What this read moved
1–25 of 49This capture is too large to show at once. Changes 1-25 of 49 are below, significant first; the rest are on the following screens.
agents-and-tools/mcp-connector Changed · +10 / -6 lines
## Compatibility
from line 2
22title: MCP connector
33url: https://platform.claude.com/docs/en/agents-and-tools/mcp-connector
44description: Connect to remote MCP servers directly from the Messages API without an MCP client, and allowlist, denylist, or configure individual tools.
5featureMetadata:
6 status: beta
7 betaHeader: mcp-client-2025-11-20
8 zdr: not-eligible
9 supportedPlatforms:
10 Claude API: beta
11 Claude Platform on AWS: beta
12 Amazon Bedrock: not available
13 Google Cloud: not available
14 Microsoft Foundry: beta
515---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `mcp-client-2025-11-20`
10- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible
11- Platforms: Claude API (beta), Claude Platform on AWS (beta), Microsoft Foundry (beta); not available on Amazon Bedrock, Google Cloud
1216
1317Claude's Model Context Protocol (MCP) connector feature enables you to connect to remote MCP servers directly from the Messages API without a separate MCP client.
1418
agents-and-tools/tool-use/browser-use-tool Changed · +19 / -5 lines
## Compatibility
from line 2
22title: Browser use tool
33url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool
44description: Let Claude navigate, read, and interact with webpages in your own browser environment with the browser use tool.
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedModels:
11 - claude-fable-5-1
12 - claude-mythos-5-1
13 - claude-fable-5
14 - claude-mythos-5
15 - claude-opus-5
16 - claude-sonnet-5
17 - claude-opus-4-8
18 supportedPlatforms:
19 Claude API: ga
20 Claude Platform on AWS: not available
21 Amazon Bedrock: not available
22 Google Cloud: ga
23 Microsoft Foundry: not available
524---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`
10- Platforms: Claude API, Google Cloud; not available on Claude Platform on AWS, Amazon Bedrock, Microsoft Foundry
1125
1226The browser use tool lets Claude navigate, read, and interact with webpages in a browser that your application runs. Claude works with the page both through its structure (the accessibility tree, elements, forms, and tabs) and through screenshots and viewport coordinates.
1327
agents-and-tools/tool-use/code-execution-tool Changed · +28 / -8 lines
## Compatibility
from line 2
22title: Code execution tool
33url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool
44description: Run Python and bash code in a sandboxed container to analyze data, generate files, and iterate on solutions.
5featureMetadata:
6 status: ga
7 zdr: not-eligible
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-opus-5
14 - claude-opus-4-8
15 - claude-opus-4-7
16 - claude-opus-4-6
17 - claude-opus-4-5-20251101
18 - claude-sonnet-5
19 - claude-sonnet-4-6
20 - claude-sonnet-4-5-20250929
21 - claude-haiku-4-5-20251001
22 supportedPlatforms:
23 Claude API: ga
24 Claude Platform on AWS: ga
25 Amazon Bedrock: not available
26 Google Cloud: not available
27 Microsoft Foundry:
28 availability: ga
29 note: On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), code execution requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).
30 details:
31 - Every supported model accepts all three [tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions). On Claude Haiku 4.5, programmatic tool calling and REPL state persistence aren't available, so the newer versions behave like `code_execution_20250825` there.
32 - For [Claude Mythos Preview](https://anthropic.com/glasswing), code execution is supported on the Claude API and Microsoft Foundry.
533---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible
9- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `claude-sonnet-4-6`, `claude-sonnet-4-5-20250929`, `claude-haiku-4-5-20251001`
10- Platforms: Claude API, Claude Platform on AWS, Microsoft Foundry [1]; not available on Amazon Bedrock, Google Cloud
11- Every supported model accepts all three [tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions). On Claude Haiku 4.5, programmatic tool calling and REPL state persistence aren't available, so the newer versions behave like `code_execution_20250825` there.
12- For [Claude Mythos Preview](https://anthropic.com/glasswing), code execution is supported on the Claude API and Microsoft Foundry.
131. On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), code execution requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).
1434
1535Claude can analyze data, create visualizations, perform complex calculations, run system commands, create and edit files, and process uploaded files directly within the API conversation. The code execution tool allows Claude to run Bash commands and manipulate files, including writing code, in a secure, sandboxed environment.
1636
agents-and-tools/tool-use/computer-use-tool Changed · +22 / -7 lines
## Compatibility
from line 2
22title: Computer use tool
33url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool
44description: Give Claude screenshot, mouse, and keyboard control of a desktop environment with the computer use tool, the computer_toolset_20260801 client toolset.
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedModels:
11 - claude-fable-5-1
12 - claude-mythos-5-1
13 - claude-fable-5
14 - claude-mythos-5
15 - claude-opus-5
16 - claude-sonnet-5
17 - claude-opus-4-8
18 supportedPlatforms:
19 Claude API: ga
20 Claude Platform on AWS: beta
21 Amazon Bedrock: beta
22 Google Cloud: ga
23 Microsoft Foundry: beta
24 details:
25 - Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 support computer use only through the earlier `computer_20251124` tool version, which requires a beta header; see [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
26 - Platforms other than the Claude API and Google Cloud currently offer only the [earlier beta tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
527---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`
10- Platforms: Claude API, Claude Platform on AWS (beta), Amazon Bedrock (beta), Google Cloud, Microsoft Foundry (beta)
11- Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 support computer use only through the earlier `computer_20251124` tool version, which requires a beta header; see [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
12- Platforms other than the Claude API and Google Cloud currently offer only the [earlier beta tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
1328
1429Claude can interact with computer environments through the computer use tool, which provides screenshot capabilities and mouse/keyboard control for autonomous desktop interaction.
1530
agents-and-tools/tool-use/programmatic-tool-calling Changed · +27 / -8 lines
## Compatibility
from line 2
22title: Programmatic tool calling
33url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling
44description: Let Claude call your tools from code in the code execution container, cutting model round trips and token use in multi-tool workflows.
5featureMetadata:
6 status: ga
7 zdr: not-eligible
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-opus-5
14 - claude-opus-4-8
15 - claude-opus-4-7
16 - claude-opus-4-6
17 - claude-opus-4-5-20251101
18 - claude-sonnet-5
19 - claude-sonnet-4-6
20 - claude-sonnet-4-5-20250929
21 supportedPlatforms:
22 Claude API: ga
23 Claude Platform on AWS: ga
24 Amazon Bedrock: not available
25 Google Cloud: not available
26 Microsoft Foundry:
27 availability: ga
28 note: On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), programmatic tool calling requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).
29 details:
30 - Programmatic tool calling requires the code execution tool with the `code_execution_20260120` or later [tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions).
31 - Claude Haiku 4.5 accepts the `code_execution_20260120` and later tool versions but doesn't support programmatic tool calling.
532---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible
9- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `claude-sonnet-4-6`, `claude-sonnet-4-5-20250929`
10- Platforms: Claude API, Claude Platform on AWS, Microsoft Foundry [1]; not available on Amazon Bedrock, Google Cloud
11- Programmatic tool calling requires the code execution tool with the `code_execution_20260120` or later [tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions).
12- Claude Haiku 4.5 accepts the `code_execution_20260120` and later tool versions but doesn't support programmatic tool calling.
131. On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), programmatic tool calling requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).
1433
1534Programmatic tool calling allows Claude to write code that calls your tools programmatically within a [code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) container, rather than requiring round trips through the model for each tool invocation. This reduces latency for multi-tool workflows and decreases token consumption by allowing Claude to filter or process data before it reaches the model's context window. On agentic search benchmarks like [BrowseComp](https://arxiv.org/abs/2504.12516) and [DeepSearchQA](https://github.com/google-deepmind/deepsearchqa), which test multistep web research and complex information retrieval, adding programmatic tool calling on top of basic search tools improved performance by an average of 11% while using 24% fewer input tokens (see [Improved web search with dynamic filtering](https://claude.com/blog/improved-web-search-with-dynamic-filtering)).
1635
build-with-claude/cache-diagnostics Changed · +12 / -6 lines
## Compatibility
from line 2
22title: Cache diagnostics
33url: https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics
44description: Diagnose unexpected prompt cache misses by comparing consecutive requests and identifying exactly where the prompt prefix diverged.
5featureMetadata:
6 status: beta
7 betaHeader: cache-diagnosis-2026-04-07
8 zdr:
9 eligibility: eligible
10 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
11 supportedPlatforms:
12 Claude API: beta
13 Claude Platform on AWS: not available
14 Amazon Bedrock: not available
15 Google Cloud: not available
16 Microsoft Foundry: not available
517---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `cache-diagnosis-2026-04-07`
10- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
11- Platforms: Claude API (beta); not available on Claude Platform on AWS, Amazon Bedrock, Google Cloud, Microsoft Foundry
1218
1319[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) cuts latency and cost significantly, but only when the beginning of your prompt is byte-for-byte identical to a recent request. A reordered tool, a timestamp interpolated into your system prompt, or an edit to an earlier message can silently invalidate the cache. Without cache diagnostics, the only signal is `usage.cache_read_input_tokens` dropping to zero, with no indication of what changed.
1420
build-with-claude/citations Changed · +11 / -4 lines
## Compatibility
from line 2
22title: Citations
33url: https://platform.claude.com/docs/en/build-with-claude/citations
44description: Ground Claude's responses in your source documents. Citations return the exact passages that support each claim, so you can verify answers and surface sources to your users.
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedPlatforms:
11 Claude API: ga
12 Claude Platform on AWS: ga
13 Amazon Bedrock: ga
14 Google Cloud: ga
15 Microsoft Foundry: ga
516---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Platforms: Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud, Microsoft Foundry
1017
1118Claude can provide detailed citations when answering questions about documents, helping you track and verify the sources behind each response.
1219
build-with-claude/compaction-background Changed · +21 / -6 lines
## Compatibility
from line 2
22title: Compaction in the background
33url: https://platform.claude.com/docs/en/build-with-claude/compaction-background
44description: Request an on-demand compaction summary while the conversation continues on its full history, then swap the block in when it arrives.
5featureMetadata:
6 status: beta
7 betaHeader: compact-2026-09-04
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-mythos-preview
14 - claude-opus-5
15 - claude-opus-4-8
16 - claude-opus-4-7
17 - claude-opus-4-6
18 - claude-sonnet-5
19 - claude-sonnet-4-6
20 supportedPlatforms:
21 Claude API: beta
22 Claude Platform on AWS: beta
23 Amazon Bedrock: not available
24 Google Cloud: beta
25 Microsoft Foundry: beta
526---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `compact-2026-09-04`
10- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `claude-sonnet-4-6`
11- Platforms: Claude API (beta), Claude Platform on AWS (beta), Microsoft Foundry (beta); not available on Amazon Bedrock, Google Cloud
1227
1328Background compaction, often called async compaction, changes two things in the [compaction loop](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#compact-in-a-loop): the compaction request runs while the conversation continues on its full history, and the swap waits until the block arrives. [Continue from the summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#continue-from-the-summary) and [Handle a missing summary or an error](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#when-no-summary-comes-back) apply unchanged.
1429
build-with-claude/compaction-keep-recent-turns Changed · +21 / -6 lines
## Compatibility
from line 2
22title: Compaction that keeps recent turns
33url: https://platform.claude.com/docs/en/build-with-claude/compaction-keep-recent-turns
44description: Summarize the older turns of a conversation with on-demand compaction and send the most recent turns after the summary, word for word.
5featureMetadata:
6 status: beta
7 betaHeader: compact-2026-09-04
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-mythos-preview
14 - claude-opus-5
15 - claude-opus-4-8
16 - claude-opus-4-7
17 - claude-opus-4-6
18 - claude-sonnet-5
19 - claude-sonnet-4-6
20 supportedPlatforms:
21 Claude API: beta
22 Claude Platform on AWS: beta
23 Amazon Bedrock: not available
24 Google Cloud: beta
25 Microsoft Foundry: beta
526---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `compact-2026-09-04`
10- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `claude-sonnet-4-6`
11- Platforms: Claude API (beta), Claude Platform on AWS (beta), Microsoft Foundry (beta); not available on Amazon Bedrock, Google Cloud
1227
1328Keep-tail compaction keeps the last few turns of a conversation word for word after the summary. It changes two things in the [compaction loop](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#compact-in-a-loop): which messages go into the compaction request, and what you send after the block. Everything in [Continue from the summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#continue-from-the-summary) applies unchanged.
1429
build-with-claude/compaction-on-demand Changed · +23 / -6 lines
## Compatibility
from line 2
22title: Compaction on demand
33url: https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand
44description: Ask Claude to summarize a conversation when your application chooses, then continue from the summary.
5featureMetadata:
6 status: beta
7 betaHeader: compact-2026-09-04
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-mythos-preview
14 - claude-opus-5
15 - claude-opus-4-8
16 - claude-opus-4-7
17 - claude-opus-4-6
18 - claude-sonnet-5
19 - claude-sonnet-4-6
20 supportedPlatforms:
21 Claude API: beta
22 Claude Platform on AWS: beta
23 Amazon Bedrock: not available
24 Google Cloud: beta
25 Microsoft Foundry: beta
526---
627
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `compact-2026-09-04`
10- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `claude-sonnet-4-6`
11- Platforms: Claude API (beta), Claude Platform on AWS (beta), Microsoft Foundry (beta); not available on Amazon Bedrock, Google Cloud
12
1328With on-demand compaction, your application decides when a conversation is summarized: you send one request with the `compaction` parameter, and Claude returns a summary in place of a reply.
1429
1530## How on-demand compaction works
from line 766
751766</CodeGroup>
752767
753768The check on `stop_reason` comes before the code looks for the block; [Handle a missing summary or an error](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#when-no-summary-comes-back) says why. The history is replaced, not appended to: the returned message replaces every message the request carried, under the rules in [Continue from the summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#continue-from-the-summary). When no summary comes back, the loop keeps its history and asks again after the next turn.
769
770The SDK [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) in Python, TypeScript, C#, Go, and Java can send the compaction request for you. When you decide to compact, call `compact_before_next_turn()` on the runner (`compactBeforeNextTurn()` in TypeScript and Java, `CompactBeforeNextTurn()` in C# and Go). Once the current turn and its tool calls finish, the runner sends the compaction request and replaces its history with the returned message. Create the runner with the `compact-2026-09-04` beta, because the runner doesn't add it. The runner builds the request from its own parameters and leaves `context_management` out. If those parameters include `stop_sequences`, a `tool_choice` of type `any` or `tool`, or a structured-output `output_config.format`, the API rejects the request with a 400 error. [Request a summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#request-a-summary) explains why. The runner refuses to compact while its `context_management` has a compaction edit, so use one kind of compaction on a runner.
754771
755772### When to compact
756773
build-with-claude/compaction-thinking-blocks Changed · +22 / -7 lines
## Compatibility
from line 2
22title: Compaction and preserved thinking
33url: https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks
44description: When thinking blocks in turns kept after on-demand compaction stay valid on models with preserved thinking, and how to check.
5featureMetadata:
6 status: beta
7 betaHeader: compact-2026-09-04
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-mythos-preview
14 - claude-opus-5
15 - claude-opus-4-8
16 - claude-opus-4-7
17 - claude-opus-4-6
18 - claude-sonnet-5
19 - claude-sonnet-4-6
20 supportedPlatforms:
21 Claude API: beta
22 Claude Platform on AWS: beta
23 Amazon Bedrock: not available
24 Google Cloud: beta
25 Microsoft Foundry: beta
526---
627
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `compact-2026-09-04`
10- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `claude-sonnet-4-6`
11- Platforms: Claude API (beta), Claude Platform on AWS (beta), Microsoft Foundry (beta); not available on Amazon Bedrock, Google Cloud
12
1328Skip this page unless you send thinking blocks back to a model with [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and keep turns after the compaction block. Kept turns are the turns that follow the block: recent turns you left out of the compaction request, as in [Compaction that keeps recent turns](https://platform.claude.com/docs/en/build-with-claude/compaction-keep-recent-turns), or turns that arrived while the summary was being written, as in [Compaction in the background](https://platform.claude.com/docs/en/build-with-claude/compaction-background).
1429
1530Models with preserved thinking check earlier thinking blocks against the conversation that produced them. A summary replaces part of that conversation, but the check accepts the swap when the API wrote the summary, so the thinking in kept turns can stay valid.
from line 37
2237* **The kept turns directly follow the summarized messages, and you send them unchanged.** Send each kept message exactly as it is in your history. Don't skip or add a message between the last summarized message and the first kept one. The first kept message must also have a different role from the last summarized message, and it can't be a mid-conversation `role: "system"` message. Otherwise, the API merges it into the last summarized message. One way to get the first kept message right is to compact exactly the `messages` of a request you already sent. The kept turns then start with Claude's reply to it.
2338* **`system` and the `tools` not marked `defer_loading: true` don't change.** They are the same on the compaction request as on the requests that produced the kept thinking, and they stay the same on the requests that follow. [Change the system prompt or tools](https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks#change-the-system-prompt-or-tools) covers how to change them safely.
2439
25If a condition doesn't hold, nothing fails when you compact, and the API accepts the block on later requests either way. The failure comes on the first later request that sends the kept thinking where the API enforces the check: a 400 error by default, or dropped thinking blocks if the request sets `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. In the Message Batches API, an item that leaves the field unset drops the blocks instead. [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) describes both outcomes, and [When the API enforces the check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement) says which requests are checked.
40If a condition doesn't hold, nothing fails when you compact, and the API accepts the block on later requests either way. The failure comes on the first later request that sends the kept thinking where the API enforces the check: a 400 error by default, or dropped thinking blocks if the request sets `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. In the Message Batches API, an item that leaves the field unset doesn't fail. Where the check applies by default, the API drops the blocks instead. [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) describes both outcomes, and [When the API enforces the check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement) says which requests are checked.
2641
2742## Compact again without breaking older thinking
2843
build-with-claude/compaction-threshold Changed · +26 / -7 lines
## Compatibility
from line 2
22title: Compaction at a token threshold
33url: https://platform.claude.com/docs/en/build-with-claude/compaction-threshold
44description: Have the API summarize older context automatically, inside an ordinary request, when the conversation reaches a token threshold you set.
5featureMetadata:
6 status: beta
7 betaHeader: compact-2026-01-12
8 zdr:
9 eligibility: eligible
10 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
11 supportedModels:
12 - claude-fable-5-1
13 - claude-mythos-5-1
14 - claude-fable-5
15 - claude-mythos-5
16 - claude-mythos-preview
17 - claude-opus-5
18 - claude-opus-4-8
19 - claude-opus-4-7
20 - claude-opus-4-6
21 - claude-sonnet-5
22 - claude-sonnet-4-6
23 supportedPlatforms:
24 Claude API: beta
25 Claude Platform on AWS: beta
26 Amazon Bedrock: beta
27 Google Cloud: beta
28 Microsoft Foundry: beta
529---
630
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `compact-2026-01-12`
10- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
11- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `claude-sonnet-4-6`
12- Platforms: Claude API (beta), Claude Platform on AWS (beta), Amazon Bedrock (beta), Google Cloud (beta), Microsoft Foundry (beta)
13
1431Threshold compaction is the automatic kind of compaction: you set a token threshold on your ordinary requests, and the API summarizes older context partway through a request once the threshold is reached. It is supported alongside on-demand compaction, where you decide when the summary is written (see [Compaction on demand](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand)). To choose between them, see [Choose how to compact](https://platform.claude.com/docs/en/build-with-claude/compaction#choose-how-to-compact).
1532
1633Compaction extends the effective context length for long-running conversations and tasks by automatically summarizing older context when approaching the context window limit. It also keeps the active context small: as a conversation grows, response quality degrades, so compaction replaces older content with a concise summary.
from line 1701
16841701 puts next_response.content
16851702 ```
16861703</CodeGroup>
1704
1705In Python, use `client.beta.messages`, as the samples on this page do. If you call `client.messages` and serialize blocks yourself, a plain `model_dump()` adds `text: null` and `citations: null` to the `compaction` block. The API then rejects the request with a 400 error (`Extra inputs are not permitted`). Use `to_dict()` or `model_dump(exclude_none=True)` instead. [Continue from the summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#continue-from-the-summary) gives the same advice for on-demand compaction.
16871706
16881707When the API receives a `compaction` block, all content blocks before it are ignored. You can either:
16891708
build-with-claude/effort Changed · +24 / -5 lines
## Compatibility
from line 2
22title: Effort
33url: https://platform.claude.com/docs/en/build-with-claude/effort
44description: Control how many tokens Claude uses when responding with the effort parameter, trading off between response thoroughness and token efficiency.
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedModels:
11 - claude-fable-5-1
12 - claude-mythos-5-1
13 - claude-fable-5
14 - claude-mythos-5
15 - claude-mythos-preview
16 - claude-opus-5
17 - claude-opus-4-8
18 - claude-opus-4-7
19 - claude-opus-4-6
20 - claude-opus-4-5-20251101
21 - claude-sonnet-5
22 - claude-sonnet-4-6
23 supportedPlatforms:
24 Claude API: ga
25 Claude Platform on AWS: ga
26 Amazon Bedrock: ga
27 Google Cloud: ga
28 Microsoft Foundry: ga
529---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `claude-sonnet-4-6`
10- Platforms: Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud, Microsoft Foundry
1130
1231The effort parameter lets you control how many tokens Claude spends when responding to requests. You can trade off between response thoroughness and token efficiency with a single model. The top-level effort parameter is available on all supported models with no beta header required. [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) is in beta.
1332
build-with-claude/files Changed · +11 / -5 lines
## Compatibility
from line 2
22title: Files API
33url: https://platform.claude.com/docs/en/build-with-claude/files
44description: Upload files once, reference them by file_id in Messages requests, and download outputs created by skills or the code execution tool.
5featureMetadata:
6 status: ga
7 zdr: not-eligible
8 supportedPlatforms:
9 Claude API: ga
10 Claude Platform on AWS: beta
11 Amazon Bedrock: not available
12 Google Cloud: not available
13 Microsoft Foundry:
14 availability: beta
15 note: On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), the Files API requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).
516---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible
9- Platforms: Claude API, Claude Platform on AWS (beta), Microsoft Foundry (beta) [1]; not available on Amazon Bedrock, Google Cloud
101. On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), the Files API requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).
1117
1218The Files API lets you upload and manage files to use with the Claude API without re-uploading content with each request. This is particularly useful when using the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) to provide inputs (for example, datasets and documents) and then download outputs (for example, charts). You can [explore the API reference directly](https://platform.claude.com/docs/en/api/files/upload), in addition to this guide.
1319
build-with-claude/pdf-support Changed · +11 / -4 lines
## Compatibility
from line 2
22title: PDF support
33url: https://platform.claude.com/docs/en/build-with-claude/pdf-support
44description: "Process PDFs with Claude: extract text, analyze charts, and understand visual content from your documents."
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedPlatforms:
11 Claude API: ga
12 Claude Platform on AWS: ga
13 Amazon Bedrock: ga
14 Google Cloud: ga
15 Microsoft Foundry: ga
516---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Platforms: Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud, Microsoft Foundry
1017
1118You can ask Claude about any text, pictures, charts, and tables in PDFs you provide. Some sample use cases:
1219
build-with-claude/structured-outputs Changed · +28 / -6 lines
## Compatibility
from line 2
22title: Structured outputs
33url: https://platform.claude.com/docs/en/build-with-claude/structured-outputs
44description: Get validated JSON results from agent workflows
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedModels:
11 - claude-fable-5-1
12 - claude-mythos-5-1
13 - claude-fable-5
14 - claude-mythos-5
15 - claude-mythos-preview
16 - claude-opus-5
17 - claude-opus-4-8
18 - claude-opus-4-7
19 - claude-opus-4-6
20 - claude-sonnet-5
21 - claude-sonnet-4-6
22 - claude-sonnet-4-5-20250929
23 - claude-opus-4-5-20251101
24 - claude-haiku-4-5-20251001
25 supportedPlatforms:
26 Claude API: ga
27 Claude Platform on AWS: ga
28 Amazon Bedrock:
29 availability: ga
30 note: On Amazon Bedrock, structured outputs are available for Claude Opus 4.6, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Opus 4.5, and Claude Haiku 4.5.
31 Google Cloud: ga
32 Microsoft Foundry: ga
533---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-mythos-preview`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-5`, `claude-sonnet-4-6`, `claude-sonnet-4-5-20250929`, `claude-opus-4-5-20251101`, `claude-haiku-4-5-20251001`
10- Platforms: Claude API, Claude Platform on AWS, Amazon Bedrock [1], Google Cloud, Microsoft Foundry
111. On Amazon Bedrock, structured outputs are available for Claude Opus 4.6, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Opus 4.5, and Claude Haiku 4.5.
1234
1335Structured outputs constrain Claude's responses to follow a specific schema, ensuring valid, parseable output for downstream processing. Structured outputs provide two complementary features:
1436
build-with-claude/task-budgets Changed · +11 / -5 lines
## Compatibility
from line 2
22title: Task budgets
33url: https://platform.claude.com/docs/en/build-with-claude/task-budgets
44description: Give Claude an advisory token budget for the full agentic loop to help the model self-regulate on long agentic tasks.
5featureMetadata:
6 status: beta
7 betaHeader: task-budgets-2026-03-13
8 supportedModels:
9 - claude-fable-5-1
10 - claude-mythos-5-1
11 - claude-fable-5
12 - claude-mythos-5
13 - claude-opus-5
14 - claude-opus-4-8
15 - claude-opus-4-7
516---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `task-budgets-2026-03-13`
10- Supported models: `claude-fable-5-1`, `claude-mythos-5-1`, `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`
1117
1218Task budgets let you tell Claude how many tokens it has for a full agentic loop, including thinking, tool calls, tool results, and output. The model sees a running countdown and uses it to prioritize work and finish gracefully as the budget is consumed.
1319
build-with-claude/token-counting Changed · +11 / -4 lines
## Compatibility
from line 2
22title: Token counting
33url: https://platform.claude.com/docs/en/build-with-claude/token-counting
44description: Count the tokens in a message before you send it to Claude. Use token counts to manage rate limits and costs, make model routing decisions, and fit prompts to a target length.
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: eligible
9 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
10 supportedPlatforms:
11 Claude API: ga
12 Claude Platform on AWS: ga
13 Amazon Bedrock: ga
14 Google Cloud: ga
15 Microsoft Foundry: ga
516---
6
7## Compatibility
8- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))
9- Platforms: Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud, Microsoft Foundry
1017
1118Token counting lets you determine the number of tokens in a message before you send it to Claude. This helps you make informed decisions about your prompts and usage. With token counting, you can:
1219
managed-agents/agent-setup Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Define your agent
33url: https://platform.claude.com/docs/en/managed-agents/agent-setup
44description: Create a reusable, versioned agent configuration.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113An agent is a reusable, versioned configuration that defines persona and capabilities. It bundles the model, system prompt, tools, MCP servers, and skills that shape how Claude behaves during a session.
1214
managed-agents/budgets Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Session budgets
33url: https://platform.claude.com/docs/en/managed-agents/budgets
44description: Cap a session's spend with a hard dollar budget enforced at public list rates.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113A session budget is an optional hard spend ceiling you set when you [create a session](https://platform.claude.com/docs/en/managed-agents/sessions). The platform continuously prices everything the session consumes at public list rates (the session's **list cost**) and stops issuing new model requests once that cost reaches the budget. The request in flight when the cap is crossed still finishes, so the final list cost can land [a fraction past the budget](https://platform.claude.com/docs/en/managed-agents/budgets#when-a-session-reaches-its-budget). A session at its budget pauses and goes [idle](https://platform.claude.com/docs/en/managed-agents/session-operations#session-statuses) rather than terminating; changing or removing the budget resumes its work automatically. Deployments accept the same budget and apply it to each session they start; see [Budgets on deployments](https://platform.claude.com/docs/en/managed-agents/budgets#budgets-on-deployments).
1214
managed-agents/cloud-sandboxes-reference Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Cloud sandbox reference
33url: https://platform.claude.com/docs/en/managed-agents/cloud-sandboxes-reference
44description: Pre-installed packages, databases, and utilities available in cloud sandboxes.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Cloud sandboxes run as isolated Linux containers on Anthropic-managed infrastructure. They come pre-installed with a comprehensive set of programming languages, databases, and utilities. The agent can use these immediately without any installation steps.
1214
managed-agents/define-outcomes Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Define outcomes
33url: https://platform.claude.com/docs/en/managed-agents/define-outcomes
44description: Tell the agent what 'done' looks like, and let it iterate until it gets there.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113An outcome tells the session what the end result should look like and how to measure its quality. The agent works toward that target, self-evaluating and iterating until the outcome is met.
1214
managed-agents/environments Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Cloud environment setup
33url: https://platform.claude.com/docs/en/managed-agents/environments
44description: Customize cloud sandboxes for your sessions.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Environments define the sandbox configuration where your agent runs. You create an environment once, then reference its ID each time you start a session. Multiple sessions can share the same environment, but each session gets its own isolated sandbox (a fresh Linux container).
1214
managed-agents/events-and-streaming Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Session event stream
33url: https://platform.claude.com/docs/en/managed-agents/events-and-streaming
44description: Send events, stream responses, and interrupt or redirect your session mid-execution.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Communication with Claude Managed Agents is event-based. You send user events to the agent, and receive agent and session events back to track status.
1214
managed-agents/files Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Adding files
33url: https://platform.claude.com/docs/en/managed-agents/files
44description: Upload files and mount them in your sandbox for reading and processing.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113You can provide files to your agent by uploading them through the Files API and mounting them in the session's sandbox.
1214