One read of Claude Developer Platformapi-20261021T183757Z

This capture is too large to show at once. Changes 26-42 of 42 are below, significant first; the rest are on the following screens.

cli-sdks-libraries/sdks/java Changed · +2 / -0 lines

from line 1255

12551255 

12561256## Semantic versioning

12571257 

1258Each major version of this SDK sends one API version in the `anthropic-version` header by default, and a new major version comes with each new API version. The first major version that sends `2026-10-21` is 3.0.0; see [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

1259 

12581260This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backward-incompatible changes may be released as minor versions:

12591261 

126012621. Changes to library internals which are technically public but not intended or documented for external use.

cli-sdks-libraries/sdks/python Changed · +3 / -1 lines

from line 525

525525 

526526## Default headers

527527 

528The SDK automatically sends the `anthropic-version` header set to `2023-06-01`.

528The SDK automatically sends the `anthropic-version` header set to the API version for this major version of the SDK (see [Semantic versioning](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/python#semantic-versioning)).

529529 

530530If you need to, you can override it by setting default headers on the client object or per-request.

531531 

from line 758

758758Use `AnthropicBedrockMantle` for new projects; `AnthropicBedrock` remains for existing applications using the Bedrock `InvokeModel` API.

759759 

760760## Semantic versioning

761 

762Each major version of this SDK sends one API version in the `anthropic-version` header by default, and a new major version comes with each new API version. The first major version that sends `2026-10-21` is 2.0.0; see [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

761763 

762764This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backward-incompatible changes may be released as minor versions:

763765 

cli-sdks-libraries/sdks/ruby Changed · +2 / -0 lines

from line 409

409409 

410410## Semantic versioning

411411 

412Each major version of this SDK sends one API version in the `anthropic-version` header by default, and a new major version comes with each new API version. The first major version that sends `2026-10-21` is 2.0.0; see [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

413 

412414This package follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions.

413415 

414416This package considers improvements to the (non-runtime) `*.rbi` and `*.rbs` type definitions to be non-breaking changes.

cli-sdks-libraries/sdks/typescript Changed · +3 / -1 lines

from line 522

522522 

523523## Default headers

524524 

525The SDK automatically sends the `anthropic-version` header set to `2023-06-01`.

525The SDK automatically sends the `anthropic-version` header set to the API version for this major version of the SDK (see [Semantic versioning](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/typescript#semantic-versioning)).

526526 

527527If you need to, you can override it by setting default headers on a per-request basis.

528528 

from line 781

781781Use `AnthropicBedrockMantle` for new projects; `AnthropicBedrock` remains for existing applications using the Bedrock `InvokeModel` API.

782782 

783783## Semantic versioning

784 

785Each major version of this SDK sends one API version in the `anthropic-version` header by default, and a new major version comes with each new API version. The first major version that sends `2026-10-21` is 1.0.0; see [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

784786 

785787This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backward-incompatible changes may be released as minor versions:

786788 

manage-claude/admin-api Changed · +1 / -1 lines

from line 1342

13421342 

13431343### API keys

13441344 

1345Monitor and manage [API keys](https://platform.claude.com/docs/en/api/organization/api_keys/list). Each key in the response includes its `expires_at` timestamp (`null` for keys without an [expiration](https://platform.claude.com/docs/en/manage-claude/authentication#key-expiration)) and `principal`, the identity it acts as (see [Key types](https://platform.claude.com/docs/en/manage-claude/authentication#key-types)). For a personal key, `principal` is `{"type": "user_actor", "user_id": "user_..."}`; for a service account key, `{"type": "service_account_actor", "service_account_id": "svac_..."}`; and for a workspace key, `null`. Each key also has a `scope` object: `{"type": "workspace", "workspace_id": "wrkspc_..."}` for a key bound to one workspace, or `{"type": "organization"}` for a key that can work across any workspace the account has access to. The top-level `workspace_id` field is deprecated and is `null` both for keys bound to the Default Workspace and for keys without a workspace scope; use `scope` to tell them apart. Filtering the list by `workspace_id` with the Default Workspace's ID returns only keys bound to the Default Workspace; keys without a workspace scope aren't returned under any `workspace_id` filter.

1345Monitor and manage [API keys](https://platform.claude.com/docs/en/api/organization/api_keys/list). Each key in the response includes its `expires_at` timestamp (`null` for keys without an [expiration](https://platform.claude.com/docs/en/manage-claude/authentication#key-expiration)) and `principal`, the identity it acts as (see [Key types](https://platform.claude.com/docs/en/manage-claude/authentication#key-types)). For a personal key, `principal` is `{"type": "user_actor", "user_id": "user_..."}`; for a service account key, `{"type": "service_account_actor", "service_account_id": "svac_..."}`; and for a workspace key, `null`. Each key also has a `scope` object: `{"type": "workspace", "workspace_id": "wrkspc_..."}` for a key bound to one workspace, or `{"type": "organization"}` for a key that can work across any workspace the account has access to. Filtering the list by `workspace_id` with the Default Workspace's ID returns only keys bound to the Default Workspace; keys without a workspace scope aren't returned under any `workspace_id` filter.

13461346 

13471347List the active API keys in a workspace:

13481348 

manage-claude/rate-limits-api Changed · +1 / -1 lines

from line 154

154154* **Rate limit groups:** Each entry in the response represents one rate limit group. Model rate limits are grouped so that several model versions share a single set of limits, and other groups cover resources such as the Message Batches API, the Files API, the Token Counting API, agent skills, and the web search tool.

155155* **`group` object:** Present on every entry, it identifies the rate limit group the entry applies to. It always has `type`, which is one of the `group_type` values, and `id`, an opaque identifier with the `rlg_` prefix. On `model_group` entries it also has `display_name`, Anthropic's current label for the group, such as `Claude Sonnet 4.x`. The label is for display only and may change. Other group types have no `display_name`.

156156* **The `id` inside `group`:** A group has the same `id` in every organization and on every workspace override, and it never changes. Use it to match entries across organizations or against your own catalog. The entry's own `id` differs per organization, and `models` changes when Anthropic moves a model between groups. Neither is a stable key for the group.

157* **`group_type`:** Deprecated in favor of the `type` inside `group`. It's still returned, always equals that value, and has no removal date. The `group_type` query parameter isn't deprecated. See [Filtering by group type](https://platform.claude.com/docs/en/manage-claude/rate-limits-api#filtering-by-group-type) for the list of values.

157* **`group_type`:** The query parameter that restricts the list to one group type. See [Filtering by group type](https://platform.claude.com/docs/en/manage-claude/rate-limits-api#filtering-by-group-type) for the values.

158158* **`models` list:** For `model_group` entries, the `models` field lists every model ID and alias that counts against that group's limits. Use this list to look up which group any model string falls under. For other group types, `models` is `null`.

159159* **`limits` list:** Each group carries a list of `{type, value}` pairs. The `type` field identifies the limiter (such as `requests_per_minute`, `input_tokens_per_minute`, or `output_tokens_per_minute`) and `value` is the configured limit. See [Rate limits](https://platform.claude.com/docs/en/api/rate-limits) for how each limiter is measured and enforced.

160160* **`source` on workspace limits:** On the workspace endpoint, every limit value also carries `source`, which says where `value` comes from: `{"type": "workspace"}` for an override stored on the workspace, or `{"type": "organization"}` for a value inherited from the organization. By default, the workspace endpoint returns overrides only, so `source.type` is always `workspace` there; inherited values appear when you pass `include_inherited=true`. See [Workspace rate limits](https://platform.claude.com/docs/en/manage-claude/rate-limits-api#workspace-rate-limits).

manage-claude/wif-admin-api Changed · +1 / -1 lines

from line 21

2121 

2222Interactive tokens are short-lived; if requests start returning 401, re-run the export command (it refreshes the token automatically).

2323 

24The SDKs and the `ant` CLI read `ANTHROPIC_AUTH_TOKEN` automatically; leave `ANTHROPIC_API_KEY` unset in the same shell, because these endpoints reject API keys and some clients prefer the key when both are set.

24The SDKs and the `ant` CLI read `ANTHROPIC_AUTH_TOKEN` automatically; leave `ANTHROPIC_API_KEY` unset in the same shell, because these endpoints reject API keys and every client uses the key when both are set.

2525 

2626### Workload (CI and automation)

2727 

manage-claude/wif-reference Changed · +2 / -2 lines

from line 47

4747The direct environment-variable federation path activates only when `ANTHROPIC_FEDERATION_RULE_ID`, `ANTHROPIC_ORGANIZATION_ID`, `ANTHROPIC_SERVICE_ACCOUNT_ID`, and one of `ANTHROPIC_IDENTITY_TOKEN_FILE` or `ANTHROPIC_IDENTITY_TOKEN` are all set. `ANTHROPIC_WORKSPACE_ID` is read alongside but does not gate activation.

4848 

4949<Warning>

50 A variable that is set to an empty string still occupies its slot in the credential precedence chain. If `ANTHROPIC_API_KEY=""` is exported, the SDK selects the API-key path with an empty key rather than falling through to federation. Unset unused credential variables rather than blanking them.

50 A variable that is set to an empty string can still occupy its slot in the credential precedence chain. Unset unused credential variables rather than blanking them.

5151</Warning>

5252 

5353### Credential precedence

from line 238

238238| SDK authenticates with an API key instead of federating | `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN` is set and wins precedence. | Unset the key or token variable. |

239239| `FileNotFoundError` on first request | The path in `ANTHROPIC_IDENTITY_TOKEN_FILE` does not exist. The SDK opens the file lazily at exchange time. | Confirm the projected-token volume is mounted and the path matches. |

240240| Token exchange succeeds but a Claude API request returns 403 | The minted token's scope does not grant access to that endpoint. | Check the rule's `oauth_scope` against [OAuth scopes](https://platform.claude.com/docs/en/manage-claude/wif-reference#oauth-scopes). |

241| Authentication fails with empty credential | A credential environment variable is exported but set to an empty string. Empty values still win their precedence slot. | Unset the variable with `unset VAR` rather than `VAR=""`. |

241| Authentication fails with empty credential | A credential environment variable is exported but set to an empty string. Empty values can still win their precedence slot. | Unset the variable with `unset VAR` rather than `VAR=""`. |

242242 

243243## Troubleshoot a failed exchange

244244 

managed-agents/quickstart Changed · +2 / -2 lines

from line 49

4949 For Linux environments, download the release binary directly.

5050 

5151 ```bash

52 VERSION=1.44.0

52 VERSION=2.0.0

5353 OS=$(uname -s | tr '[:upper:]' '[:lower:]')

5454 case $(uname -m) in

5555 x86_64) ARCH=amd64 ;;

from line 66

6666 You can also install the CLI from source using `go install`. Requires Go 1.25 or later.

6767 

6868 ```bash

69 go install github.com/anthropics/anthropic-cli/cmd/ant@latest

69 go install github.com/anthropics/anthropic-cli/v2/cmd/ant@latest

7070 ```

7171 

7272 The binary is placed in `$(go env GOPATH)/bin`. Add it to your `PATH` if it isn't already:

managed-agents/self-hosted-sandboxes-workers Changed · +1 / -1 lines

from line 437

437437 

438438 ```dockerfile

439439 FROM your-base-image

440 ARG ANT_VERSION=1.44.0

440 ARG ANT_VERSION=2.0.0

441441 ARG TARGETARCH

442442 RUN ARCH=$([ "$TARGETARCH" = "arm64" ] && echo arm64 || echo amd64) && \

443443 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${ANT_VERSION}/ant_${ANT_VERSION}_linux_${ARCH}.tar.gz" \

models/fable-5-1/whats-new-fable-5-1 Changed · +1 / -1 lines

from line 379

379379* `thinking.display` defaults to `"omitted"`. `"summarized"` is available, and the raw chain of thought is never returned.

380380* Reasoning between tool calls appears in thinking blocks rather than text, and [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking) is automatic with no beta header.

381381* Prefilling the assistant response returns a 400 error.

382* Non-default `temperature`, `top_p`, or `top_k` values return a 400 error.

382* Setting `temperature`, `top_p`, or `top_k` returns a 400 error.

383383* The minimum cacheable prompt length is 512 tokens.

384384* [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) and tool changes are supported.

385385 

models/haiku-5-5/migration-guide Changed · +1 / -1 lines

from line 118

118118 

119119## Remove sampling parameters

120120 

121Claude Haiku 4.5 accepts `temperature`, `top_p`, and `top_k`. On Claude Haiku 5.5, omit all three and use prompting to guide the model's behavior instead. If a request includes `temperature`, it must be `1`. If it includes `top_p`, it must be `0.99`, its default. Any other `temperature` or `top_p` value returns a 400 error, including a `top_p` of `1`. So does any `top_k` value, and so does a request that includes both `temperature` and `top_p`.

121On Claude Haiku 5.5, omit `temperature`, `top_p`, and `top_k` and use prompting to guide the model's behavior instead.

122122 

123123## Replace assistant prefill

124124 

models/haiku-5-5/overview Changed · +1 / -1 lines

from line 90

9090## Good to know

9191 

9292* Adaptive thinking is on by default. Control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort).

93* Omit `temperature`, `top_p`, and `top_k`. See [Remove sampling parameters](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters) for the values that return a 400 error.

93* Omit `temperature`, `top_p`, and `top_k`.

9494* On the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta), Claude Haiku 5.5 supports up to 300k output tokens with the `output-300k-2026-03-24` beta header.

9595* The minimum cacheable prompt length is 512 tokens. See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations).

9696* Query limits and capabilities programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list).

models/sonnet-5-5/migration-guide Changed · +2 / -2 lines

from line 485

485485 

486486* Expect [thinking on requests with no `thinking` field](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-on-by-default), and revisit `max_tokens`.

487487* Replace [thinking budgets](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#sonnet-46-breaking-changes) with an effort level.

488* Remove non-default `temperature`, `top_p`, and `top_k` values.

488* Remove `temperature`, `top_p`, and `top_k`.

489489* If you [show thinking text](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-in-responses), set `display: "summarized"`.

490490* [Recount tokens](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#other-changes-from-claude-sonnet-4-6), and re-budget image tokens.

491491 

from line 1189

11891189 ```

11901190</CodeGroup>

11911191 

1192**Sampling parameters return an error.** Claude Sonnet 4.6 and earlier models and Claude Haiku 4.5 accept `temperature`, `top_p`, and `top_k`. On Claude Sonnet 5.5, a non-default value returns a 400 error. Remove them.

1192**Sampling parameters return an error.** Remove `temperature`, `top_p`, and `top_k`.

11931193 

11941194**Thinking text is omitted by default.** See [Handle thinking in responses](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-in-responses).

11951195 

models/sonnet-5-5/overview Changed · +1 / -1 lines

from line 96

9696## Good to know

9797 

9898* Adaptive thinking is on by default. The lowest thinking setting is `between_tools`, which turns off up-front thinking. It works at `high` effort or below. See [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking).

99* Setting `temperature`, `top_p`, or `top_k` to a non-default value returns a 400 error.

99* Setting `temperature`, `top_p`, or `top_k` returns a 400 error.

100100* The minimum cacheable prompt length is 512 tokens. See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations).

101101* On the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta), Claude Sonnet 5.5 supports up to 300k output tokens with the `output-300k-2026-03-24` beta header.

102102* Query limits and capabilities programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list).

models/sonnet-5/overview Changed · +1 / -1 lines

from line 81

8181## Good to know

8282 

8383* On the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta), Claude Sonnet 5 supports up to 300k output tokens with the `output-300k-2026-03-24` beta header.

84* Setting `temperature`, `top_p`, or `top_k` to non-default values returns a 400 error.

84* Setting `temperature`, `top_p`, or `top_k` returns a 400 error.

8585* Query limits and capabilities programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list).

8686 

8787## Resources

test-and-evaluate/strengthen-guardrails/reduce-latency Changed · +0 / -1 lines

from line 221

221221 

222222 tokens, the response will be cut off, perhaps mid-sentence or mid-word, so this is a blunt technique that might require post-processing and is usually most appropriate for multiple choice or short answer responses where the answer comes right at the beginning.

223223 </Note>

224* **Experiment with temperature:** The `temperature` [parameter](https://platform.claude.com/docs/en/api/messages/create) controls the randomness of the output. Lower values (for example, 0.2) can sometimes lead to more focused and shorter responses, while higher values (for example, 0.8) might result in more diverse but potentially longer outputs. Claude 4.7 and later models and Claude Mythos Preview accept only the default `temperature` and return a 400 error for any other value, so on those models lower [effort](https://platform.claude.com/docs/en/build-with-claude/effort) instead.

225224 

226225Finding the right balance among prompt clarity, output quality, and token count might require some experimentation.

227226