One read of Claude Developer Platformapi-20261020T020708Z
124 pages moved out of 785 read.
Pages moved
124
significant first
Pages read
785
in this capture
Captured
02:07 UTC
Corpus hash
05505ffc3bb1
index-hash
What this read moved
76-100 of 124, page 4 of 5This capture is too large to show at once. Changes 76-100 of 124 are below, significant first; the rest are on the following screens.
managed-agents/workflow-runs Changed · +12 / -7 lines
from line 254
254254 events: [
255255 {
256256 type: "user.message",
257 content: [{ type: "text", text: "Which contracts in /contracts have a change-of-control clause?" }],
258 },
259 ],
257 content: [
258 {
259 type: "text",
260 text: "Which contracts in /contracts have a change-of-control clause?"
261 }
262 ]
263 }
264 ]
260265 });
261266
262267 events: for await (const event of stream) {
from line 295
290295 {
291296 type: "user.custom_tool_result",
292297 custom_tool_use_id: event.id,
293 content: [{ type: "text", text: result }],
294 },
295 ],
298 content: [{ type: "text", text: result }]
299 }
300 ]
296301 });
297302 } catch (error) {
298303 // The server refuses a result that comes too late, after it
from line 444
439444 ```
440445
441446 ```go Go
442 openRuns := map[string]string{} // workflow_run_id -> run name
447 openRuns := map[string]string{} // workflow_run_id -> run name
443448 phaseNames := map[[2]string]string{} // {run ID, phase ID} -> phase name
444449
445450 // Open the stream first, then send the user message
models/opus-5-5/migration-guide Changed · +5 / -7 lines
from line 33
3333* **Effort:** Control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort), the only request parameter that controls it. All five levels (`low`, `medium`, `high`, `xhigh`, `max`) are supported, and the default is `medium`. See [Recommended effort levels for Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-opus-5-5).
3434* **Tool choice:** Use `tool_choice` `{"type": "auto"}` (the default) or `{"type": "none"}`. Forcing a tool call with `{"type": "any"}` or `{"type": "tool", "name": "..."}` is rejected. See the [before and after for tool choice](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#forced-tool-use).
3535* **Sampling parameters:** Omit `temperature`, `top_p`, and `top_k`, or leave them at their defaults: any other value is rejected. Use prompting to guide the model's behavior.
36* **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. On Amazon Bedrock, structured outputs aren't available for Claude Opus 5.5, so use system prompt instructions there.
36* **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.
3737* **Computer use:** On the Claude API and Google Cloud, declare computer use as the `computer_toolset_20260801` toolset; the earlier `computer_20251124` tool is rejected there. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
3838* **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.
3939
from line 103
103103 }
104104 });
105105
106 const textBlock = response.content.find(
107 (block): block is Anthropic.TextBlock => block.type === "text"
108 );
106 const textBlock = response.content.find((block) => block.type === "text");
109107 console.log(textBlock?.text);
110108 ```
111109
from line 284
286284* Update the model ID to `claude-opus-5-5`.
287285* Remove `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}`; choose an effort level instead.
288286* Set `effort` explicitly: the default is `medium`, where Claude Opus 5's is `high`.
289* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs, or with `auto` alone on Amazon Bedrock.
287* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
290288* If you use computer use on the Claude API or Google Cloud, declare `computer_toolset_20260801` (no beta header) instead of `computer_20251124` and update your agent loop for the toolset. On Amazon Bedrock, keep `computer_20251124`; check the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section for other platforms.
291289* 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). Claude Opus 5.5 itself reads thinking from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Google Cloud, from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models.
292290* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.
from line 568
570568
571569#### Forced tool use is not supported
572570
573`tool_choice` types `any` and `tool` return a 400 error (`tool_choice: type "tool" and "any" are not supported for this model.`), including on the token counting endpoint. Use `auto` with [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), and say in the prompt when the tool applies. Strict tool use accepts a subset of JSON Schema, so check each tool's `input_schema` before you add `strict: true`. Every object in the schema must set `additionalProperties: false`; see [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations). On Amazon Bedrock, structured outputs, which include strict tool use, aren't available for Claude Opus 5.5. There, send `auto` without `strict`, say in the prompt when the tool applies, and validate the tool input in your code. See [Forced tool use is not supported](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported).
571`tool_choice` types `any` and `tool` return a 400 error (`tool_choice: type "tool" and "any" are not supported for this model.`), including on the token counting endpoint. Use `auto` with [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), and say in the prompt when the tool applies. Strict tool use accepts a subset of JSON Schema, so check each tool's `input_schema` before you add `strict: true`. Every object in the schema must set `additionalProperties: false`; see [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations). See [Forced tool use is not supported](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported).
574572
575573Before. Claude Opus 5 accepts this request, and Claude Opus 5.5 rejects it with a 400 error:
576574
from line 1511
15131511
15141512 Update your `max_tokens` parameters to give additional headroom, including compaction triggers, and re-test any code path that estimates tokens client-side or assumes a fixed token-to-character ratio. Use the [Token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting) to verify. Prompting interventions, [`task_budget`](https://platform.claude.com/docs/en/build-with-claude/task-budgets), and [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort) can help control costs; these controls may trade off model intelligence.
15151513
15165. **Prefill removal (already in effect on Claude Opus 4.6):** Prefilling assistant messages returns a 400 error on Claude Opus 4.6 and later Opus models, including Claude Opus 5.5, so this is a change only if you come from Claude Opus 4.5 or earlier. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) or system prompt instructions instead. On Amazon Bedrock, structured outputs aren't available for Claude Opus 5.5, so use system prompt instructions there.
15145. **Prefill removal (already in effect on Claude Opus 4.6):** Prefilling assistant messages returns a 400 error on Claude Opus 4.6 and later Opus models, including Claude Opus 5.5, so this is a change only if you come from Claude Opus 4.5 or earlier. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) or system prompt instructions instead.
15171515
15181516### Behavior changes
15191517
models/sonnet-5-5/migration-guide Changed · +4 / -6 lines
from line 94
9494 });
9595
9696 console.log(`Stop reason: ${response.stop_reason}`);
97 const textBlock = response.content.find(
98 (block): block is Anthropic.TextBlock => block.type === "text"
99 );
97 const textBlock = response.content.find((block) => block.type === "text");
10098 console.log(textBlock?.text);
10199 ```
102100
from line 474
476474* Change the model ID to `claude-sonnet-5-5`.
477475* [Read content blocks by `type`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-in-responses), and pass `thinking` blocks back unchanged.
478476* To keep running without up-front thinking, send [the lowest thinking setting](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking) at `high` effort or below.
479* Replace [forced tool use](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use) with `auto` and strict tools, or with `auto` alone on Amazon Bedrock.
477* Replace [forced tool use](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use) with `auto` and strict tools.
480478* Keep conversations [append-only](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).
481479* On the Claude API and Google Cloud, move computer use to the [toolset](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset), without the `fine-grained-tool-streaming-2025-05-14` beta header.
482480* Pair the [advisor tool](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#advisor-tool) with a supported advisor, and expect encrypted advice.
from line 526
528526tool_choice: type "tool" and "any" are not supported for this model.
529527```
530528
531Send `tool_choice: {"type": "auto"}`, and mark the tool `strict: true` so its input matches the schema. The model can then answer without calling the tool, so say in the prompt when to use it. [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) supports a subset of JSON Schema and needs `additionalProperties: false` on every object. See [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations). On Amazon Bedrock, [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), which include strict tool use, aren't available for Claude Sonnet 5.5. There, send `auto` without `strict`, say in the prompt when to call the tool, and validate the tool input in your code.
529Send `tool_choice: {"type": "auto"}`, and mark the tool `strict: true` so its input matches the schema. The model can then answer without calling the tool, so say in the prompt when to use it. [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) supports a subset of JSON Schema and needs `additionalProperties: false` on every object. See [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations).
532530
533531Before (Claude Sonnet 5):
534532
from line 1213
12151213
12161214Replace each prefill according to what it was for:
12171215
1218* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification. On Amazon Bedrock, structured outputs aren't available for Claude Sonnet 5.5. There, describe the format in the prompt or use a tool without `strict`, and validate the output in your code.
1216* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification.
12191217* **Preambles:** ask in the system prompt for a direct answer.
12201218* **Unwanted refusals:** clear instructions in the user message are usually enough.
12211219* **Continuations:** move them to the user message, for example "Your previous response was interrupted and ended with `[previous_response]`. Continue from where you left off."
release-notes/overview Changed · +5 / -4 lines
from line 14
1414
1515### October 15, 2026
1616
17* We've added `capabilities.thinking.types.between_tools` to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now report whether each model accepts `thinking: {type: "between_tools"}`, which turns off up-front thinking. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
1718* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now returns the text each organization member saved as **Instructions for Claude** in claude.ai and as **Global instructions** in Cowork, in beta for Claude Enterprise organizations. Call `GET /v1/compliance/organizations/{org_uuid}/user_preferences` with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [List user preferences](https://platform.claude.com/docs/en/manage-claude/compliance-org-data#list-user-preferences).
1819* [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the `fast-mode-2026-02-01` beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in the Start, Build, and Scale usage tiers. Fast mode for Claude Opus 5 and Claude Opus 4.8 remains in research preview. Keep sending the beta header with fast mode requests to those models.
1920* [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 5.5 is now available on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure.
from line 38
3738
3839* We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).
3940* We've launched **Claude Haiku 5.5** (`claude-haiku-5-5`), our most capable model tuned for high-volume and latency-sensitive work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). 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 on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5).
40* Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (`budget_tokens`), the sampling parameters `temperature`, `top_p`, and `top_k`, and assistant message prefill can each return a 400 error. `computer_20250124` also returns a 400 error: use the `computer_toolset_20260801` toolset on the Claude API and Google Cloud, or `computer_20251124` on Amazon Bedrock. A request that sends thinking blocks back after a change to `system`, `tools`, or earlier turns can also return a 400 error. On Amazon Bedrock, structured outputs aren't available for Claude Haiku 5.5. Adaptive thinking is on by default, so a response can begin with `thinking` blocks, and their text is omitted unless you set `thinking.display` to `"summarized"`. The same text also counts as more tokens. See the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide) for each change. For model-specific prompting patterns, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).
41* Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (`budget_tokens`), the sampling parameters `temperature`, `top_p`, and `top_k`, and assistant message prefill can each return a 400 error. `computer_20250124` also returns a 400 error: use the `computer_toolset_20260801` toolset on the Claude API and Google Cloud, or `computer_20251124` on Amazon Bedrock. A request that sends thinking blocks back after a change to `system`, `tools`, or earlier turns can also return a 400 error. Adaptive thinking is on by default, so a response can begin with `thinking` blocks, and their text is omitted unless you set `thinking.display` to `"summarized"`. The same text also counts as more tokens. See the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide) for each change. For model-specific prompting patterns, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).
4142* The Python and TypeScript SDKs now include classes, in beta, for the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) and the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool). You subclass one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback. See [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk).
4243* Claude Max and Team plans now include monthly API credits. To learn how to claim them, see [API credits for Max and Team plans](https://platform.claude.com/docs/en/about-claude/api-credits-for-subscribers).
4344* In Claude Managed Agents, a cloud environment with `limited` networking now also applies its `allowed_hosts` to the `web_search` and `web_fetch` tools. A `web_fetch` call for a URL on a host that `allowed_hosts` does not match returns a `url_not_allowed` error result to the agent. `web_search` omits results from such hosts. When `allowed_hosts` lists no hosts, neither tool returns a page or a search result. `allow_package_managers` and `allow_mcp_servers` add no hosts for these tools. To let the tools reach a host, add it to `allowed_hosts`, which also opens it to the sandbox. `unrestricted` networking and self-hosted environments do not limit these tools. See [Environment networking](https://platform.claude.com/docs/en/managed-agents/environments#networking).
from line 204
203204
204205### July 17, 2026
205206
206* The legacy **Workbench** ([platform.claude.com/workbench](https://platform.claude.com/workbench)) in the Claude Console is being sunset with access ending on August 17, 2026. Saved prompts, variables, and evals are not supported in the updated [Workbench](https://platform.claude.com/playground). You can export any data you want to keep from the banner and under your **Organizational Settings**. For more, see [How do I use the Workbench?](https://support.claude.com/en/articles/8606378-how-do-i-use-the-workbench) in the Claude Help Center.
207* The legacy **Workbench** ([platform.claude.com/workbench](https://platform.claude.com/workbench)) in the Claude Console is being sunset with access ending on August 17, 2026. Saved prompts, variables, and evals are not supported in the updated [Workbench](https://platform.claude.com/playground) in the Console. You can export any data you want to keep from the banner and under your **Organizational Settings**. For more, see [How do I use the Workbench?](https://support.claude.com/en/articles/8606378-how-do-i-use-the-workbench) in the Claude Help Center.
207208* The experimental prompt tools APIs for generating, improving, and templatizing prompts (`/v1/experimental/generate_prompt`, `/v1/experimental/improve_prompt`, and `/v1/experimental/templatize_prompt`) are being retired along with the Workbench on August 17, 2026. After removal, requests to these endpoints will return an error.
208209
209210### July 15, 2026
from line 625
624625
625626### June 23, 2025
626627
627* Console users with the Developer role can now access the [Cost](https://console.anthropic.com/settings/cost) page. Previously, the Developer role allowed access to the [Usage](https://console.anthropic.com/settings/usage) page, but not the Cost page.
628* In the Console, users with the Developer role can now access the [Cost](https://console.anthropic.com/settings/cost) page. Previously, the Developer role allowed access to the [Usage](https://console.anthropic.com/settings/usage) page, but not the Cost page.
628629
629630### June 11, 2025
630631
from line 743
742743### November 20th, 2024
743744
744745* We've updated our rate limits for the Messages API. We've replaced the tokens per minute rate limit with new input and output tokens per minute rate limits. Read more in [Rate limits](https://platform.claude.com/docs/en/api/rate-limits).
745* We've added support for [tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) in the [Workbench](https://console.anthropic.com/workbench).
746* We've added support for [tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) in the Console [Workbench](https://console.anthropic.com/workbench).
746747
747748### November 13th, 2024
748749
about-claude/api-credits-for-subscribers Changed · +2 / -2 lines
from line 52
5252| **Claude plan** | Max: the subscriber<br />Team: Primary Owner, Owner |
5353| **Claude Console organization** | Owner, Admin, or Billing |
5454
55If you don't have a Console organization, create one at [platform.claude.com](https://platform.claude.com/) first, or create one during the claim flow.
55If you don't have a Claude Console organization, create one in the Console at [platform.claude.com](https://platform.claude.com/) first, or create one during the claim flow.
5656
5757### Steps
5858
from line 85
8585| [Claude API](https://platform.claude.com/docs/en/api/overview) | Yes |
8686| [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) | Yes |
8787| [Claude Agent SDK](https://code.claude.com/docs/en/agent-sdk/overview) | Yes |
88| [Playground](https://platform.claude.com/playground) | Yes |
88| [Playground](https://platform.claude.com/playground) in the Claude Console | Yes |
8989| Claude Code | No |
9090| Extra usage in the Claude apps | No |
9191| Claude Platform on AWS, Bedrock, Google Cloud, Microsoft Foundry | No |
agents-and-tools/mcp-connector Changed · +0 / -2 lines
from line 1347
13471347 import (
13481348 "github.com/anthropics/anthropic-sdk-go/mcp"
13491349 )
1350
13511350 ```
13521351
13531352 ```java Java
from line 1529
15301529 }
15311530 fmt.Println(finalMessage.RawJSON())
15321531 }
1533
15341532 ```
15351533
15361534 ```java Java
agents-and-tools/tool-use/memory-tool Changed · +2 / -1 lines
from line 342
342342 using Anthropic;
343343 using Anthropic.Helpers.Beta;
344344 using Anthropic.Models.Beta.Messages;
345 using Model = Anthropic.Models.Messages.Model;
345346
346347 var client = new AnthropicClient();
347348
from line 352
351352 var runner = client.Beta.Messages.ToolRunner(
352353 new MessageCreateParams
353354 {
354 Model = Anthropic.Models.Messages.Model.ClaudeOpus5_5,
355 Model = Model.ClaudeOpus5_5,
355356 MaxTokens = 1024,
356357 Messages =
357358 [
agents-and-tools/tool-use/parallel-tool-use Changed · +1 / -1 lines
from line 212
212212
213213 // Simulate tool execution and format results correctly
214214 const toolResults: Anthropic.ToolResultBlockParam[] = toolUses
215 .filter((block): block is Anthropic.ToolUseBlock => block.type === "tool_use")
215 .filter((block) => block.type === "tool_use")
216216 .map((toolUse) => {
217217 const input = toolUse.input as Record<string, string>;
218218 let result: string;
api/beta-headers Changed · +1 / -1 lines
from line 16
1616
1717```http
1818POST /v1/messages
19x-api-key: YOUR_API_KEY
19Authorization: Bearer YOUR_API_KEY
2020anthropic-version: 2023-06-01
2121anthropic-beta: BETA_FEATURE_NAME
2222content-type: application/json
api/beta/organization/plugin_marketplaces Changed · +2 / -2 lines
from line 986
986986
987987- `repository_url: string`
988988
989 The `https://` URL of a public repository on github.com that holds the marketplace. Any other host, a URL with credentials in it, or one that does not name a repository is a 400.
989 The `https://` URL of a public repository on github.com that holds the marketplace. A URL longer than 2,048 characters, on any other host or scheme, with a port other than 443 or 80, with credentials in it, or that does not name exactly `owner/repo` (a trailing `.git` or `/` is accepted) is a 400. A private or missing repository is reported in the response, not refused.
990990
991991 minLength: 1
992992
993993- `ref: optional string or null`
994994
995 The branch to validate the tip of, or the full 40-character SHA of the commit to validate. When omitted, the branch a synchronization would read (usually the repository's default branch); if that is not the default branch, the report's `ref` says which branch was read. An empty string, or a value that is neither a branch name nor a 40-character SHA, is a 400.
995 The branch to validate the tip of, or the full 40-character SHA of the commit to validate. When omitted, the branch a synchronization would read (usually the repository's default branch); if that is not the default branch, the report's `ref` says which branch was read. An empty string, a value longer than 255 characters, or one that contains `..` or a character other than ASCII letters, digits, `.`, `_`, `-`, `+`, and `/`, is a 400. Any other value that is not a 40-character SHA is read as a branch name; if the repository has no such branch, the response is a report with `valid: false`, not a 400.
996996
997997 minLength: 1
998998
api/beta/organization/plugin_marketplaces/validate_repository Changed · +2 / -2 lines
from line 142
142142
143143- `repository_url: string`
144144
145 The `https://` URL of a public repository on github.com that holds the marketplace. Any other host, a URL with credentials in it, or one that does not name a repository is a 400.
145 The `https://` URL of a public repository on github.com that holds the marketplace. A URL longer than 2,048 characters, on any other host or scheme, with a port other than 443 or 80, with credentials in it, or that does not name exactly `owner/repo` (a trailing `.git` or `/` is accepted) is a 400. A private or missing repository is reported in the response, not refused.
146146
147147 minLength: 1
148148
149149- `ref: optional string or null`
150150
151 The branch to validate the tip of, or the full 40-character SHA of the commit to validate. When omitted, the branch a synchronization would read (usually the repository's default branch); if that is not the default branch, the report's `ref` says which branch was read. An empty string, or a value that is neither a branch name nor a 40-character SHA, is a 400.
151 The branch to validate the tip of, or the full 40-character SHA of the commit to validate. When omitted, the branch a synchronization would read (usually the repository's default branch); if that is not the default branch, the report's `ref` says which branch was read. An empty string, a value longer than 255 characters, or one that contains `..` or a character other than ASCII letters, digits, `.`, `_`, `-`, `+`, and `/`, is a 400. Any other value that is not a 40-character SHA is read as a branch name; if the repository has no such branch, the response is a report with `valid: false`, not a 400.
152152
153153 minLength: 1
154154
api/beta/organization/plugins/versions/create Changed · +2 / -2 lines
from line 280
280280
281281 - `manifest_version: string or null`
282282
283 The version string the manifest declares; null when it declares none.
283 The manifest's `version`, normalized for display: one leading `v` or `V` is dropped, and the result is returned only if it is 1 to 64 characters, starts with a digit, and uses only ASCII letters, digits, `.`, `+`, and `-`; otherwise `null`. For example, `"v1.4.0"` is returned as `"1.4.0"`, and `"latest"` as `null`. For a synchronized plugin, the `version` of its `marketplace.json` entry can take the place of the manifest's `version`. It is also `null` for a version stored before claude.ai began recording this field (August 2026).
284284
285285 - `plugin_id: string`
286286
from line 288
288288
289289 - `reach: "contained" or "privileged" or "remote" or null`
290290
291 How far the version reaches: `remote`, `privileged` or `contained`, as on the Plugin; null when not classifiable.
291 How far the version reaches: `remote`, `privileged`, `contained`, or `null`, as defined on the Plugin's `reach`.
292292
293293 - `"contained"`
294294
api/beta/organization/plugins/versions/list Changed · +2 / -2 lines
from line 272
272272
273273 - `manifest_version: string or null`
274274
275 The version string the manifest declares; null when it declares none.
275 The manifest's `version`, normalized for display: one leading `v` or `V` is dropped, and the result is returned only if it is 1 to 64 characters, starts with a digit, and uses only ASCII letters, digits, `.`, `+`, and `-`; otherwise `null`. For example, `"v1.4.0"` is returned as `"1.4.0"`, and `"latest"` as `null`. For a synchronized plugin, the `version` of its `marketplace.json` entry can take the place of the manifest's `version`. It is also `null` for a version stored before claude.ai began recording this field (August 2026).
276276
277277 - `plugin_id: string`
278278
from line 280
280280
281281 - `reach: "contained" or "privileged" or "remote" or null`
282282
283 How far the version reaches: `remote`, `privileged` or `contained`, as on the Plugin; null when not classifiable.
283 How far the version reaches: `remote`, `privileged`, `contained`, or `null`, as defined on the Plugin's `reach`.
284284
285285 - `"contained"`
286286
api/beta/organization/plugins/versions/retrieve Changed · +2 / -2 lines
from line 259
259259
260260 - `manifest_version: string or null`
261261
262 The version string the manifest declares; null when it declares none.
262 The manifest's `version`, normalized for display: one leading `v` or `V` is dropped, and the result is returned only if it is 1 to 64 characters, starts with a digit, and uses only ASCII letters, digits, `.`, `+`, and `-`; otherwise `null`. For example, `"v1.4.0"` is returned as `"1.4.0"`, and `"latest"` as `null`. For a synchronized plugin, the `version` of its `marketplace.json` entry can take the place of the manifest's `version`. It is also `null` for a version stored before claude.ai began recording this field (August 2026).
263263
264264 - `plugin_id: string`
265265
from line 267
267267
268268 - `reach: "contained" or "privileged" or "remote" or null`
269269
270 How far the version reaches: `remote`, `privileged` or `contained`, as on the Plugin; null when not classifiable.
270 How far the version reaches: `remote`, `privileged`, `contained`, or `null`, as defined on the Plugin's `reach`.
271271
272272 - `"contained"`
273273
api/claude-code/routines-fire Changed · +1 / -1 lines
from line 20
2020
2121| Aspect | This endpoint | Claude Platform APIs |
2222| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
23| Authentication | `Authorization: Bearer` with a per-routine token (`sk-ant-oat01-...`) created at [claude.ai/code/routines](https://claude.ai/code/routines) | `x-api-key` with a Claude API key from Claude Console |
23| Authentication | `Authorization: Bearer` with a per-routine token (`sk-ant-oat01-...`) created at [claude.ai/code/routines](https://claude.ai/code/routines) | A Claude API key from Claude Console, sent as `Authorization: Bearer` |
2424| Token scope | One routine only; no read access | Workspace-level |
2525| SDK support | None | Available in all [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) |
2626| Billing | Claude Code subscription usage on claude.ai | Claude Platform usage |
api/compliance/apps Changed · +1 / -1 lines
from line 3552
35523552
35533553- `multi_file_format: optional string`
35543554
3555 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the artifact copied from its type (the app that displays every artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the artifact's owns that type. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
3555 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the Artifact copied from its type (the app that displays every Artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the Artifact's owns that type. Files the version uses from another Artifact are always listed there and left out. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
35563556
35573557#### Headers
35583558
api/compliance/apps/code Changed · +1 / -1 lines
from line 259
259259
260260- `multi_file_format: optional string`
261261
262 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the artifact copied from its type (the app that displays every artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the artifact's owns that type. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
262 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the Artifact copied from its type (the app that displays every Artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the Artifact's owns that type. Files the version uses from another Artifact are always listed there and left out. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
263263
264264#### Headers
265265
api/compliance/apps/code/artifacts Changed · +1 / -1 lines
from line 257
257257
258258- `multi_file_format: optional string`
259259
260 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the artifact copied from its type (the app that displays every artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the artifact's owns that type. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
260 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the Artifact copied from its type (the app that displays every Artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the Artifact's owns that type. Files the version uses from another Artifact are always listed there and left out. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
261261
262262### Headers
263263
api/compliance/apps/code/artifacts/retrieve_version Changed · +1 / -1 lines
from line 43
4343
4444- `multi_file_format: optional string`
4545
46 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the artifact copied from its type (the app that displays every artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the artifact's owns that type. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
46 Set to `zip`, its only value, to receive a version that has more than one file as a ZIP archive of its files with an index, `files.json`. Files the Artifact copied from its type (the app that displays every Artifact of that type) are listed under `omitted_files` in the index, and left out of the archive, when an organization other than the Artifact's owns that type. Files the version uses from another Artifact are always listed there and left out. A Claude Doc's version never comes back as a ZIP: it is answered as without this parameter, except that a version with more than one file, one of them with a name the API cannot export, gets 422 `file_set_unavailable`. A version with one file is returned as that file, as without this parameter.
4747
4848## Headers
4949
api/overview Changed · +1 / -1 lines
from line 163
163163* **Spend limits**: Maximum monthly cost for API usage
164164* **Rate limits**: Maximum number of requests per minute (RPM) and tokens per minute (TPM)
165165
166You can view your rate limits on the [Rate limits](https://platform.claude.com/usage/limits) page and your spend limits on the [Billing](https://platform.claude.com/settings/billing) page in the Console. For higher rate limits or a higher monthly spend cap, use **Request tier increase** on the Rate limits page.
166In the Console, you can view your rate limits on the [Rate limits](https://platform.claude.com/usage/limits) page and your spend limits on the [Billing](https://platform.claude.com/settings/billing) page. For higher rate limits or a higher monthly spend cap, use **Request tier increase** on the Rate limits page.
167167
168168For detailed information about limits, tiers, and the token bucket algorithm used for rate limiting, see [Rate limits](https://platform.claude.com/docs/en/api/rate-limits).
169169
build-with-claude/batch-processing Changed · +2 / -2 lines
from line 43
4343* A Message Batch is limited to either 100,000 Message requests or 256 MB in size, whichever is reached first.
4444* The system processes each batch as fast as possible, with most batches completing within 1 hour. You can access batch results when all messages have completed or after 24 hours, whichever comes first. Batches expire if processing does not complete within 24 hours.
4545* Batch results are available for 29 days after creation. After that, you may still view the Batch, but its results will no longer be available for download.
46* Batches are scoped to a [Workspace](https://platform.claude.com/settings/workspaces). You may view all batches (and their results) that were created within the Workspace your request runs in.
46* Batches are scoped to a [Workspace](https://platform.claude.com/settings/workspaces) in the Claude Console. You may view all batches (and their results) that were created within the Workspace your request runs in.
4747* Rate limits apply to both Batches API HTTP requests and the number of requests within a batch waiting to be processed. See [Message Batches API rate limits](https://platform.claude.com/docs/en/api/rate-limits#message-batches-api). Additionally, processing may be slowed down based on current demand and your request volume. In that case, you may see more requests expiring after 24 hours.
48* Because of high throughput and concurrent processing, batches may go slightly over your Workspace's configured [spend limit](https://platform.claude.com/settings/billing).
48* Because of high throughput and concurrent processing, batches may go slightly over the [spend limit](https://platform.claude.com/settings/billing) configured in the Claude Console for your Workspace.
4949* Each batched request must have `max_tokens` of at least `1`. `max_tokens: 0` ([cache pre-warming](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pre-warming-the-cache)) is not supported inside a batch, because an ephemeral cache entry written during batch processing would likely expire before the follow-up request runs.
5050
5151### Supported models
build-with-claude/claude-in-amazon-bedrock Changed · +1 / -1 lines
from line 373
373373* [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)
374374* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), and [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool)
375375* [Citations](https://platform.claude.com/docs/en/build-with-claude/citations)
376* [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)
376377
377378### Features not supported
378379
379* [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)
380380* Input sources (URL sources for images and documents, Files API)
381381* Server-side tools (code execution, web search, web fetch, advisor)
382382* Agent infrastructure (Agent Skills, MCP connector, programmatic tool calling)
build-with-claude/claude-on-amazon-bedrock-legacy Changed · +1 / -1 lines
from line 730
730730* [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)
731731* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), and [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool)
732732* [Citations](https://platform.claude.com/docs/en/build-with-claude/citations)
733* [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), for the models in the Amazon Bedrock note under its [Compatibility](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#compatibility) section
733* [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)
734734
735735### Features not supported
736736
build-with-claude/effort Changed · +1 / -3 lines
from line 105
105105 }
106106 });
107107
108 const textBlock = response.content.find(
109 (block): block is Anthropic.TextBlock => block.type === "text"
110 );
108 const textBlock = response.content.find((block) => block.type === "text");
111109 console.log(textBlock?.text);
112110 ```
113111
build-with-claude/fallback-credit Changed · +1 / -1 lines
from line 513
513513The retry model must be one of the refused model's permitted fallback targets. For Claude Fable 5.1, Claude Fable 5, and Claude Opus 5.5, those are Claude Opus 4.8 (`claude-opus-4-8`) and Claude Opus 5 (`claude-opus-5`). For Claude Opus 5, it is Claude Opus 4.8. For Claude Sonnet 5.5, it is Claude Sonnet 5 (`claude-sonnet-5`).
514514
515515<Accordion title="Looking up permitted fallback targets programmatically">
516 On the Claude API and Claude Platform on AWS, the target list is published as `allowed_fallback_models` on each model's entry in the [Models API](https://platform.claude.com/docs/en/api/models/list) when the `server-side-fallback-2026-07-01` beta header is set. The list is not yet visible under the `fallback-credit-*` header alone. It is not exposed on Amazon Bedrock, Google Cloud, or Microsoft Foundry.
516 On the Claude API and Claude Platform on AWS, the target list is published as `allowed_fallback_models` on each model's entry in the [Models API](https://platform.claude.com/docs/en/api/beta/models/list) when the `server-side-fallback-2026-07-01` beta header is set. The list is not yet visible under the `fallback-credit-*` header alone. It is not exposed on Amazon Bedrock, Google Cloud, or Microsoft Foundry.
517517</Accordion>
518518
519519## Checking that the credit applied