Value |

76| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

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

78| Released | February 17, 2026 |

79| Retirement | Not sooner than February 17, 2027 |

80| Platforms | Claude API, [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

8181

8282## Resources

8383

from line 114

114114 Lifecycle status and retirement commitments for every Claude model.

115115 </Card>

116116

117 <Card title="Amazon Bedrock (Opus 4.6 and earlier)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

118 Claude Sonnet 4.6 uses the InvokeModel Bedrock integration and Bedrock-style model IDs.

117 <Card title="Amazon Bedrock (bedrock-runtime)" icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy">

118 Claude Sonnet 4.6 is on the `bedrock-runtime` endpoint (the InvokeModel and Converse APIs), with Bedrock-style model IDs.

119119 </Card>

120120</CardGroup>

121121

models/sonnet-5-5/migration-guide Changed · +16 / -16 lines

from line 16

1616/claude-api migrate this project to claude-sonnet-5-5

1717```

1818

19Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. For features and prompting, see [What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).

19Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. For features and prompting, see [What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).

2020

2121## Send a request to Claude Sonnet 5.5

2222

23This request works on Claude Sonnet 5.5 as written. It sets an effort level, and the SDK example reads the reply by block type. It leaves out five settings that return a 400 error: [thinking budgets](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#sonnet-46-breaking-changes), [sampling parameters](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#sonnet-46-breaking-changes), [assistant prefill](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-sonnet-45), [forced tool choice](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use), and [`thinking: {"type": "disabled"}`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking).

23This request works on Claude Sonnet 5.5 as written. It sets an effort level and leaves out five settings that return a 400 error: [thinking budgets](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#sonnet-46-breaking-changes), [sampling parameters](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#sonnet-46-breaking-changes), [assistant prefill](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-sonnet-45), [forced tool choice](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use), and [`thinking: {"type": "disabled"}`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking).

2424

2525<CodeGroup>

2626 ```bash cURL

from line 177

177177 messages: [

178178 ['role' => 'user', 'content' => 'Analyze the trade-offs between microservices and monolithic architectures']

179179 ],

180 model: 'claude-sonnet-5-5',

180 model: Model::CLAUDE_SONNET_5_5,

181181 outputConfig: ['effort' => 'medium'],

182182 );

183183

184184 echo "Stop reason: {$message->stopReason}", PHP_EOL;

185185 foreach ($message->content as $block) {

186 if ($block->type === 'text') {

186 if ($block instanceof \Anthropic\Messages\TextBlock) {

187187 echo $block->text, PHP_EOL;

188188 }

189189 }

from line 205

205205

206206 puts "Stop reason: #{message.stop_reason}"

207207 message.content.each do |block|

208 puts block.text if block.type == :text

208 puts block.text if block.is_a?(Anthropic::Models::TextBlock)

209209 end

210210 ```

211211</CodeGroup>

from line 239

239239To turn thinking off on this model, send "thinking": {"type": "between_tools"} instead of {"type": "disabled"}. The model does not think before responding. The short updates it writes between tool calls come back as thinking blocks.

240240```

241241

242`between_tools` works on every platform that offers Claude Sonnet 5.5, with no beta header. It’s accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max`, it returns a 400 error. To run at those levels, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. With [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), a `between_tools` request that falls back to Claude Sonnet 5 runs there with `thinking: {"type": "disabled"}`.

242`between_tools` works on every platform that offers Claude Sonnet 5.5. It’s accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max`, it returns a 400 error. To run at those levels, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. With [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), a `between_tools` request that falls back to Claude Sonnet 5 runs there with `thinking: {"type": "disabled"}`.

243243

244244With `between_tools`, effort can’t change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking. For prompting guidance, see [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking).

245245

from line 548

548548 }

549549 }],

550550 "tool_choice": {"type": "tool", "name": "get_weather"},

551 "messages": [{"role": "user", "content": "What'\''s the weather in Paris?"}]

551 "messages": [{"role": "user", "content": "What is the weather in Paris?"}]

552552 }'

553553 ```

554554

from line 683

683683 "tool_choice": {"type": "auto"},

684684 "messages": [{

685685 "role": "user",

686 "content": "What'\''s the weather in Paris? Use the get_weather tool."

686 "content": "What is the weather in Paris? Use the get_weather tool."

687687 }]

688688 }'

689689 ```

from line 840

840840

841841Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5. It doesn’t read blocks from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. The API drops blocks the model can’t read. The request still returns 200, and dropped blocks aren’t billed. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

842842

843Each Claude Sonnet 5.5 thinking block is also signed over the conversation before it. Keep conversations append-only, and change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). A request that replays a block after an edit to earlier history and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. This applies on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them or in an account linked to it. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).

843Each Claude Sonnet 5.5 thinking block is also signed over the conversation before it. Keep conversations append-only, and change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). A request can replay a block after an edit to earlier history and leave `thinking.block_binding.prefix_mismatch_behavior` unset. On accounts created on or after August 31, 2026, 00:00 UTC, that request gets a 400 error. [Preserved thinking availability](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#feature-availability) lists the platforms where this applies. Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them or in an account linked to it. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).

844844

845845### Some computer use tool versions are not supported

846846

from line 856

856856

857857### Text between tool calls is returned in thinking blocks

858858

859On Claude Sonnet 5.5, notes longer than a sentence or two that the model writes between tool calls come back as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates), empty at the default `display`. Shorter remarks stay `text`. On Claude Sonnet 5 and earlier models, all text between tool calls comes back as `text` blocks. No request fails, but an interface that shows those notes goes quiet.

859On Claude Sonnet 5.5, notes longer than a sentence or two that the model writes between tool calls come back as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates), empty at the default `display`. Shorter remarks stay `text`. On Claude Sonnet 5 and earlier models, all text between tool calls comes back as `text` blocks. No request fails, but an interface that shows those notes stops showing them.

860860

861861With adaptive thinking, set `display` to `"updates"` (beta, `thinking-display-updates-2026-08-18` header) to get the updates alone, or to `"summarized"` to get them mixed with reasoning. Render each non-empty `thinking` block before the `tool_use` block that follows it. With [`between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking), the text comes back without `display`. See [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#user-facing-progress-updates).

862862

from line 1009

10091009 $message = $client->messages->create(

10101010 maxTokens: 16000,

10111011 messages: [['role' => 'user', 'content' => '...']],

1012 model: 'claude-sonnet-4-6',

1013 thinking: ['type' => 'enabled', 'budget_tokens' => 10000],

1012 model: Model::CLAUDE_SONNET_4_6,

1013 thinking: ['type' => 'enabled', 'budgetTokens' => 10000],

10141014 );

10151015 ```

10161016

from line 1214

12141214

12151215**Effort.** Claude Sonnet 4.5 has no effort parameter. Set an effort level explicitly, as [Recommended changes](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#recommended-changes) describes.

12161216

1217**Context and output.** Claude Sonnet 5.5 has a larger context window, with no beta header, and a higher output limit. See the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. Remove any context-window beta header.

1217**Context and output.** Claude Sonnet 5.5 has a larger context window and a higher output limit. See the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. Remove any context-window beta header.

12181218

12191219**Beta headers.** Remove `interleaved-thinking-2025-05-14`, because adaptive thinking interleaves automatically. Replace `fine-grained-tool-streaming-2025-05-14` with `eager_input_streaming: true` on each tool that needs it. That header returns a 400 error alongside a computer use or browser use toolset entry. See [Fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming).

12201220

from line 1225

12251225Claude Sonnet 4 is retired on the Claude API but available on Claude Models on Google Cloud (Google managed) and Amazon Bedrock. Claude 3.7 Sonnet is retired. From either model, first apply every preceding section, then these changes:

12261226

12271227* **Tool versions:** Use `text_editor_20250728`, with the tool name `str_replace_based_edit_tool` and no `undo_edit` command. Use `code_execution_20260521`. See the [text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool) and the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version).

1228* **Stop reasons:** Handle `refusal`. Claude 4.5 and later models also stop with `model_context_window_exceeded` at the context window limit. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).

1228* **Stop reasons:** Handle `refusal`. Claude 4.5 and later models also stop with `model_context_window_exceeded` at the context window limit. See [Stop reasons and fallback](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).

12291229* **Trailing newlines:** Claude 4.5 and later models keep them in tool call string parameters.

12301230* **Beta headers:** Remove `token-efficient-tools-2025-02-19` and `output-128k-2025-02-19`.

12311231* **Prompts:** Review them against [prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).

from line 1235

12351235First apply every section up to and including [Migrating from Claude Sonnet 4.5 or earlier](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-sonnet-45), skipping the Claude Sonnet 4 subsection. Then make these changes:

12361236

12371237* **Model ID:** Replace `claude-haiku-4-5-20251001`, or the alias `claude-haiku-4-5`, with `claude-sonnet-5-5`.

1238* **Cost:** The price per token is higher, and the same text produces more tokens. Recount tokens and re-baseline cost. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing).

1238* **Cost:** The price per token is higher, and the same text produces more tokens. Recount tokens and re-baseline cost. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing).

12391239* **Prompt caching:** The minimum cacheable prompt drops from 4,096 tokens to the [Claude Sonnet 5.5 minimum](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#other-changes-from-claude-sonnet-5).

1240* **Interleaved thinking:** Adaptive thinking runs between tool calls automatically, with no beta header.

1240* **Interleaved thinking:** Adaptive thinking runs between tool calls automatically.

12411241* **Routing:** Claude Sonnet 5.5 reads Claude Haiku 4.5 thinking blocks. A conversation that moves up keeps its reasoning. One that moves back down to Claude Haiku 4.5 drops Claude Sonnet 5.5’s blocks.

12421242

models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +53 / -17 lines

from line 20

2020| ----------------- | ----------------- | ---------------------------------------------- |

2121| Claude Sonnet 5.5 | claude-sonnet-5-5 | The best combination of speed and intelligence |

2222

23[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is on by default, and the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) controls thinking depth. Its default on the Claude API is `high`. The tokenizer is the same as Claude Sonnet 5’s, so the same text produces the same token counts. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).

23[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is on by default, and the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) controls thinking depth. Its default on the Claude API is `high`. The tokenizer is the same as Claude Sonnet 5’s, so the same text produces the same token counts. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page.

2424

25For all current models, see the [models overview](https://platform.claude.com/docs/en/models/overview).

25For all current models, see [Models overview](https://platform.claude.com/docs/en/models/overview).

2626

2727## Breaking changes

2828

2929### Turn off up-front thinking with `between_tools`

3030

31To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It’s the lowest thinking setting on this model. It’s available on every platform that offers Claude Sonnet 5.5. It needs no beta header. The short [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) the model writes between tool calls still come back as `thinking` blocks with their summary text. Pass those blocks back unchanged with the rest of the assistant turn. A progress-update block you send back gives the model the full note it wrote, not the summary. If your requests don’t use tools, the response contains only text, as with `disabled` on Claude Sonnet 5.

31To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It’s the lowest thinking setting on this model. It’s available on every platform that offers Claude Sonnet 5.5. The short [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) the model writes between tool calls still come back as `thinking` blocks with their summary text. Pass those blocks back unchanged with the rest of the assistant turn. A progress-update block you send back gives the model the full note it wrote, not the summary. If your requests don’t use tools, the response contains only text, as with `disabled` on Claude Sonnet 5.

3232

3333On Claude Sonnet 5.5, a request that sends `thinking: {"type": "disabled"}` returns a 400 `invalid_request_error` whose message points to `between_tools`.

3434

35`between_tools` is accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max` effort, a request with `between_tools` returns a 400 error. To run at `xhigh` or `max`, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`, which is equivalent. With `between_tools`, effort can’t change mid-conversation: a [per-message](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking.

35`between_tools` is accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max` effort, a request with `between_tools` returns a 400 error. To run at `xhigh` or `max`, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`, which is equivalent. With `between_tools`, effort can’t change mid-conversation: a [per-message `output_config.effort`](https://platform.claude.com/docs/en/build-with-claude/effort-per-message) that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking.

3636

3737`between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. Manual thinking budgets (`thinking: {"type": "enabled", "budget_tokens": N}`) return a 400 error. See [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) and [Turn off up-front thinking](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking) in the migration guide.

3838

from line 44

4444tool_choice: type "tool" and "any" are not supported for this model.

4545```

4646

47`tool_choice: {"type": "auto"}` (the default) and `{"type": "none"}` are supported. The same check applies to the [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) endpoint. For schema-valid tool input, keep `tool_choice: {"type": "auto"}` and set `strict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs). To make the model call a tool rather than reply in text, say in the prompt when the tool applies. The migration guide shows the [before and after](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use).

47`tool_choice: {"type": "auto"}` (the default) and `{"type": "none"}` are supported. The same check applies to the [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) endpoint. For schema-valid tool input, keep `tool_choice: {"type": "auto"}` and set `strict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs). To make the model call a tool rather than reply in text, say in the prompt when the tool applies. [Forced tool use is not supported](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use) in the migration guide shows the before and after.

4848

4949### Thinking blocks are tied to the model and the conversation

5050

51Every thinking block records which model produced it. Each model reads its own blocks and only some other models’ blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads them from Claude Haiku 5.5. It doesn’t read them from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 reads Claude Sonnet 5.5 thinking blocks. So do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. No other model does.

51Every thinking block records which model produced it. A conversation that switches models keeps its earlier reasoning only if the model that it switches to can read the earlier model’s thinking blocks:

5252

53So a conversation keeps its reasoning when it moves from Claude Sonnet 5 onto Claude Sonnet 5.5, or from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API and Claude Models on Google Cloud (Google managed), or up to Claude Fable 5.2 or Claude Mythos 5.2 where they read Claude Sonnet 5.5 blocks. Any other move away from Claude Sonnet 5.5 runs the turns after the switch without it. When a request carries a block the target model can’t read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

53| Switch | Keeps its reasoning |

54| ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |

55| To Claude Sonnet 5.5, from Claude Sonnet 5 or earlier, Claude Opus 4.8 or earlier, or Claude Haiku 4.5 or earlier | Yes |

56| To Claude Sonnet 5.5, from Claude Haiku 5.5 | Yes, on the Claude API and Claude Models on Google Cloud (Google managed) only |

57| To Claude Sonnet 5.5, from any other model | No |

58| From Claude Sonnet 5.5, to Claude Opus 5.5, Claude Fable 5.2, or Claude Mythos 5.2 | Yes, on the Claude API and Claude Models on Google Cloud (Google managed) only |

59| From Claude Sonnet 5.5, to any other model | No |

5460

55The API also checks whether anything before a Claude Sonnet 5.5 thinking block has changed since the block was produced: the `system` prompt, the `tools`, or an earlier message. Keep the conversation append-only: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. A request that replays a block after such a change and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. This applies on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). On accounts created before that date, the request gets the error only when it sets the field to `"error"`. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set the field to `"drop_block"`. `block_binding` works only with `thinking: {"type": "adaptive"}`. With any other thinking setting, you can’t send `block_binding`, so strip the block the error names and every later `thinking` and `redacted_thinking` block, then retry once.

61When a request carries a block the target model can’t read, the API drops it before the model sees it. The request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models). For switches that don’t involve Claude Sonnet 5.5, see [Which model switches keep the reasoning on the Claude API](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#which-model-switches-keep-reasoning).

5662

63The API also checks whether anything before a Claude Sonnet 5.5 thinking block has changed since the block was produced: the `system` prompt, the `tools`, or an earlier message. Keep the conversation append-only: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits.

64

65A request that replays a block after such a change, with `thinking.block_binding.prefix_mismatch_behavior` unset, gets a 400 error. This applies to accounts created on or after August 31, 2026, 00:00 UTC. [Preserved thinking availability](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#feature-availability) lists the platforms where this applies. On accounts created before that date, the request might or might not get the error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set the field to `"drop_block"`.

66

67`block_binding` works only with `thinking: {"type": "adaptive"}`. With any other thinking setting, you can’t send `block_binding`. Instead, strip the block the error names and every later `thinking` and `redacted_thinking` block. Leave them out of later requests, and retry.

68

5769See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).

5870

5971### Some computer use tool versions are not supported

from line 80

6880

6981### Some advisor tool pairings are not supported

7082

71With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), which is in beta, a Claude Sonnet 5.5 executor needs Claude Mythos 5.2, Claude Fable 5.2, Claude Mythos 5.1, Claude Fable 5.1, Claude Mythos 5, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5 as its advisor, or Claude Sonnet 5.5 itself. Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 advisors work with a Claude Sonnet 5 executor, but with a Claude Sonnet 5.5 executor they return a 400 `invalid_request_error`. Every advisor that Claude Sonnet 5.5 accepts returns its advice encrypted, as an `advisor_redacted_result` block, so your client can’t read the advice text. See the advisor tool’s [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) and [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants).

83The [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) is in beta. A Claude Sonnet 5.5 executor accepts only these advisors:

7284

85* Claude Mythos 5.2 and Claude Fable 5.2

86* Claude Mythos 5.1 and Claude Fable 5.1

87* Claude Mythos 5 and Claude Fable 5

88* Claude Opus 5.5 and Claude Opus 5

89* Claude Sonnet 5.5 itself

90

91Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 advisors work with a Claude Sonnet 5 executor. With a Claude Sonnet 5.5 executor, they return a 400 `invalid_request_error`. Every advisor that Claude Sonnet 5.5 accepts returns its advice encrypted, as an `advisor_redacted_result` block. So your client can’t read the advice text. See the advisor tool’s [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) and [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants).

92

7393## Feature support

7494

75Claude Sonnet 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) (beta), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). Per-message effort, mid-conversation system messages, and mid-conversation tool changes aren’t available on Claude Sonnet 5, whose minimum cacheable prompt is 1,024 tokens. See each feature’s page for model availability.

95Claude Sonnet 5.5 supports these features:

7696

97* [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort-per-message), which is in beta

98* [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages)

99* [Mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), which are in beta

100* [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), with a minimum cacheable prompt of 512 tokens

101* [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing)

102* The [Files API](https://platform.claude.com/docs/en/build-with-claude/files)

103* [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support)

104* [Vision](https://platform.claude.com/docs/en/build-with-claude/vision)

105* Server-side and client-side tools (see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview))

106

107Claude Sonnet 5 doesn’t support per-message effort, mid-conversation system messages, or mid-conversation tool changes. On Claude Sonnet 5, the minimum cacheable prompt is 1,024 tokens. See each feature’s page for model availability.

108

77109### Compact on demand (beta)

78110

79With the `compact-2026-09-04` beta header, a request that sends the top-level `compaction` parameter returns a signed `compaction` block that summarizes the whole conversation. You then send that block first, in place of the summarized messages. You choose when to compact, and the thinking blocks in the turns you keep can stay valid after the swap, under the conditions in [Compaction and preserved thinking](https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks#conditions-for-kept-thinking-to-stay-valid). That matters on Claude Sonnet 5.5 because its [thinking blocks are tied to the conversation](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them). See [Compaction on demand](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand) for platform availability and the full request flow.

111With the `compact-2026-09-04` beta header, a request that sends the top-level `compaction` parameter returns a signed `compaction` block that summarizes the messages in that request. In later requests, the block goes first in `messages`, in place of the messages it summarizes. You choose when to compact and which turns to keep after the block. On Claude Sonnet 5.5, the thinking blocks in the kept turns can stay valid after compaction. For the conditions, see [Compaction and preserved thinking](https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks#conditions-for-kept-thinking-to-stay-valid). See [Compaction on demand](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand) for platform availability and the full request flow.

80112

81113### Define tools in a message (beta)

82114

from line 116

84116

85117### Thinking blocks stay with the account that produced them

86118

87Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model receives it, and the request succeeds. On the Claude API and Claude Models on Google Cloud (Google managed), with the `thinking-binding-controls-2026-08-01` beta header, the response lists each dropped block in `input_transformations` with `reason: "organization_binding_mismatch"`. Blocks from earlier models aren’t affected. See [thinking blocks from another account](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) in Preserved thinking.

119Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model receives it, and the request succeeds. On the Claude API and Claude Models on Google Cloud (Google managed), you can see which blocks were dropped. Send the `thinking-binding-controls-2026-08-01` beta header, and the response lists each dropped block in `input_transformations` with `reason: "organization_binding_mismatch"`. Blocks from earlier models aren’t affected. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).

88120

89121## Behavior differences

90122

from line 128

96128

97129## Refusals, fallback, and billing

98130

99Everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies to Claude Sonnet 5.5. A declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area. Handle refusals and configure fallback. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn’t retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. You can also use the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) or your own retry. Whether a refusal that arrives before any output is billed depends on its refusal category, and it counts against your rate limits either way. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).

131Everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies to Claude Sonnet 5.5. A declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area.

100132

133Handle refusals in your code, and configure fallback. With [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), a request declined in the `"cyber"` or `"frontier_llm"` category runs again on Claude Sonnet 5. A request declined in the `"bio"`, `"reasoning_extraction"`, or `"general_harms"` category isn’t retried. Server-side fallback is in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). You can also use the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) or your own retry.

134

135A refusal that arrives before any output is billed in some refusal categories and not in others. Either way, it counts against your rate limits. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).

136

101137## Pricing

102138

103139Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for the full list, data residency, and tool pricing.

from line 197

1611975. If you use the advisor tool with a Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, or Claude Haiku 5.5 advisor, [switch to an advisor that Claude Sonnet 5.5 accepts](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings).

1621986. If your interface shows the text between tool calls, set `thinking.display` when you use adaptive thinking. With `between_tools`, the text comes back without it. See [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#text-between-tool-calls).

163199

164The [migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide) has step-by-step instructions from Claude Sonnet 5 and earlier models, and the full checklist.

200The [Claude Sonnet 5.5 migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide) has step-by-step instructions from Claude Sonnet 5 and earlier models, and the full checklist.

165201

166202## Next steps

167203

release-notes/overview Changed · +8 / -6 lines

from line 14

1414

1515### November 9, 2026

1616

17* We’ve launched **Claude Fable 5.2** (`claude-fable-5-2`), built for demanding reasoning and long-horizon agentic work. **Claude Mythos 5.2** (`claude-mythos-5-2`) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Both models have a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). They cost $8 USD per MTok of input and $40 USD per MTok of output (Claude Fable 5.1 and Claude Mythos 5.1 cost $10 USD per MTok of input and $50 USD per MTok of output). Claude Fable 5.2 is available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). It’s also available on [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock). It’s also available on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). It’s also available on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2) for API changes and migration guidance. For model-specific prompting patterns, see [Prompting Claude Fable 5.2](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2).

17* We’ve launched **Claude Fable 5.2** (`claude-fable-5-2`), built for demanding reasoning and long-horizon agentic work. **Claude Mythos 5.2** (`claude-mythos-5-2`) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Both models have a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). They cost $8 USD per MTok of input and $40 USD per MTok of output (Claude Fable 5.1 and Claude Mythos 5.1 cost $10 USD per MTok of input and $50 USD per MTok of output). Claude Fable 5.2 is available on the Claude API, [Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), 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 5.2](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2) for API changes and migration guidance. For model-specific prompting patterns, see [Prompting Claude Fable 5.2](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2).

1818* Claude Fable 5.2 and Claude Mythos 5.2 enforce the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) for every account, whatever its age. Claude Fable 5.1 returns the error by default on accounts created on or after August 31, 2026 (see [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement)). If your code edits the `system` prompt, `tools`, or an earlier message and then sends back a Claude Fable 5.2 or Claude Mythos 5.2 thinking block from a later turn, the request returns a 400 error. Before you switch, [check whether your code edits the prefix](https://platform.claude.com/docs/en/models/fable-5-2/migration-guide#fable-5-2-preserved-thinking).

19* On the Claude API and Claude Models on Google Cloud (Google managed), a conversation that moves onto Claude Fable 5.2 or Claude Mythos 5.2 keeps the reasoning from other models, including Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. When the conversation moves the other way, to any other model, including Claude Opus 5.5 and Claude Fable 5.1, the API drops the thinking blocks that Claude Fable 5.2 or Claude Mythos 5.2 produced, and the request still succeeds. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

19* Claude Fable 5.2 and Claude Mythos 5.2 read other models’ thinking blocks on the Claude API and Claude Models on Google Cloud (Google managed). So on those platforms, a conversation that moves onto either model keeps its reasoning. The other models include Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5.

20* No other model reads thinking blocks from Claude Fable 5.2 or Claude Mythos 5.2. When a conversation moves from either one to a model outside this pair, the API drops those blocks. That includes a move to Claude Opus 5.5 or Claude Fable 5.1. The request still succeeds. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).

2021* Claude Fable 5.2 and Claude Mythos 5.2 support computer use through the `computer_toolset_20260801` toolset. A request that declares the earlier `computer_20251124` tool returns a 400 error on every platform except Amazon Bedrock, where the earlier tool still works. See [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

2122* With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), which is in beta, a Claude Fable 5.2 or Claude Mythos 5.2 executor accepts only Claude Fable 5.2 or Claude Mythos 5.2 as its advisor. Any other advisor returns a 400 error, so set the advisor’s `model` to one of these two models when you move an executor to them. Every executor model accepts Claude Fable 5.2 as its advisor. See [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).

2223* Both models require 30-day data retention, like Claude Fable 5.1 and Claude Mythos 5.1. They 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).

2324* Thinking blocks that Claude Fable 5.2 and Claude Mythos 5.2 produce work only in the account that produced them, or in an account linked to it. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).

25* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Fable 5.2. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#feature-availability).

2426* We’ve launched [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Fable 5.2 in Messages API requests on the Claude API. Fast mode delivers up to 2.5x higher output tokens per second, at $16 USD per MTok of input and $80 USD per MTok of output. Set `speed: "fast"` on your request, with no beta header.

2527

2628### November 5, 2026

from line 176

174176

175177### September 1, 2026

176178

177* 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 USD 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 Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), 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.

179* 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. For Project Glasswing participants, we’ve also launched **Claude Mythos 5.1** (`claude-mythos-5-1`). 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). They cost $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 USD 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), and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws). It’s also on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for specifications.

178180* 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).

179181* 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).

180182* 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).

from line 250

248250

249251### July 24, 2026

250252

251* We’ve launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It’s 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 Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for new features, behavior changes, and migration guidance, and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.

252* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What’s new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview).

253* We’ve launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It’s 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 Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.

254* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [Effort with thinking](https://platform.claude.com/docs/en/build-with-claude/effort#effort-with-thinking).

253255* [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) is the primary control for steering Claude Opus 5: the model supports the full ladder (`low`, `medium`, `high`, `xhigh`, `max`), with `max` for capability-critical work.

254256* Mid-conversation tool changes are now in beta on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5: add or remove tools between turns of a conversation while preserving the prompt cache. Include the `mid-conversation-tool-changes-2026-07-01` beta header in your requests.

255257* The `fallbacks` parameter now supports a `"default"` mode, which applies Anthropic’s recommended fallback models by refusal category. Server-side fallback is in beta, and the `"default"` mode requires the `server-side-fallback-2026-07-01` beta header. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

from line 298

296298

297299### June 30, 2026

298300

299* We’ve launched **Claude Sonnet 5** (`claude-sonnet-5`), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 USD per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is now on by default; manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See [What’s new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) for details and migration guidance. For behavioral differences and model-specific prompting patterns, see [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5).

301* We’ve launched **Claude Sonnet 5** (`claude-sonnet-5`), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 USD per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is now on by default; manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) for details. For behavioral differences and model-specific prompting patterns, see [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5).

300302* Claude Managed Agents session event streams now support [event deltas](https://platform.claude.com/docs/en/managed-agents/event-deltas). Opt in with the `event_deltas[]` query parameter on `GET /v1/sessions/{session_id}/events/stream`. The `event_start` and `event_delta` events preview an agent message’s text as it’s generated, before the complete `agent.message` event arrives.

301303* [Listing sessions](https://platform.claude.com/docs/en/managed-agents/session-operations#listing-sessions) for Claude Managed Agents now supports backward pagination. `GET /v1/sessions` returns a `prev_page` cursor alongside `next_page`; pass it as the `page` parameter to return to the previous page. See [Pagination](https://platform.claude.com/docs/en/api/overview#pagination).

302304* When creating a Claude Managed Agents session, you can now [override the agent’s configuration for that session](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session). Pass `agent` with `type: "agent_with_overrides"` to replace the model, system prompt, tools, MCP servers, or skills for a single session. The agent itself is unchanged.

test-and-evaluate/strengthen-guardrails/handle-streaming-refusals Changed · +7 / -7 lines

from line 25

2525 - claude-sonnet-4-5-20250929

2626 supportedPlatforms:

2727 Claude API: stable

28 Claude Platform on AWS: stable

2928 Amazon Bedrock: stable

30 Amazon Bedrock (InvokeModel): stable

29 Amazon Bedrock (bedrock-runtime): stable

30 Claude Platform on AWS: stable

3131 Claude Models on Google Cloud (Google managed): stable

3232 Microsoft Foundry: stable

3333---

from line 91

9191

9292<CodeGroup exclude="shell:cURL, shell:CLI">

9393 <CodeGroupItem language="cURL">

94 Detecting a refusal in the stream and resetting the conversation needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

94 Detecting a refusal in the stream and resetting the conversation needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

9595 </CodeGroupItem>

9696

9797 <CodeGroupItem language="CLI">

98 Detecting a refusal in the stream and resetting the conversation needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

98 Detecting a refusal in the stream and resetting the conversation needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.

9999 </CodeGroupItem>

100100

101101 ```python Python

from line 383

383383* Availability: Always on

384384* Usage: The stream ends with `stop_reason` `"refusal"`, and `stop_details` (`category` and `explanation`) arrives on the `message_delta` event.

385385

386| Status | Cloud platforms |

387| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

388| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |

386| Status | Cloud platforms |

387| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

388| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |

389389

390390#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)

391391

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

from line 21

2121 Deprecated models are likely to be less reliable than active models. Move workloads to active models to maintain the highest level of support and reliability.

2222</Warning>

2323

24The dates on this page apply to Anthropic-operated platforms: the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Amazon Bedrock, set their own retirement schedules, so a model’s lifecycle status and dates can differ. See the [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#supported-models), [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed#api-model-ids) model tables.

24The dates on this page apply to Anthropic-operated platforms: the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Amazon Bedrock, set their own retirement schedules, so a model’s lifecycle status and dates can differ. See the [Amazon Bedrock (`bedrock-mantle`)](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#supported-models), [Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed#api-model-ids) model tables.

2525

2626## Migrating to replacements

2727

One read of Claude Developer Platformapi-20261111T173709Z

What this read moved

manage-claude/opentelemetry Changed · +4 / -4 lines

manage-claude/opentelemetry/sdk Changed · +10 / -10 lines

manage-claude/wif-providers/spiffe Changed · +5 / -2 lines

managed-agents/agent-setup Changed · +28 / -19 lines

managed-agents/dreams Changed · +4 / -3 lines

managed-agents/events-and-streaming Changed · +6 / -6 lines

models/fable-5-1/overview Changed · +2 / -4 lines

models/fable-5-2/migration-guide Changed · +17 / -17 lines

models/fable-5-2/overview Changed · +14 / -14 lines

models/fable-5-2/whats-new-fable-5-2 Changed · +8 / -13 lines

models/haiku-4-5/overview Changed · +18 / -18 lines

models/haiku-5-5/migration-guide Changed · +11 / -2 lines

models/mythos-5-2/overview Changed · +13 / -13 lines

models/opus-4-5/overview Changed · +17 / -17 lines

models/opus-4-6/overview Changed · +16 / -16 lines

models/opus-5-5/migration-guide Changed · +59 / -61 lines

models/opus-5-5/whats-new-opus-5-5 Changed · +22 / -9 lines

models/overview Changed · +37 / -7 lines

models/sonnet-4-5/overview Changed · +18 / -18 lines

models/sonnet-4-6/overview Changed · +16 / -16 lines

models/sonnet-5-5/migration-guide Changed · +16 / -16 lines

models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +53 / -17 lines

release-notes/overview Changed · +8 / -6 lines

test-and-evaluate/strengthen-guardrails/handle-streaming-refusals Changed · +7 / -7 lines

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