One read of Claude Developer Platformapi-20261027T185806Z
260 pages moved out of 821 read.
Pages moved
260
significant first
Pages read
821
in this capture
Captured
18:58 UTC
Corpus hash
23cb04cc4921
corpus-hash
What this read moved
226-250 of 260, page 10 of 11This capture is too large to show at once. Changes 226-250 of 260 are below, significant first; the rest are on the following screens.
models/fable-5-1/whats-new-fable-5-1 Changed · +23 / -23 lines
from line 4
44description: Overview of new features, breaking changes, and capability improvements in Claude Fable 5.1 and Claude Mythos 5.1.
55---
66
7Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet, and slide work. For most workloads, start with Claude Opus 5.5 (see [Choosing a model](https://platform.claude.com/docs/en/about-claude/models/choosing-a-model)). Use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still don't meet your requirements. Claude Mythos 5.1 offers the same capabilities only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).
7Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet, and slide work. For most workloads, start with Claude Opus 5.5 (see [Choosing a model](https://platform.claude.com/docs/en/about-claude/models/choosing-a-model)). Use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still don’t meet your requirements. Claude Mythos 5.1 offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).
88
99If you already call Claude Fable 5, four changes are breaking:
1010
1111* [Forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-tool-use-is-not-supported).
12* Only Claude Fable 5.1 and Claude Mythos 5.1 can [read Claude Fable 5.1's thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them).
12* Only Claude Fable 5.1 and Claude Mythos 5.1 can [read Claude Fable 5.1’s thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them).
1313* [Editing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#editing-earlier-turns-invalidates-thinking-blocks).
1414* [Some advisor tool pairings are not supported](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#advisor-tool-pairings).
1515
from line 26
2626| Model | Claude API ID | Description | Availability |
2727| ----------------- | ----------------- | ------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
2828| Claude Fable 5.1 | claude-fable-5-1 | Successor to Claude Fable 5, for long-running agentic coding, knowledge work, and research | All customers, on the Claude API and partner platforms |
29| Claude Mythos 5.1 | claude-mythos-5-1 | Same capabilities as Claude Fable 5.1. Successor to Claude Mythos 5. | Organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842) |
29| Claude Mythos 5.1 | claude-mythos-5-1 | Same capabilities as Claude Fable 5.1. Successor to Claude Mythos 5. | Organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842) |
3030
3131Claude Fable 5.1 and Claude Mythos 5.1 share specs and pricing:
3232
from line 41
4141
4242### Forced tool use is not supported
4343
44Claude Fable 5.1 and Claude Mythos 5.1 don't support forced tool use. `tool_choice` set to `{"type": "any"}` or `{"type": "tool", "name": "..."}` returns a 400 `invalid_request_error`:
44Claude Fable 5.1 and Claude Mythos 5.1 don’t support forced tool use. `tool_choice` set to `{"type": "any"}` or `{"type": "tool", "name": "..."}` returns a 400 `invalid_request_error`:
4545
4646```text wrap
4747tool_choice: type "tool" and "any" are not supported for this model.
from line 49
4949
5050`tool_choice: {"type": "auto"}` (the default) and `{"type": "none"}` are unchanged. The same validation applies to the [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) endpoint.
5151
52Thinking is always on for these models, and a forced tool call would skip it. The model would write its working-out into the tool arguments instead, which lowers argument quality. For schema-valid JSON, keep `tool_choice: {"type": "auto"}` and set `strict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs). To make the model call a tool rather than reply in text, state in the prompt when the tool applies (for example, "Use the `get_weather` tool to answer"). Claude Fable 5.1 follows explicit tool instructions reliably.
52Thinking is always on for these models, and a forced tool call would skip it. The model would write its working-out into the tool arguments instead, which lowers argument quality. For schema-valid JSON, keep `tool_choice: {"type": "auto"}` and set `strict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs). To make the model call a tool rather than reply in text, state in the prompt when the tool applies (for example, “Use the `get_weather` tool to answer”). Claude Fable 5.1 follows explicit tool instructions reliably.
5353
5454### Only Claude Fable 5.1 and Claude Mythos 5.1 read Claude Fable 5.1 thinking blocks
5555
56Every thinking block records which model produced it. Claude Fable 5.1 reads earlier models' thinking blocks, but only Claude Fable 5.1 and Claude Mythos 5.1 read Claude Fable 5.1's. A conversation that moves onto Claude Fable 5.1 (from Claude Opus 5, Claude Fable 5, or any earlier Claude model) keeps its reasoning. A conversation that moves from Claude Fable 5.1 to any other model loses it for the turns that run there.
56Every thinking block records which model produced it. Claude Fable 5.1 reads earlier models’ thinking blocks, but only Claude Fable 5.1 and Claude Mythos 5.1 read Claude Fable 5.1’s. A conversation that moves onto Claude Fable 5.1 (from Claude Opus 5, Claude Fable 5, or any earlier Claude model) keeps its reasoning. A conversation that moves from Claude Fable 5.1 to any other model loses it for the turns that run there.
5757
58When a request carries a block the target model can't read (a router or fallback that switches models mid-conversation, for example), the API drops the block before the model receives it. Dropped blocks don't count toward `input_tokens` and aren't billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. Without it, the drop is silent. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
58When a request carries a block the target model can’t read (a router or fallback that switches models mid-conversation, for example), the API drops the block before the model receives it. Dropped blocks don’t count toward `input_tokens` and aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. Without it, the drop is silent. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
5959
6060### Editing earlier turns invalidates thinking blocks
6161
62Modifying anything before a Claude Fable 5.1 thinking block (the `system` prompt, the `tools`, or an earlier message) results in an error on the next request, or in the block being dropped if you opt into that. Claude Mythos 5.1 doesn't run this check. Claude Code, claude.ai, [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), and the [Claude Agent SDK](https://code.claude.com/docs/en/agent-sdk/overview) keep that prefix intact for you. If your code builds the `messages` array itself, check it before you migrate: [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) walks through the check and each fix. The check is enforced for new accounts created on or after August 31, 2026. For accounts created earlier, the API records the mismatch but acts on it only when the request sets `thinking.block_binding.prefix_mismatch_behavior`.
62Modifying anything before a Claude Fable 5.1 thinking block (the `system` prompt, the `tools`, or an earlier message) results in an error on the next request, or in the block being dropped if you opt into that. Claude Mythos 5.1 doesn’t run this check. Claude Code, claude.ai, [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), and the [Claude Agent SDK](https://code.claude.com/docs/en/agent-sdk/overview) keep that prefix intact for you. If your code builds the `messages` array itself, check it before you migrate: [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) walks through the check and each fix. The check is enforced for new accounts created on or after August 31, 2026. For accounts created earlier, the API records the mismatch but acts on it only when the request sets `thinking.block_binding.prefix_mismatch_behavior`.
6363
6464These patterns invalidate every later thinking block:
6565
from line 72
7272
7373Where the check is enforced, a request that replays an invalidated block is rejected with a 400 whose message says `The block is bound to a different conversation`. To drop the block and continue instead, send the `thinking-binding-controls-2026-08-01` beta header with `thinking.block_binding.prefix_mismatch_behavior: "drop_block"`. The drop is reported in `input_transformations` with `reason: "prefix_binding_mismatch"`.
7474
75To keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) (a [turn-scoped system message](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta) if it should apply to one turn only) and change tools with [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) rather than editing `system` or `tools`. Trim context with server-side [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) or [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction), which don't count as edits. These patterns also keep the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) warm. To find out whether your integration edits history, run a session with `prefix_mismatch_behavior: "drop_block"` and log `input_transformations`: the migration guide has the three-step [history-editing check](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-preserved-thinking). See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) for the full rules.
75To keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) (a [turn-scoped system message](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta) if it should apply to one turn only) and change tools with [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) rather than editing `system` or `tools`. Trim context with server-side [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) or [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction), which don’t count as edits. These patterns also keep the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) warm. To find out whether your integration edits history, run a session with `prefix_mismatch_behavior: "drop_block"` and log `input_transformations`: the migration guide has the three-step [history-editing check](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-preserved-thinking). See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) for the full rules.
7676
7777### Some advisor tool pairings are not supported
7878
79With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), the advisor must be at least as capable as the executor. Claude Mythos 5, Claude Fable 5, Claude Opus 5.5, and Claude Opus 5 advisors work with a Claude Fable 5 or Claude Mythos 5 executor. With a Claude Fable 5.1 or Claude Mythos 5.1 executor, they return a 400 `invalid_request_error`. See the advisor tool's [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
79With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), the advisor must be at least as capable as the executor. Claude Mythos 5, Claude Fable 5, Claude Opus 5.5, and Claude Opus 5 advisors work with a Claude Fable 5 or Claude Mythos 5 executor. With a Claude Fable 5.1 or Claude Mythos 5.1 executor, they return a 400 `invalid_request_error`. See the advisor tool’s [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
8080
8181## New features
8282
from line 354
354354
355355### Turn-scoped system messages (beta)
356356
357A [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) can be scoped to one turn. Set `clear_at: "next_user_message"` on a `role: "system"` message and its text carries system-prompt authority for the current turn, then stops rendering once a later `user` message exists. The message stays in `messages` and you keep sending it back verbatim, so nothing earlier in the conversation changes. The [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) keeps matching, later [thinking blocks stay valid](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation), and a cleared message costs no input tokens. Use it for per-turn reminders in a tool loop ("check your inbox before running more code," "the user can't see that tool output") instead of injecting text into the history and deleting it on the next request. Turn-scoped system messages are in beta: include the `mid-conversation-system-clear-at-2026-08-21` beta header. See [how turn-scoped system messages work](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) in Mid-conversation system messages and tool changes.
357A [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) can be scoped to one turn. Set `clear_at: "next_user_message"` on a `role: "system"` message and its text carries system-prompt authority for the current turn, then stops rendering once a later `user` message exists. The message stays in `messages` and you keep sending it back verbatim, so nothing earlier in the conversation changes. The [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) keeps matching, later [thinking blocks stay valid](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation), and a cleared message costs no input tokens. Use it for per-turn reminders in a tool loop (“check your inbox before running more code,” “the user can’t see that tool output”) instead of injecting text into the history and deleting it on the next request. Turn-scoped system messages are in beta: include the `mid-conversation-system-clear-at-2026-08-21` beta header. See [how turn-scoped system messages work](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) in Mid-conversation system messages and tool changes.
358358
359359```json
360360{
from line 366
366366
367367### Progress updates between tool calls (beta)
368368
369Like Claude Fable 5, Claude Fable 5.1 writes short progress updates between tool calls on what it found and what it will do next, though fewer of them (see [Changed from Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#changed-from-claude-fable-5)). Each update arrives as its own `thinking` block immediately before the tool call. Under the default `thinking.display` of `"omitted"` those blocks come back empty, like reasoning, so a long agentic turn can look silent to your users. What's new is the `display: "updates"` option: set it with the `thinking-display-updates-2026-08-18` beta header to receive the progress updates as text while reasoning stays hidden. Any `thinking` block with non-empty text is then a status line you can show the user. `"summarized"` returns them too, mixed with summarized reasoning. See [Progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates).
369Like Claude Fable 5, Claude Fable 5.1 writes short progress updates between tool calls on what it found and what it will do next, though fewer of them (see [Changed from Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#changed-from-claude-fable-5)). Each update arrives as its own `thinking` block immediately before the tool call. Under the default `thinking.display` of `"omitted"` those blocks come back empty, like reasoning, so a long agentic turn can look silent to your users. What’s new is the `display: "updates"` option: set it with the `thinking-display-updates-2026-08-18` beta header to receive the progress updates as text while reasoning stays hidden. Any `thinking` block with non-empty text is then a status line you can show the user. `"summarized"` returns them too, mixed with summarized reasoning. See [Progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates).
370370
371371### Content provenance
372372
373Text generated by Claude Fable 5.1 and Claude Mythos 5.1 carries Anthropic's statistical text watermark on every platform where the model is available. Supported image, video, and audio files Claude produces (through the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool), for example) carry signed [C2PA](https://c2pa.org/) Content Credentials when you retrieve them through the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) on the Claude API.
373Text generated by Claude Fable 5.1 and Claude Mythos 5.1 carries Anthropic’s statistical text watermark on every platform where the model is available. Supported image, video, and audio files Claude produces (through the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool), for example) carry signed [C2PA](https://c2pa.org/) Content Credentials when you retrieve them through the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) on the Claude API.
374374
375The watermark doesn't change the meaning, quality, or readability of the output. It adds no tokens or hidden characters, carries no information about you or your organization, and needs no changes to your requests or responses. For background, see [How Claude marks AI-generated content](https://support.claude.com/en/articles/16266773-how-claude-marks-ai-generated-content) and [How Claude's text watermark works](https://www.anthropic.com/news/claude-text-watermark).
375The watermark doesn’t change the meaning, quality, or readability of the output. It adds no tokens or hidden characters, carries no information about you or your organization, and needs no changes to your requests or responses. For background, see [How Claude marks AI-generated content](https://support.claude.com/en/articles/16266773-how-claude-marks-ai-generated-content) and [How Claude’s text watermark works](https://www.anthropic.com/news/claude-text-watermark).
376376
377377## Behavior differences
378378
from line 380
380380
381381Claude Fable 5.1 differs from Claude Fable 5 in several ways that show up without any code change. Each has a prompting fix in [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1):
382382
383* **Parallel tool calling is more variable.** Claude Fable 5.1 might issue one tool call in each turn where Claude Fable 5 batched several. This shows up in long agent loops where the next independent reads are only implied: custom coding agents, bash-and-editor harnesses, computer use. The extra turns cost tokens, round trips, and wall-clock time but don't reduce answer quality. Requests naming several things to fetch still run in parallel. Add the one-line batching instruction from [Batch independent tool calls in agent loops](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#batch-independent-tool-calls-in-agent-loops).
383* **Parallel tool calling is more variable.** Claude Fable 5.1 might issue one tool call in each turn where Claude Fable 5 batched several. This shows up in long agent loops where the next independent reads are only implied: custom coding agents, bash-and-editor harnesses, computer use. The extra turns cost tokens, round trips, and wall-clock time but don’t reduce answer quality. Requests naming several things to fetch still run in parallel. Add the one-line batching instruction from [Batch independent tool calls in agent loops](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#batch-independent-tool-calls-in-agent-loops).
384384* **Fewer progress updates during long tool runs.** The model writes less user-facing text between tool calls, especially at higher effort. Set `thinking.display` to `"updates"` (beta) to receive the [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) it does write, and remove any prompt line that tells it to hold findings for the final response. If your UI depends on narration, ask explicitly for an opening line, periodic updates, and a closing recap. See [Ask for user-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#ask-for-user-facing-progress-updates).
385385* **Answers from memory more often at `low` effort.** At the lowest effort level the model calls a search or retrieval tool less often. Raise effort for turns that need fresh information, including [mid-conversation](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#change-effort-mid-conversation-beta), or add the verification nudge from [Search triggering at low effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#search-triggering-at-low-effort).
386* **Denser prose in places.** In some cases its prose is denser than Claude Fable 5's, with longer sentences and fewer paragraph breaks. See [Writing density](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#writing-density).
386* **Denser prose in places.** In some cases its prose is denser than Claude Fable 5’s, with longer sentences and fewer paragraph breaks. See [Writing density](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#writing-density).
387387* **Less formatting in chat.** The model uses bold, headers, and lists less than earlier Claude models, so anti-formatting rules written for those models can suppress structure the content needs. See [Formatting in chat](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#formatting-in-chat).
388388* **Unmarked quotations in summaries.** When summarizing documents, the model is more likely to reproduce passages of the source without marking them as quotations. See [Quoting retrieved sources](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#quoting-retrieved-sources).
389389* **Whole-file rewrites for small changes.** When editing text files, the model is more likely to rewrite the entire file than make a targeted edit. The result is usually the same, but the rewrite costs more output tokens and time. See [Prefer targeted edits over whole-file rewrites](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#prefer-targeted-edits-over-whole-file-rewrites).
from line 411
411411* **Long-context work**, reasoning over and connecting details across the full [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows)
412412* **Computer use**, operating a browser and desktop applications more reliably and recovering from failed steps
413413
414Multilingual performance is at the same level as Claude Fable 5's.
414Multilingual performance is at the same level as Claude Fable 5’s.
415415
416416## Refusals, fallback, and billing
417417
from line 419
419419
420420* **Refusals:** a declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area that fired.
421421* **Fallback:** retry a refused request on another model with [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback), or your own retry. `fallbacks: "default"` (beta) retries a declined request on the model Anthropic recommends for that category. The permitted fallback targets for Claude Fable 5.1 are Claude Opus 4.8 and Claude Opus 5.
422* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale ([How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed)). Before September 24, 2026, these refusals weren't billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching models.
422* **Billing:** a refusal that arrives before any output is billed when it’s in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic’s safeguards at scale ([How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed)). Before September 24, 2026, these refusals weren’t billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching models.
423423
424424## Pricing
425425
from line 442
442442* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `claude-fable-5-1`, and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), as `claude-fable-5-1`
443443* **Microsoft Foundry:** [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), on Anthropic infrastructure
444444
445Claude Mythos 5.1 is available only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). To request access, apply to the program that covers your use case, or contact your Anthropic, AWS, or Google Cloud account team.
445Claude Mythos 5.1 is available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). To request access, apply to the program that covers your use case, or contact your Anthropic, AWS, or Google Cloud account team.
446446
447Claude Fable 5.1 and Claude Mythos 5.1 carry 30-day data retention and aren't available under zero data retention unless expressly authorized by Anthropic. Both are [Covered Models](https://support.claude.com/en/articles/15425695), like Claude Fable 5 and Claude Mythos 5. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
447Claude Fable 5.1 and Claude Mythos 5.1 carry 30-day data retention and aren’t available under zero data retention unless expressly authorized by Anthropic. Both are [Covered Models](https://support.claude.com/en/articles/15425695), like Claude Fable 5 and Claude Mythos 5. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
448448
449449## Migrate from Claude Fable 5
450450
models/haiku-5-5/migration-guide Changed · +10 / -10 lines
from line 65
6565* `usage` fields and [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) results are higher for the same text.
6666* A given number of tokens holds less text.
6767* A `max_tokens` limit tuned for Claude Haiku 4.5 might cut off equivalent output.
68* Cost estimates made from Claude Haiku 4.5's token counts need recomputing with Claude Haiku 5.5's counts and [prices](https://platform.claude.com/docs/en/about-claude/pricing), including its higher prices for long prompts. See [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing).
68* Cost estimates made from Claude Haiku 4.5’s token counts need recomputing with Claude Haiku 5.5’s counts and [prices](https://platform.claude.com/docs/en/about-claude/pricing), including its higher prices for long prompts. See [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing).
6969
7070Large images can also cost more tokens. Claude Haiku 5.5 uses the high-resolution image tier, which downscales images above 2,576 pixels on the long edge or 4,784 visual tokens. Claude Haiku 4.5 and earlier Haiku models use the standard tier, which downscales images above 1,568 pixels on the long edge or 1,568 visual tokens. An image of 2,000 by 1,500 pixels costs about 2.5 times as many visual tokens on Claude Haiku 5.5 as on Claude Haiku 4.5. See [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size).
7171
from line 98
9898}
9999```
100100
101Adaptive thinking is on by default, so a response can start with one or more `thinking` blocks even when the request doesn't set `thinking`. Leave `thinking` unset or set it to `{"type": "adaptive"}`, and use [effort](https://platform.claude.com/docs/en/build-with-claude/effort) as the control: where Claude Haiku 4.5 ran without thinking, or with a small budget to save tokens, choose a lower effort level. At a lower level the model thinks less, and it can skip thinking entirely on simpler requests. For prompting guidance, see [Use effort to control thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#use-effort-to-control-thinking). Select content blocks by their `type` field rather than by position, and pass `thinking` blocks back unmodified with tool results.
101Adaptive thinking is on by default, so a response can start with one or more `thinking` blocks even when the request doesn’t set `thinking`. Leave `thinking` unset or set it to `{"type": "adaptive"}`, and use [effort](https://platform.claude.com/docs/en/build-with-claude/effort) as the control: where Claude Haiku 4.5 ran without thinking, or with a small budget to save tokens, choose a lower effort level. At a lower level the model thinks less, and it can skip thinking entirely on simpler requests. For prompting guidance, see [Use effort to control thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#use-effort-to-control-thinking). Select content blocks by their `type` field rather than by position, and pass `thinking` blocks back unmodified with tool results.
102102
103103Thinking tokens count toward `max_tokens`, so a request with a small `max_tokens` can stop with `stop_reason: "max_tokens"` after a `thinking` block and before any text. If you set a small `max_tokens` for Claude Haiku 4.5, raise it to leave room for thinking, or choose a lower [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level.
104104
105Thinking blocks from earlier assistant turns stay in context and count as input tokens, where Claude Haiku 4.5 keeps only the latest turn's. Multi-turn conversations therefore carry more input tokens than the tokenizer change alone explains. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). See [Thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).
105Thinking blocks from earlier assistant turns stay in context and count as input tokens, where Claude Haiku 4.5 keeps only the latest turn’s. Multi-turn conversations therefore carry more input tokens than the tokenizer change alone explains. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). See [Thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).
106106
107107By default, Claude Haiku 5.5 returns each `thinking` block with an empty `thinking` field and only a `signature`, where Claude Haiku 4.5 returns summarized thinking. To receive summarized thinking, set `thinking: {"type": "adaptive", "display": "summarized"}`.
108108
109109Claude Haiku 5.5 accepts a forced `tool_choice` (`any` or a named tool), but the response starts with the tool call and has no `thinking` block. To let the model think before it calls a tool, use `tool_choice: {"type": "auto"}` and say in the prompt when to use the tool.
110110
111Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, so a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn't read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5's blocks. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
111Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, so a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn’t read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5’s blocks. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
112112
113113## Remove sampling parameters
114114
115On Claude Haiku 5.5, omit `temperature`, `top_p`, and `top_k` and use prompting to guide the model's behavior instead.
115On Claude Haiku 5.5, omit `temperature`, `top_p`, and `top_k` and use prompting to guide the model’s behavior instead.
116116
117117## Replace assistant prefill
118118
from line 120
120120
121121* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification.
122122* **Preambles:** ask in the system prompt for a direct answer.
123* **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."
123* **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.”
124124* **Context reminders:** put them in the user turn.
125125
126126## Move computer use to the toolset
127127
128Claude Haiku 4.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_20250124` tool, with the `computer-use-2025-01-24` beta header. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 supports computer use only through the `computer_toolset_20260801` toolset, and a request that declares `computer_20250124` returns a 400 error. On Amazon Bedrock, Claude Haiku 5.5 doesn't accept `computer_20250124` either; use the `computer_20251124` tool version with the `computer-use-2025-11-24` beta header.
128Claude Haiku 4.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_20250124` tool, with the `computer-use-2025-01-24` beta header. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 supports computer use only through the `computer_toolset_20260801` toolset, and a request that declares `computer_20250124` returns a 400 error. On Amazon Bedrock, Claude Haiku 5.5 doesn’t accept `computer_20250124` either; use the `computer_20251124` tool version with the `computer-use-2025-11-24` beta header.
129129
130To move an integration to the toolset, drop the `computer-use-2025-01-24` beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then make the other request and agent-loop changes in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): dispatch on each member `tool_use` block's `name` and `toolset_name` rather than on `input.action`, handle every such block in a turn, and echo `toolset_name` on results. Zoom is on by default in the toolset; if your environment doesn't implement it, add `"configs": {"zoom": {"enabled": false}}`. If you send the `fine-grained-tool-streaming-2025-05-14` beta header, remove it. Alongside a toolset entry, it returns a 400 error. For other platforms, see the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section.
130To move an integration to the toolset, drop the `computer-use-2025-01-24` beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then make the other request and agent-loop changes in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): dispatch on each member `tool_use` block’s `name` and `toolset_name` rather than on `input.action`, handle every such block in a turn, and echo `toolset_name` on results. Zoom is on by default in the toolset; if your environment doesn’t implement it, add `"configs": {"zoom": {"enabled": false}}`. If you send the `fine-grained-tool-streaming-2025-05-14` beta header, remove it. Alongside a toolset entry, it returns a 400 error. For other platforms, see the computer use tool’s [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section.
131131
132On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. Claude Haiku 4.5 doesn't support it.
132On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. Claude Haiku 4.5 doesn’t support it.
133133
134134## Replay thinking blocks through the account that produced them
135135
from line 137
137137
138138## Keep earlier turns unchanged
139139
140A Claude Haiku 5.5 thinking block stays valid only while everything sent before it is unchanged: a request that sends a thinking block back after a change to `system`, `tools`, or earlier `messages` returns a 400 error. Claude Haiku 4.5 doesn't run this check. Keep conversations append-only. On accounts created before August 31, 2026, 00:00 UTC, the error comes only on requests that set `thinking.block_binding.prefix_mismatch_behavior`. For the changes that trigger the error and what to do instead, see [Who needs to change anything](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#who-is-affected).
140A Claude Haiku 5.5 thinking block stays valid only while everything sent before it is unchanged: a request that sends a thinking block back after a change to `system`, `tools`, or earlier `messages` returns a 400 error. Claude Haiku 4.5 doesn’t run this check. Keep conversations append-only. On accounts created before August 31, 2026, 00:00 UTC, the error comes only on requests that set `thinking.block_binding.prefix_mismatch_behavior`. For the changes that trigger the error and what to do instead, see [Who needs to change anything](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#who-is-affected).
141141
142142## Migrating to Claude Haiku 5.5 from Claude Haiku 3.5 and earlier Haiku models
143143
models/haiku-5-5/whats-new-haiku-5-5 Changed · +5 / -5 lines
from line 17
1717| [Adaptive thinking and effort](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#adaptive-thinking-and-effort) | New | Optional: set `effort` to trade response quality against speed and cost. |
1818| [Larger context window and output](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#larger-context-window-and-output) | New | None. Existing `max_tokens` values stay valid, but thinking tokens count toward them. Long prompts are billed at higher prices; see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing). |
1919| [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | New | None. Available on the Claude API and Claude Models on Google Cloud (Google managed). |
20| [Safety classifiers can decline a request](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn't available. |
20| [Safety classifiers can decline a request](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn’t available. |
2121| [Manual extended thinking returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Breaking | Replace `budget_tokens` with adaptive thinking. |
2222| [Sampling parameters can return an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters) | Breaking | Omit `temperature`, `top_p`, and `top_k`. |
2323| [Assistant message prefill returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill) | Breaking | End `messages` with a user turn. |
from line 29
2929| [Replaying thinking blocks across accounts](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#replaying-thinking-blocks-across-accounts) | Changed | If you replay stored conversations through a different account, replay each through the account that produced it. |
3030| [Earlier thinking blocks stay in context](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#earlier-thinking-blocks-stay-in-context) | Changed | Expect more input tokens in multi-turn conversations. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). |
3131| [Shorter prompts can be cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations) | Changed | None. The minimum cacheable prompt length is 512 tokens, down from 4,096 on Claude Haiku 4.5, so a prompt in between that sets `cache_control` is cached on Claude Haiku 5.5. |
32| [Context awareness tags aren't injected](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness) | Changed | To give the model an explicit budget for an agentic loop, use [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta). |
32| [Context awareness tags aren’t injected](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness) | Changed | To give the model an explicit budget for an agentic loop, use [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta). |
3333
3434## New capabilities
3535
from line 45
4545
4646### Responses can start with thinking blocks
4747
48Adaptive thinking is on by default, so a response can start with one or more `thinking` blocks even when the request doesn't mention thinking. Code that reads the first content block as the answer needs to select blocks by their `type` field. See [Configure thinking](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) in the migration guide.
48Adaptive thinking is on by default, so a response can start with one or more `thinking` blocks even when the request doesn’t mention thinking. Code that reads the first content block as the answer needs to select blocks by their `type` field. See [Configure thinking](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) in the migration guide.
4949
5050### Earlier thinking blocks stay in context
5151
52Claude Haiku 5.5 keeps thinking blocks from all earlier assistant turns in context, and they count as input tokens. Claude Haiku 4.5 kept only the latest turn's blocks. Multi-turn conversations therefore carry more input tokens than the tokenizer change alone explains. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). See [Thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).
52Claude Haiku 5.5 keeps thinking blocks from all earlier assistant turns in context, and they count as input tokens. Claude Haiku 4.5 kept only the latest turn’s blocks. Multi-turn conversations therefore carry more input tokens than the tokenizer change alone explains. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). See [Thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).
5353
5454### Same text counts as more tokens
5555
56Claude Haiku 5.5 uses the same newer tokenizer as Claude 4.7 and later models. As with all models that use this tokenizer, the same input text produces approximately 30 percent more tokens on Claude Haiku 5.5 than on Claude Haiku 4.5. The exact increase depends on the content. The shape of requests and responses doesn't depend on the tokenizer, but anything you measure or budget in tokens changes. See [Recount tokens](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#recount-tokens) in the migration guide.
56Claude Haiku 5.5 uses the same newer tokenizer as Claude 4.7 and later models. As with all models that use this tokenizer, the same input text produces approximately 30 percent more tokens on Claude Haiku 5.5 than on Claude Haiku 4.5. The exact increase depends on the content. The shape of requests and responses doesn’t depend on the tokenizer, but anything you measure or budget in tokens changes. See [Recount tokens](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#recount-tokens) in the migration guide.
5757
5858### Replaying thinking blocks across accounts
5959
models/opus-5-5/migration-guide Changed · +28 / -28 lines
#### Thinking can’t be disabled #### Thinking can't be disabled
from line 16
1616
1717This page lists the code changes for moving to Claude Opus 5.5 from [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-47), [Claude Opus 4.6 and earlier Opus models](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-46), or [Claude Sonnet 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-sonnet-5). Every reader needs [What every request to Claude Opus 5.5 must satisfy](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#request-requirements) and [Handle thinking in every response](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-in-every-response). Then go to the section for your current model: its first sentence names the other sections that apply to you. The [migration checklist](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migration-checklist) lists every change by starting model.
1818
19Claude Opus 5.5 costs less than Claude Opus 5 ($4 / $20 USD per million input / output tokens, compared with $5 / $25 USD; see [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing)). For feature support, see [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#feature-support). For behavioral differences and model-specific prompting patterns, see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5).
19Claude Opus 5.5 costs less than Claude Opus 5 ($4 / $20 USD per million input / output tokens, compared with $5 / $25 USD; see [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing)). For feature support, see [What’s new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#feature-support). For behavioral differences and model-specific prompting patterns, see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5).
2020
2121## What every request to Claude Opus 5.5 must satisfy
2222
2323Whichever model you are coming from, a request to `claude-opus-5-5` must meet the following. Where an item says a setting is rejected, the API returns a 400 error.
2424
25* **Model ID:** Use `claude-opus-5-5`, a fixed model ID with no date suffix. On Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Google managed), and Microsoft Foundry, use that platform's model ID; see [Availability](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#availability).
25* **Model ID:** Use `claude-opus-5-5`, a fixed model ID with no date suffix. On Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Google managed), and Microsoft Foundry, use that platform’s model ID; see [Availability](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#availability).
2626* **Thinking:** Send no `thinking` field, or send `thinking: {"type": "adaptive"}`, which is equivalent: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is always on. `thinking: {"type": "disabled"}` and manual thinking budgets (`thinking: {"type": "enabled", "budget_tokens": N}`) are rejected. See the [before and after for thinking](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-cant-be-disabled).
2727* **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).
2828* **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).
29* **Sampling parameters:** Omit `temperature`, `top_p`, and `top_k`. Use prompting to guide the model's behavior.
30* **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.
29* **Sampling parameters:** Omit `temperature`, `top_p`, and `top_k`. Use prompting to guide the model’s behavior.
30* **Prefill:** Don’t end `messages` with a prefilled assistant turn: it is rejected. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) or system prompt instructions instead.
3131* **Computer use:** On the Claude API and Claude Models on Google Cloud (Google managed), 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).
3232* **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.
3333
from line 277
277277
278278* Update the model ID to `claude-opus-5-5`.
279279* Remove `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}`; choose an effort level instead.
280* Set `effort` explicitly: the default is `medium`, where Claude Opus 5's is `high`.
280* Set `effort` explicitly: the default is `medium`, where Claude Opus 5’s is `high`.
281281* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
282* If you use computer use on the Claude API or Claude Models on Google Cloud (Google managed), 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.
283* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5's thinking blocks (Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them). Claude Opus 5.5 itself reads thinking from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models.
282* If you use computer use on the Claude API or Claude Models on Google Cloud (Google managed), 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.
283* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5’s thinking blocks (Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them). Claude Opus 5.5 itself reads thinking from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models.
284284* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.
285285* If your interface renders text between tool calls, set `display: "updates"` (beta) or `"summarized"` and render the non-empty `thinking` blocks.
286286* If your code edits earlier turns, the `system` prompt, or `tools` mid-conversation, follow [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
from line 290
290290
291291### Claude Opus 4.8 or earlier
292292
293* Review workloads that ran without a `thinking` field: on Claude Opus 5.5 they run with thinking, and thinking can't be disabled. Revisit `max_tokens`, which remains a hard limit on total output (thinking plus response text), and lower `effort` where you want less thinking. Thinking tokens are billed as output tokens, so these workloads can produce more output tokens per request.
293* Review workloads that ran without a `thinking` field: on Claude Opus 5.5 they run with thinking, and thinking can’t be disabled. Revisit `max_tokens`, which remains a hard limit on total output (thinking plus response text), and lower `effort` where you want less thinking. Thinking tokens are billed as output tokens, so these workloads can produce more output tokens per request.
294294* Verify any code that parses the `thinking` field treats it as display text only. Set `display: "summarized"` to receive readable summaries.
295295* Review prompts near the caching minimum: prompts of 512 tokens or more can create cache entries.
296296* If your organization has a [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) commitment, plan capacity separately: Priority Tier is not supported on Claude Opus 5.5.
from line 303
303303* Remove any context-window beta header.
304304* If you rebuild conversation history to update instructions, consider switching to a mid-conversation system message to preserve prompt cache hits.
305305* Verify your stop-reason handling reads `stop_details` on refusals.
306* If you want fast mode, which Claude Opus 4.7 rejects, set `speed: "fast"` on your Claude API requests. Claude Opus 5.5 doesn't need a beta header.
306* If you want fast mode, which Claude Opus 4.7 rejects, set `speed: "fast"` on your Claude API requests. Claude Opus 5.5 doesn’t need a beta header.
307307
308308### Claude Opus 4.6 or earlier
309309
from line 353
353353model = "claude-opus-5-5" # After
354354```
355355
356`claude-opus-5-5` is a fixed model ID with no date suffix, the same scheme as `claude-opus-5`. On Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Google managed), and Microsoft Foundry, use that platform's model ID; see [Availability](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#availability).
356`claude-opus-5-5` is a fixed model ID with no date suffix, the same scheme as `claude-opus-5`. On Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Google managed), and Microsoft Foundry, use that platform’s model ID; see [Availability](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#availability).
357357
358358### Breaking changes
359359
360Each change is explained under [Breaking changes](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#breaking-changes) in What's new in Claude Opus 5.5; this section gives the code change for each.
360Each change is explained under [Breaking changes](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#breaking-changes) in What’s new in Claude Opus 5.5; this section gives the code change for each.
361361
362#### Thinking can't be disabled
362#### Thinking can’t be disabled
363363
364`thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", "budget_tokens": N}` both return a 400 error (`"thinking.type.disabled" is not supported for this model.` or `"thinking.type.enabled" is not supported for this model.`). Remove the `thinking` field and pick an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level; where you disabled thinking to save tokens, use a lower one. Responses then start with `thinking` blocks, so select content blocks by `type` and pass `thinking` blocks back unmodified with tool results. See [Thinking can't be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled).
364`thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", "budget_tokens": N}` both return a 400 error (`"thinking.type.disabled" is not supported for this model.` or `"thinking.type.enabled" is not supported for this model.`). Remove the `thinking` field and pick an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level; where you disabled thinking to save tokens, use a lower one. Responses then start with `thinking` blocks, so select content blocks by `type` and pass `thinking` blocks back unmodified with tool results. See [Thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled).
365365
366366Before. Claude Opus 5 accepts this request, and Claude Opus 5.5 rejects it with a 400 error:
367367
from line 562
562562
563563#### Forced tool use is not supported
564564
565`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).
565`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).
566566
567567Before. Claude Opus 5 accepts this request, and Claude Opus 5.5 rejects it with a 400 error:
568568
from line 880
880880
881881#### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
882882
883On the Claude API and Claude Models on Google Cloud (Google managed), a `tools` entry of type `computer_20251124` returns a 400 error (`'claude-opus-5-5' does not support tool types: computer_20251124.`, followed by the tool types the model accepts). Declare the `computer_toolset_20260801` toolset instead: drop the beta header and send the entry with no `name` or display dimensions. In your agent loop, handle member `tool_use` blocks (the action is the block's `name`, not `input.action`), several of them per turn, and echo `toolset_name` on every result. The request change is shown below; the agent-loop changes are listed in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, the earlier `computer_20251124` tool continues to work on Claude Opus 5.5 as it does on Claude Opus 5, so no change is needed there; for other platforms, see the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section. See [The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported).
883On the Claude API and Claude Models on Google Cloud (Google managed), a `tools` entry of type `computer_20251124` returns a 400 error (`'claude-opus-5-5' does not support tool types: computer_20251124.`, followed by the tool types the model accepts). Declare the `computer_toolset_20260801` toolset instead: drop the beta header and send the entry with no `name` or display dimensions. In your agent loop, handle member `tool_use` blocks (the action is the block’s `name`, not `input.action`), several of them per turn, and echo `toolset_name` on every result. The request change is shown below; the agent-loop changes are listed in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, the earlier `computer_20251124` tool continues to work on Claude Opus 5.5 as it does on Claude Opus 5, so no change is needed there; for other platforms, see the computer use tool’s [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section. See [The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported).
884884
885885Before. Claude Opus 5 accepts this request, and on the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 rejects it with a 400 error:
886886
from line 1144
11441144
11451145### Safety classifiers and fallback
11461146
1147Claude Opus 5.5 can return `stop_reason: "refusal"` with a `stop_details` category. Its classifiers cover a broader set of categories than Claude Opus 5's, so expect `stop_details.category` values such as `"bio"` in addition to `"cyber"` and `"reasoning_extraction"`; see the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). Handle refusals and configure [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) or your own retry (server-side fallback doesn't retry requests declined with `"reasoning_extraction"`; that refusal is returned to you); see [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).
1147Claude Opus 5.5 can return `stop_reason: "refusal"` with a `stop_details` category. Its classifiers cover a broader set of categories than Claude Opus 5’s, so expect `stop_details.category` values such as `"bio"` in addition to `"cyber"` and `"reasoning_extraction"`; see the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). Handle refusals and configure [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) or your own retry (server-side fallback doesn’t retry requests declined with `"reasoning_extraction"`; that refusal is returned to you); see [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).
11481148
11491149### Recommended changes
11501150
11511. **Re-run your effort sweep.** Effort is the only thinking control on Claude Opus 5.5, and its default is `medium` where Claude Opus 5's is `high`, so a request that omits `effort` now runs at `medium`. Step down where quality holds, and step up for the most demanding work. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).
11522. **Re-evaluate model-specific prompt instructions.** Instructions tuned for Claude Opus 5's behavior might no longer be needed; see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5). If you ran with thinking disabled, also see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled).
11511. **Re-run your effort sweep.** Effort is the only thinking control on Claude Opus 5.5, and its default is `medium` where Claude Opus 5’s is `high`, so a request that omits `effort` now runs at `medium`. Step down where quality holds, and step up for the most demanding work. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).
11522. **Re-evaluate model-specific prompt instructions.** Instructions tuned for Claude Opus 5’s behavior might no longer be needed; see [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5). If you ran with thinking disabled, also see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled).
115311533. **Test in a development environment** before switching production traffic.
11541154
11551155## Migrating to Claude Opus 5.5 from Claude Opus 4.8
from line 1188
11881188
11891189None of these items adds a breaking change to those in the earlier sections; they are worth checking after you swap the model ID.
11901190
11911. **Effort levels recalibrated:** The token allocation behind each effort level changes on Claude Opus 5.5 compared to Claude Opus 4.7. The default is `medium`, where Claude Opus 4.7's is `high`. Run a fresh effort sweep on your own evals rather than carrying over a setting tuned for Claude Opus 4.7. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).
11911. **Effort levels recalibrated:** The token allocation behind each effort level changes on Claude Opus 5.5 compared to Claude Opus 4.7. The default is `medium`, where Claude Opus 4.7’s is `high`. Run a fresh effort sweep on your own evals rather than carrying over a setting tuned for Claude Opus 4.7. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort).
11921192
119311932. **1M context window is the default:** Claude Opus 5.5 serves the full 1M token [context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default with no beta header. If your client passes a context-window beta header for compatibility with older models, remove it.
11941194
119511953. **Mid-conversation system messages:** On the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 accepts `role: "system"` messages immediately after a user turn in the `messages` array (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)). Use the top-level `system` field for instructions that apply from the start. Claude Opus 4.7 rejects `role: "system"` in `messages` with a 400 error. If you maintain code paths that rebuild the full message history to update instructions, you can simplify them and preserve [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) hits on earlier turns.
11961196
11974. **Refusal stop details:** When the model declines a request, Claude Opus 5.5 returns a `stop_details` object that names the category of refusal, alongside the `refusal` stop reason. Claude Opus 4.7 returns the same object, so this matters only if your stop-reason handling does not read it yet. No beta header is required, and there is no opt-out. If your stop-reason handling doesn't read it yet, see [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons). Claude Opus 5.5 declines in more categories; see [Safety classifiers and fallback](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#safety-classifiers-and-fallback).
11974. **Refusal stop details:** When the model declines a request, Claude Opus 5.5 returns a `stop_details` object that names the category of refusal, alongside the `refusal` stop reason. Claude Opus 4.7 returns the same object, so this matters only if your stop-reason handling does not read it yet. No beta header is required, and there is no opt-out. If your stop-reason handling doesn’t read it yet, see [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons). Claude Opus 5.5 declines in more categories; see [Safety classifiers and fallback](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#safety-classifiers-and-fallback).
11981198
11995. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on the Claude API. Fast mode is not available on Claude Opus 4.7, where requests with `speed: "fast"` return an error. Set `speed: "fast"` on your requests. Claude Opus 5.5 doesn't need a beta header.
11995. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on the Claude API. Fast mode is not available on Claude Opus 4.7, where requests with `speed: "fast"` return an error. Set `speed: "fast"` on your requests. Claude Opus 5.5 doesn’t need a beta header.
12001200
12016. **Computer use toolset and browser use tool:** On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages. Claude Opus 4.7 supports neither. On those platforms Claude Opus 5.5 doesn't accept the earlier `computer_20251124` tool; see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
12016. **Computer use toolset and browser use tool:** On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages. Claude Opus 4.7 supports neither. On those platforms Claude Opus 5.5 doesn’t accept the earlier `computer_20251124` tool; see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
12021202
12031203## Migrating to Claude Opus 5.5 from Claude Opus 4.6 and earlier Opus models
12041204
from line 1509
15091509
15101510Claude Opus 4.7 introduced behavioral differences from Claude Opus 4.6 that are not API breaking changes. These three affect code or scaffolding:
15111511
15121. **Built-in progress updates in agentic traces:** Claude Opus 4.7 provides more regular, higher-quality updates to the user throughout long agentic traces. If you've added scaffolding to force interim status messages ("After every 3 tool calls, summarize progress"), try removing it. On Claude Opus 5.5 these updates arrive in `thinking` blocks, which are empty at the default `thinking.display`. To receive them, see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls). To shape their length and contents, see [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates).
15121. **Built-in progress updates in agentic traces:** Claude Opus 4.7 provides more regular, higher-quality updates to the user throughout long agentic traces. If you’ve added scaffolding to force interim status messages (“After every 3 tool calls, summarize progress”), try removing it. On Claude Opus 5.5 these updates arrive in `thinking` blocks, which are empty at the default `thinking.display`. To receive them, see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls). To shape their length and contents, see [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates).
15131513
151415142. **Real-time cybersecurity safeguards:** These safeguards are new in Claude Opus 4.7: requests that involve prohibited or high-risk topics might lead to refusals. For legitimate security work such as penetration testing, vulnerability research, or red-teaming, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet) to request reduced restrictions. The application route depends on how you access Claude.
15151515
from line 1550
15501550
15511551### Migrating from Claude 4.1 or earlier
15521552
1553If you're migrating from Claude Opus 4.1 or earlier models directly to Claude Opus 5.5, first apply everything in [Migrating from Claude Opus 4.5 or earlier](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-45). That subsection starts with every earlier section, so in effect you read this page from the top. Then apply the additional changes in this subsection.
1553If you’re migrating from Claude Opus 4.1 or earlier models directly to Claude Opus 5.5, first apply everything in [Migrating from Claude Opus 4.5 or earlier](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-45). That subsection starts with every earlier section, so in effect you read this page from the top. Then apply the additional changes in this subsection.
15541554
15551555#### Additional breaking changes
15561556
models/opus-5-5/overview Changed · +3 / -3 lines
from line 16
1616
1717## Overview
1818
19Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: [thinking can't be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled), [forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported), [thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them), and, on the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported). The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
19Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: [thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled), [forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported), [thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them), and, on the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported). The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
2020
21[What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5)
21[What’s new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5)
2222
2323## How it compares
2424
from line 88
8888
8989## Good to know
9090
91* Adaptive thinking is always on and can't be turned off. Control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort).
91* Adaptive thinking is always on and can’t be turned off. Control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort).
9292* On the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta), Claude Opus 5.5 supports up to 300k output tokens with the `output-300k-2026-03-24` beta header.
9393* The minimum cacheable prompt length is 512 tokens. See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations).
9494* Query limits and capabilities programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list).
models/opus-5-5/whats-new-opus-5-5 Changed · +11 / -11 lines
### Thinking can’t be disabled ### Thinking can't be disabled
from line 4
44description: Overview of breaking changes, feature support, and behavior differences in Claude Opus 5.5.
55---
66
7Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: [thinking can't be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled), [forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported), [thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them), and, on the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported). The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
7Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: [thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled), [forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported), [thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them), and, on the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported). The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
88
99## New model
1010
from line 16
1616
1717## Breaking changes
1818
19### Thinking can't be disabled
19### Thinking can’t be disabled
2020
2121On Claude Opus 5, thinking is on by default and `thinking: {"type": "disabled"}` is accepted at effort `high` or below. On Claude Opus 5.5, thinking is always on: a request that sets `thinking: {"type": "disabled"}`, or a manual budget with `thinking: {"type": "enabled", "budget_tokens": N}`, returns a 400 `invalid_request_error`. Omit the `thinking` field, or send `thinking: {"type": "adaptive"}`, which is equivalent. No beta header is involved.
2222
from line 30
3030"thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.
3131```
3232
33The [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) is the control for thinking depth, latency, and cost: lower it where you previously disabled thinking; [Optimizing for cost and intelligence](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#tune-effort) has measured results for choosing a level. Because every response can start with one or more `thinking` blocks (returned with an empty `thinking` field at the default `display: "omitted"`), select content blocks by their `type` field rather than by position, and pass `thinking` blocks back unmodified in tool-use loops. Code that already runs on Claude Opus 5 with thinking on needs no change. See [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) and the migration guide's [before and after for thinking](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-cant-be-disabled).
33The [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) is the control for thinking depth, latency, and cost: lower it where you previously disabled thinking; [Optimizing for cost and intelligence](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#tune-effort) has measured results for choosing a level. Because every response can start with one or more `thinking` blocks (returned with an empty `thinking` field at the default `display: "omitted"`), select content blocks by their `type` field rather than by position, and pass `thinking` blocks back unmodified in tool-use loops. Code that already runs on Claude Opus 5 with thinking on needs no change. See [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) and the migration guide’s [before and after for thinking](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-cant-be-disabled).
3434
3535### Forced tool use is not supported
3636
37Claude Opus 5.5 doesn't support forced tool use. `tool_choice` set to `{"type": "any"}` or `{"type": "tool", "name": "..."}` returns a 400 `invalid_request_error`:
37Claude Opus 5.5 doesn’t support forced tool use. `tool_choice` set to `{"type": "any"}` or `{"type": "tool", "name": "..."}` returns a 400 `invalid_request_error`:
3838
3939```text wrap
4040tool_choice: type "tool" and "any" are not supported for this model.
from line 44
4444
4545### Thinking blocks are tied to the model and the conversation
4646
47Every thinking block records which model produced it, and each model reads its own blocks and only some other models'. Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two, or onto it from a Claude Fable or Claude Mythos model, runs the turns after the switch without the previous model's reasoning. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
47Every thinking block records which model produced it, and each model reads its own blocks and only some other models’. Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two, or onto it from a Claude Fable or Claude Mythos model, runs the turns after the switch without the previous model’s reasoning. When a request carries a block the target model can’t read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
4848
49The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. As on Claude Fable 5.1, it enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms. On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. Keep the conversation append-only so the question never arises: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide's [note on thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).
49The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. As on Claude Fable 5.1, it enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms. On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. Keep the conversation append-only so the question never arises: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).
5050
5151### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
5252
from line 56
5656'claude-opus-5-5' does not support tool types: computer_20251124.
5757```
5858
59To move an existing integration on the Claude API or Claude Models on Google Cloud (Google managed), follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): drop the beta header, replace the `tools` entry with `{"type": "computer_toolset_20260801"}`, and update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. On Amazon Bedrock, the earlier `computer_20251124` tool continues to work on Claude Opus 5.5 as it does on Claude Opus 5, so no change is needed there. For other platforms, see the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section. Integrations that already use the toolset, and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), need no change. The migration guide shows the request [before and after](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
59To move an existing integration on the Claude API or Claude Models on Google Cloud (Google managed), follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): drop the beta header, replace the `tools` entry with `{"type": "computer_toolset_20260801"}`, and update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. On Amazon Bedrock, the earlier `computer_20251124` tool continues to work on Claude Opus 5.5 as it does on Claude Opus 5, so no change is needed there. For other platforms, see the computer use tool’s [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section. Integrations that already use the toolset, and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), need no change. The migration guide shows the request [before and after](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
6060
6161## Feature support
6262
63Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). On the Claude API and Claude Models on Google Cloud (Google managed), computer use requires the `computer_toolset_20260801` toolset (see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported)). See each feature's page for model availability.
63Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). On the Claude API and Claude Models on Google Cloud (Google managed), computer use requires the `computer_toolset_20260801` toolset (see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported)). See each feature’s page for model availability.
6464
6565### Fast mode
6666
67[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Opus 5.5 on the Claude API, on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure. On the Claude API and on Claude Models on Google Cloud (Anthropic managed), set `speed: "fast"` on your request. Claude Opus 5.5 doesn't need a beta header. See [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for supported models, rate limits, and pricing.
67[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Opus 5.5 on the Claude API, on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure. On the Claude API and on Claude Models on Google Cloud (Anthropic managed), set `speed: "fast"` on your request. Claude Opus 5.5 doesn’t need a beta header. See [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for supported models, rate limits, and pricing.
6868
6969### Define tools in a message (beta)
7070
from line 84
8484* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one. As on Claude Opus 5, requests that push it to reproduce its internal reasoning in the response text might be declined with the `reasoning_extraction` category. See [Refusals and fallback in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).
8585* **Sharper reading of charts, diagrams, and screenshots.** The model reads values off dense charts and layout-dependent visuals much more precisely without tools, so prompt-side vision workarounds built for earlier models might no longer be needed; image tools still add accuracy on the densest inputs. See [Tools for complex visual inputs](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#tools-for-complex-visual-inputs).
8686
87If your Claude Opus 5 integration ran with thinking disabled, see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled) alongside the breaking change [Thinking can't be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled). For the capability gains in agentic coding and code review, knowledge work, communication, visual inputs, and computer use, see [Capabilities relevant to prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#capability-improvements).
87If your Claude Opus 5 integration ran with thinking disabled, see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled) alongside the breaking change [Thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled). For the capability gains in agentic coding and code review, knowledge work, communication, visual inputs, and computer use, see [Capabilities relevant to prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#capability-improvements).
8888
8989## Refusals and fallback
9090
from line 92
9292
9393## Pricing
9494
95Claude Opus 5.5 costs $4 USD per million input tokens and $20 USD per million output tokens, below Claude Opus 5's $5 and $25 USD, with 5-minute cache writes at $5 USD, 1-hour cache writes at $8 USD, and cache reads at $0.20 USD per million tokens (0.05x the base input price). [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) is half price: $2 and $10 USD. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for data residency and tool pricing.
95Claude Opus 5.5 costs $4 USD per million input tokens and $20 USD per million output tokens, below Claude Opus 5’s $5 and $25 USD, with 5-minute cache writes at $5 USD, 1-hour cache writes at $8 USD, and cache reads at $0.20 USD per million tokens (0.05x the base input price). [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) is half price: $2 and $10 USD. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for data residency and tool pricing.
9696
9797## Availability
9898
models/overview Changed · +15 / -11 lines
from line 22
2222
2323## Compare models
2424
25If you're unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still fall short. All current models support text and image input, text output, multilingual capabilities, vision, and tool use. Each model's page lists the platforms it's available on.
25If you’re unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still fall short. All current models support text and image input, text output, multilingual capabilities, vision, and tool use. Each model’s page lists the platforms it’s available on.
2626
2727| Feature | Claude Fable 5.1 | Claude Opus 5.5 | Claude Sonnet 5.5 | Claude Haiku 5.5 |
2828| :------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------- |
from line 64
6464
6565Legacy models (still available): [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview).
6666
67Once you've picked a model, [learn how to make your first API call](https://platform.claude.com/docs/en/get-started). To understand how model IDs, aliases, and snapshots work, see [Model IDs and versioning](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions); for the reliable-knowledge and training-data cutoffs behind each model, see Anthropic's [Transparency Hub](https://www.anthropic.com/transparency).
67Once you’ve picked a model, [learn how to make your first API call](https://platform.claude.com/docs/en/get-started). To understand how model IDs, aliases, and snapshots work, see [Model IDs and versioning](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions); for the reliable-knowledge and training-data cutoffs behind each model, see Anthropic’s [Transparency Hub](https://www.anthropic.com/transparency).
6868
6969## Using the Models API
7070
71You can query model capabilities and token limits programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list). The response includes `max_input_tokens`, `max_tokens`, and a `capabilities` object for every available model.
71You can query model capabilities and token limits programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list). The response includes [`max_input_tokens`](https://platform.claude.com/docs/en/api/models#model_info.max_input_tokens), [`max_tokens`](https://platform.claude.com/docs/en/api/models#model_info.max_tokens), and a [`capabilities`](https://platform.claude.com/docs/en/api/models#model_info.capabilities) object for every available model.
7272
73Each model in the response also has a `line` field, which names the model line it belongs to. Claude Opus 4.5 and Claude Opus 4.6 both report `opus`. Use `line` to group models, for example, in a model picker. `line` is `null` when a model belongs to no line. Read `line` instead of inferring it from the model's `id`. Anthropic might add more lines, so don't treat the set of values as fixed.
73Each model in the response also has a [`line`](https://platform.claude.com/docs/en/api/models#model_info.line) field, which names the model line it belongs to. Claude Opus 4.5 and Claude Opus 4.6 both report `opus`. Use `line` to group models, for example, in a model picker. `line` is `null` when a model belongs to no line. Read `line` instead of inferring it from the model’s `id`. Anthropic might add more lines, so don’t treat the set of values as fixed.
7474
75Each model's `capabilities` object includes `thinking.types.disabled`, which reports whether the model accepts `thinking: {type: "disabled"}`, the setting that [turns thinking off](https://platform.claude.com/docs/en/build-with-claude/thinking#turning-thinking-off). `supported` is `false` when the model rejects `"disabled"` with a 400 error, and `true` on a model that doesn't support thinking. Even when `supported` is `true`, the API can still reject a `"disabled"` request for another reason. One such reason is an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level that the model doesn't allow with thinking off.
75Each model’s `capabilities` object includes [`thinking.types.disabled`](https://platform.claude.com/docs/en/api/models#thinking_types.disabled), which reports whether the model accepts `thinking: {type: "disabled"}`, the setting that [turns thinking off](https://platform.claude.com/docs/en/build-with-claude/thinking#turning-thinking-off). `supported` is `false` when the model rejects `"disabled"` with a 400 error, and `true` on a model that doesn’t support thinking. Even when `supported` is `true`, the API can still reject a `"disabled"` request for another reason. One such reason is an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level that the model doesn’t allow with thinking off.
7676
77Each model's `capabilities` object also includes `thinking.types.between_tools`, which reports whether the model accepts `thinking: {type: "between_tools"}`, the setting that [turns off up-front thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#turning-thinking-off). `supported` is `false` when the model rejects `"between_tools"` with a 400 error. Even when `supported` is `true`, the API can still reject a `"between_tools"` request for another reason, such as an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level that the model doesn't allow with `"between_tools"`. For Claude Sonnet 5.5, for example, the Models API reports `thinking.types.between_tools.supported` as `true` and `thinking.types.disabled.supported` as `false`.
77Each model’s `capabilities` object also includes [`thinking.types.between_tools`](https://platform.claude.com/docs/en/api/models#thinking_types.between_tools), which reports whether the model accepts `thinking: {type: "between_tools"}`, the setting that [turns off up-front thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#turning-thinking-off). `supported` is `false` when the model rejects `"between_tools"` with a 400 error. Even when `supported` is `true`, the API can still reject a `"between_tools"` request for another reason, such as an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level that the model doesn’t allow with `"between_tools"`. For Claude Sonnet 5.5, for example, the Models API reports `thinking.types.between_tools.supported` as `true` and `thinking.types.disabled.supported` as `false`.
7878
79Each model's `capabilities` object also includes `server_tools`, which reports whether the model accepts the [web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) and [code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) tools. It doesn't cover other server tools, such as web fetch. `server_tools.web_search.supported` and `server_tools.code_execution.supported` are `true` when the model accepts at least one version of that tool, not necessarily every version. `server_tools.supported` is `true` when the model accepts at least one of the two tools. Even when a tool is supported, your organization's settings can still cause a request that uses it to fail. For example, an administrator can [disable web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool#how-to-use-web-search).
79Each model’s `capabilities` object also includes [`server_tools`](https://platform.claude.com/docs/en/api/models#model_capabilities.server_tools), which reports whether the model accepts the [web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) and [code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) tools. It doesn’t cover other server tools, such as web fetch. `server_tools.web_search.supported` and `server_tools.code_execution.supported` are `true` when the model accepts at least one version of that tool, not necessarily every version. `server_tools.supported` is `true` when the model accepts at least one of the two tools. Even when a tool is supported, your organization’s settings can still cause a request that uses it to fail. For example, an administrator can [disable web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool#how-to-use-web-search).
8080
81The top-level `code_execution` capability is a different check. It reports whether code that Claude runs in the code execution tool can call the request's other tools, as in [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling). For Claude Haiku 4.5, for example, the Models API reports `server_tools.code_execution.supported` as `true` and `code_execution.supported` as `false`.
81The top-level [`code_execution`](https://platform.claude.com/docs/en/api/models#model_capabilities.code_execution) capability is a different check. It reports whether code that Claude runs in the code execution tool can call the request’s other tools, as in [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling). For Claude Haiku 4.5, for example, the Models API reports `server_tools.code_execution.supported` as `true` and `code_execution.supported` as `false`.
8282
83The API reference lists the List Models endpoint’s parameters and full response.
84
85(See the `models/list` method in [the API reference](https://platform.claude.com/docs/en/api/models/list).)
86
8387## Prompt and output performance
8488
8589Current Claude models excel in:
from line 90
8690
8791* **Performance:** Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) for general and model-specific prompting guidance.
8892* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions. If you prefer more concise responses, adjust your prompts to guide the model toward the output length you want. Refer to the [prompt engineering guides](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering) for details.
89* **Output quality:** When migrating from a previous model generation, you might notice larger improvements in overall performance. If you're on Claude Opus 5 or earlier, see the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).
93* **Output quality:** When migrating from a previous model generation, you might notice larger improvements in overall performance. If you’re on Claude Opus 5 or earlier, see the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).
9094
9195## Get started with Claude
9296
93Whether you're a developer looking to integrate Claude into your applications or a user wanting to experience the power of AI firsthand, the following resources can help.
97Whether you’re a developer looking to integrate Claude into your applications or a user wanting to experience the power of AI firsthand, the following resources can help.
9498
9599<CardGroup cols={3}>
96100 <Card title="Intro to Claude" icon="check" href="https://platform.claude.com/docs/en/intro">
97 Explore Claude's capabilities and development flow.
101 Explore Claude’s capabilities and development flow.
98102 </Card>
99103
100104 <Card title="Quickstart" icon="lightning" href="https://platform.claude.com/docs/en/get-started">
models/sonnet-5-5/migration-guide Changed · +18 / -18 lines
from line 16
1616/claude-api migrate this project to claude-sonnet-5-5
1717```
1818
19Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. For features and prompting, see [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
19Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. For features and prompting, see [What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
2020
2121## Send a request to Claude Sonnet 5.5
2222
from line 233
233233
234234### Turn off up-front thinking
235235
236To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}`. It's the lowest thinking setting. Its progress updates between tool calls still come back as `thinking` blocks with their summary text. Without tools, the response contains only text. Claude Sonnet 5 turns thinking off with `thinking: {"type": "disabled"}` instead, and earlier models run without thinking by default. On Claude Sonnet 5.5, `disabled` returns a 400 `invalid_request_error`:
236To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}`. It’s the lowest thinking setting. Its progress updates between tool calls still come back as `thinking` blocks with their summary text. Without tools, the response contains only text. Claude Sonnet 5 turns thinking off with `thinking: {"type": "disabled"}` instead, and earlier models run without thinking by default. On Claude Sonnet 5.5, `disabled` returns a 400 `invalid_request_error`:
237237
238238```text wrap
239239To turn thinking off on this model, send "thinking": {"type": "between_tools"} instead of {"type": "disabled"}. The model does not think before responding. The short updates it writes between tool calls come back as thinking blocks.
240240```
241241
242`between_tools` works on every platform that offers Claude Sonnet 5.5, with no beta header. It's accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max`, it returns a 400 error. To run at those levels, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. With [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), a `between_tools` request that falls back to Claude Sonnet 5 runs there with `thinking: {"type": "disabled"}`.
242`between_tools` works on every platform that offers Claude Sonnet 5.5, with no beta header. It’s accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max`, it returns a 400 error. To run at those levels, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. With [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), a `between_tools` request that falls back to Claude Sonnet 5 runs there with `thinking: {"type": "disabled"}`.
243243
244With `between_tools`, effort can't change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking. For prompting guidance, see [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking).
244With `between_tools`, effort can’t change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking. For prompting guidance, see [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking).
245245
246246Before (Claude Sonnet 5):
247247
from line 461
461461
462462## Migration checklist by starting model
463463
464Work down the groups and stop after the one that names your model. On Claude Haiku 4.5, apply every group except "Claude Sonnet 4 or earlier," ending with "Claude Haiku 4.5 only."
464Work down the groups and stop after the one that names your model. On Claude Haiku 4.5, apply every group except “Claude Sonnet 4 or earlier,” ending with “Claude Haiku 4.5 only.”
465465
466466### Every starting model
467467
from line 835
835835 ```
836836</CodeGroup>
837837
838The example marks every tool in the list strict. A request can have at most 20 strict tools, and the MCP, computer use, and browser use toolset entries don't accept `strict`. In a longer tools list, mark only the tools that need it.
838The example marks every tool in the list strict. A request can have at most 20 strict tools, and the MCP, computer use, and browser use toolset entries don’t accept `strict`. In a longer tools list, mark only the tools that need it.
839839
840840### Thinking blocks are tied to the model and the conversation
841841
842Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5. It doesn't read blocks from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. The API drops blocks the model can't read. The request still returns 200, and dropped blocks aren't billed. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
842Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5. It doesn’t read blocks from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. The API drops blocks the model can’t read. The request still returns 200, and dropped blocks aren’t billed. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
843843
844844Each Claude Sonnet 5.5 thinking block is also signed over the conversation before it. For accounts created on or after August 31, 2026, 00:00 UTC, the API enforces this by default, on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). On those accounts, a request that replays a block after an edit to earlier history returns a 400 error. Keep conversations append-only, and change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
845845
846846### Computer use needs the toolset on the Claude API and Claude Models on Google Cloud (Google managed)
847847
848On the Claude API and Claude Models on Google Cloud (Google managed), Claude Sonnet 5.5 supports computer use only through the `computer_toolset_20260801` toolset. There, `computer_20251124` returns a 400 error. Claude Sonnet 5.5 doesn't accept `computer_20250124` on any platform. Find the version you send today:
848On the Claude API and Claude Models on Google Cloud (Google managed), Claude Sonnet 5.5 supports computer use only through the `computer_toolset_20260801` toolset. There, `computer_20251124` returns a 400 error. Claude Sonnet 5.5 doesn’t accept `computer_20250124` on any platform. Find the version you send today:
849849
850850| Version you send today | Starting models that send it | Send on the Claude API and Claude Models on Google Cloud (Google managed) | Send on Amazon Bedrock |
851851| ---------------------- | ---------------------------------------------------- | ------------------------------------------------------------------------- | ---------------------- |
from line 858
858858
859859### The advisor tool accepts fewer advisors
860860
861With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), a Claude Sonnet 5.5 executor needs one of these advisors: Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5, Claude Fable 5.1, Claude Mythos 5, or Claude Mythos 5.1. Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 5.5 advisors return a 400 error. The advice comes back encrypted as an `advisor_redacted_result` block, so its text isn't readable in the response. See [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
861With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), a Claude Sonnet 5.5 executor needs one of these advisors: Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5, Claude Fable 5.1, Claude Mythos 5, or Claude Mythos 5.1. Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 5.5 advisors return a 400 error. The advice comes back encrypted as an `advisor_redacted_result` block, so its text isn’t readable in the response. See [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
862862
863863### Text between tool calls is returned in thinking blocks
864864
from line 876
876876* **`"reasoning_extraction"`:** The request asks the model to reproduce its internal reasoning in the response text.
877877* **`"general_harms"`:** The request falls under another usage-policy area. Benign work can also trigger this category.
878878
879[Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn't retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) and [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
879[Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn’t retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) and [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
880880
881881Real-time cyber safeguards are new for code from Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5. For legitimate security work, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet).
882882
from line 883
883883### Other changes
884884
885885* **Prompt caching:** The minimum cacheable prompt is 512 tokens, down from 1,024 on Claude Sonnet 5, Claude Sonnet 4.6, and Claude Sonnet 4.5. See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations).
886* **New features:** For mid-conversation system messages, mid-conversation tool changes, and per-message effort, see [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support). With [`between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking), effort can't change mid-conversation.
886* **New features:** For mid-conversation system messages, mid-conversation tool changes, and per-message effort, see [What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support). With [`between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking), effort can’t change mid-conversation.
887887
888888### Recommended changes
889889
890Re-run your effort sweep. Claude Sonnet 5.5 has five effort levels: `low`, `medium`, `high`, `xhigh`, and `max`. The default on the Claude API is `high`. The levels are recalibrated, so a level doesn't produce the same amount of thinking as on Claude Sonnet 5. Start at `high` unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool use, start at `medium` for well-specified tasks and move to `high` for harder or longer ones. For chat and other latency-sensitive work, start at `medium` or `low`. Set the level in `output_config.effort`. See [Recommended effort levels for Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-sonnet-5-5). Then re-evaluate model-specific prompt instructions against [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
890Re-run your effort sweep. Claude Sonnet 5.5 has five effort levels: `low`, `medium`, `high`, `xhigh`, and `max`. The default on the Claude API is `high`. The levels are recalibrated, so a level doesn’t produce the same amount of thinking as on Claude Sonnet 5. Start at `high` unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool use, start at `medium` for well-specified tasks and move to `high` for harder or longer ones. For chat and other latency-sensitive work, start at `medium` or `low`. Set the level in `output_config.effort`. See [Recommended effort levels for Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-sonnet-5-5). Then re-evaluate model-specific prompt instructions against [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
891891
892892## Migrating to Claude Sonnet 5.5 from Claude Sonnet 4.6 and earlier Sonnet models
893893
from line 903
903903"thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.
904904```
905905
906Remove the budget and set an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level. There's no fixed mapping from a budget to an effort level, so run your evaluations at two or three levels.
906Remove the budget and set an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level. There’s no fixed mapping from a budget to an effort level, so run your evaluations at two or three levels.
907907
908908Before (Claude Sonnet 4.6):
909909
from line 1192
11921192
11931193### Other changes
11941194
1195* **About 30 percent more tokens:** Claude Sonnet 5.5 uses Claude Sonnet 5's tokenizer. Against Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5, the same text produces about 30 percent more tokens, depending on the content. Recount with [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting), and revisit `max_tokens` and cost.
1195* **About 30 percent more tokens:** Claude Sonnet 5.5 uses Claude Sonnet 5’s tokenizer. Against Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5, the same text produces about 30 percent more tokens, depending on the content. Recount with [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting), and revisit `max_tokens` and cost.
11961196* **Effort:** `xhigh` is new, and the levels are recalibrated. See [Recommended changes](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#recommended-changes).
11971197* **Images:** Claude Sonnet 5.5 uses the high-resolution image tier, up to 2,576 pixels on the long edge and up to 4,784 visual tokens for an image. Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5 stop at 1,568 pixels and 1,568 tokens. A 2000×1500 image costs about 2.5 times as many tokens on Claude Sonnet 5.5. See [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size).
11981198
from line 1211
12111211* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification.
12121212* **Preambles:** ask in the system prompt for a direct answer.
12131213* **Unwanted refusals:** clear instructions in the user message are usually enough.
1214* **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."
1214* **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.”
12151215* **Context reminders:** put them in the user turn.
12161216
12171217**Tool input escaping.** Escaping in tool call arguments can differ. Parse `input` with a standard JSON parser.
12181218
1219**Computer use.** Claude Sonnet 5.5 doesn't accept `computer_20250124`. See the [computer use table](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset).
1219**Computer use.** Claude Sonnet 5.5 doesn’t accept `computer_20250124`. See the [computer use table](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset).
12201220
12211221**Effort.** Claude Sonnet 4.5 has no effort parameter. Set an effort level explicitly, as [Recommended changes](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#recommended-changes) describes.
12221222
from line 1244
12441244* **Cost:** The price per token is higher, and the same text produces more tokens. Recount tokens and re-baseline cost. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing).
12451245* **Prompt caching:** The minimum cacheable prompt drops from 4,096 tokens to the [Claude Sonnet 5.5 minimum](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#other-changes-from-claude-sonnet-5).
12461246* **Interleaved thinking:** Adaptive thinking runs between tool calls automatically, with no beta header.
1247* **Routing:** Claude Sonnet 5.5 reads Claude Haiku 4.5 thinking blocks. A conversation that moves up keeps its reasoning. One that moves back down to Claude Haiku 4.5 drops Claude Sonnet 5.5's blocks.
1247* **Routing:** Claude Sonnet 5.5 reads Claude Haiku 4.5 thinking blocks. A conversation that moves up keeps its reasoning. One that moves back down to Claude Haiku 4.5 drops Claude Sonnet 5.5’s blocks.
12481248
models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +15 / -15 lines
from line 20
2020| ----------------- | ----------------- | ---------------------------------------------- |
2121| Claude Sonnet 5.5 | claude-sonnet-5-5 | The best combination of speed and intelligence |
2222
23[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is on by default, and the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) controls thinking depth. Its default on the Claude API is `high`. The tokenizer is the same as Claude Sonnet 5's, so the same text produces the same token counts. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).
23[Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is on by default, and the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) controls thinking depth. Its default on the Claude API is `high`. The tokenizer is the same as Claude Sonnet 5’s, so the same text produces the same token counts. For the context window, output limits, knowledge cutoff, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).
2424
2525For all current models, see the [models overview](https://platform.claude.com/docs/en/models/overview).
2626
from line 28
2828
2929### Turn off up-front thinking with `between_tools`
3030
31To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It's the lowest thinking setting on this model. It's available on every platform that offers Claude Sonnet 5.5. It needs no beta header. The short [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) the model writes between tool calls still come back as `thinking` blocks with their summary text. Pass those blocks back unchanged with the rest of the assistant turn. A progress-update block you send back gives the model the full note it wrote, not the summary. If your requests don't use tools, the response contains only text, as with `disabled` on Claude Sonnet 5.
31To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It’s the lowest thinking setting on this model. It’s available on every platform that offers Claude Sonnet 5.5. It needs no beta header. The short [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) the model writes between tool calls still come back as `thinking` blocks with their summary text. Pass those blocks back unchanged with the rest of the assistant turn. A progress-update block you send back gives the model the full note it wrote, not the summary. If your requests don’t use tools, the response contains only text, as with `disabled` on Claude Sonnet 5.
3232
3333On Claude Sonnet 5.5, a request that sends `thinking: {"type": "disabled"}` returns a 400 `invalid_request_error` whose message points to `between_tools`.
3434
35`between_tools` is accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max` effort, a request with `between_tools` returns a 400 error. To run at `xhigh` or `max`, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`, which is equivalent. With `between_tools`, effort can't change mid-conversation: a [per-message](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking.
35`between_tools` is accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max` effort, a request with `between_tools` returns a 400 error. To run at `xhigh` or `max`, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`, which is equivalent. With `between_tools`, effort can’t change mid-conversation: a [per-message](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking.
3636
3737`between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. Manual thinking budgets (`thinking: {"type": "enabled", "budget_tokens": N}`) return a 400 error. See [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) and [Turn off up-front thinking](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking) in the migration guide.
3838
3939### Forced tool use is not supported
4040
41Claude Sonnet 5.5 doesn't support forced tool use. `tool_choice` set to `{"type": "any"}` or `{"type": "tool", "name": "..."}` returns a 400 `invalid_request_error`:
41Claude Sonnet 5.5 doesn’t support forced tool use. `tool_choice` set to `{"type": "any"}` or `{"type": "tool", "name": "..."}` returns a 400 `invalid_request_error`:
4242
4343```text wrap
4444tool_choice: type "tool" and "any" are not supported for this model.
from line 48
4848
4949### Thinking blocks are tied to the model and the conversation
5050
51Every thinking block records which model produced it. Each model reads its own blocks and only some other models' blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 reads Claude Sonnet 5.5 thinking blocks; no other model does.
51Every thinking block records which model produced it. Each model reads its own blocks and only some other models’ blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 reads Claude Sonnet 5.5 thinking blocks; no other model does.
5252
53So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5, or from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API and Claude Models on Google Cloud (Google managed), keeps its reasoning, and any other move away from Claude Sonnet 5.5 runs the turns after the switch without it. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
53So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5, or from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API and Claude Models on Google Cloud (Google managed), keeps its reasoning, and any other move away from Claude Sonnet 5.5 runs the turns after the switch without it. When a request carries a block the target model can’t read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
5454
5555The API also checks whether anything before a Claude Sonnet 5.5 thinking block has changed since the block was produced: the `system` prompt, the `tools`, or an earlier message. It enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, keep the history append-only, or strip the thinking blocks from the edited turn on.
5656
57Keep the conversation append-only so the check never fails: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide's [note on thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).
57Keep the conversation append-only so the check never fails: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).
5858
5959### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
6060
from line 66
6666
6767On Amazon Bedrock, Claude Sonnet 5.5 accepts the earlier `computer_20251124` tool.
6868
69To move an existing integration on the Claude API or Claude Models on Google Cloud (Google managed), follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124), which shows the request before and after. Drop the beta header, replace the `tools` entry with `{"type": "computer_toolset_20260801"}`, and update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. The toolset is available on both the Claude API and Claude Models on Google Cloud (Google managed). For other platforms, see the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section. Integrations that already use the toolset, and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), need no change.
69To move an existing integration on the Claude API or Claude Models on Google Cloud (Google managed), follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124), which shows the request before and after. Drop the beta header, replace the `tools` entry with `{"type": "computer_toolset_20260801"}`, and update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. The toolset is available on both the Claude API and Claude Models on Google Cloud (Google managed). For other platforms, see the computer use tool’s [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section. Integrations that already use the toolset, and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), need no change.
7070
7171### Some advisor tool pairings are not supported
7272
73With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), a Claude Sonnet 5.5 executor needs Claude Mythos 5.1, Claude Fable 5.1, Claude Mythos 5, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5 as its advisor, or Claude Sonnet 5.5 itself. Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 advisors work with a Claude Sonnet 5 executor, but with a Claude Sonnet 5.5 executor they return a 400 `invalid_request_error`. Every advisor that Claude Sonnet 5.5 accepts returns its advice encrypted, as an `advisor_redacted_result` block, so your client can't read the advice text. See the advisor tool's [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) and [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants).
73With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), a Claude Sonnet 5.5 executor needs Claude Mythos 5.1, Claude Fable 5.1, Claude Mythos 5, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5 as its advisor, or Claude Sonnet 5.5 itself. Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 advisors work with a Claude Sonnet 5 executor, but with a Claude Sonnet 5.5 executor they return a 400 `invalid_request_error`. Every advisor that Claude Sonnet 5.5 accepts returns its advice encrypted, as an `advisor_redacted_result` block, so your client can’t read the advice text. See the advisor tool’s [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) and [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants).
7474
7575## Feature support
7676
77Claude Sonnet 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) (beta), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). Per-message effort, mid-conversation system messages, and mid-conversation tool changes aren't available on Claude Sonnet 5, whose minimum cacheable prompt is 1,024 tokens. On the Claude API and Claude Models on Google Cloud (Google managed), computer use requires the `computer_toolset_20260801` toolset (see the [computer use breaking change](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported)). See each feature's page for model availability.
77Claude Sonnet 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) (beta), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). Per-message effort, mid-conversation system messages, and mid-conversation tool changes aren’t available on Claude Sonnet 5, whose minimum cacheable prompt is 1,024 tokens. On the Claude API and Claude Models on Google Cloud (Google managed), computer use requires the `computer_toolset_20260801` toolset (see the [computer use breaking change](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported)). See each feature’s page for model availability.
7878
7979### Compact on demand (beta)
8080
from line 86
8686
8787### Thinking blocks stay with the account that produced them
8888
89Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model receives it, and the request succeeds. On the Claude API and Claude Models on Google Cloud (Google managed), with the `thinking-binding-controls-2026-08-01` beta header, the response lists each dropped block in `input_transformations` with `reason: "organization_binding_mismatch"`. Blocks from earlier models aren't affected. See [thinking blocks from another account](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) in Preserved thinking.
89Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model receives it, and the request succeeds. On the Claude API and Claude Models on Google Cloud (Google managed), with the `thinking-binding-controls-2026-08-01` beta header, the response lists each dropped block in `input_transformations` with `reason: "organization_binding_mismatch"`. Blocks from earlier models aren’t affected. See [thinking blocks from another account](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) in Preserved thinking.
9090
9191## Behavior differences
9292
9393Claude Sonnet 5.5 differs from Claude Sonnet 5 in several ways that show up without any code change. [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5) has guidance for each:
9494
95* **Effort levels are recalibrated.** An [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level doesn't produce the same amount of thinking as it did on Claude Sonnet 5. Re-run your effort sweep rather than carrying a setting over. Start at `high` unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool use, start at `medium` for well-specified tasks and move to `high` for harder or longer ones. For chat and other latency-sensitive work, start at `medium` or `low`.
96* **Text between tool calls comes back in thinking blocks.** Between tool calls, notes longer than a sentence or two come back as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates). Shorter remarks stay `text`. At the default `display: "omitted"`, the progress-update blocks' text is empty, so an application that streams those notes to its users goes quiet between tool calls, with no error. If you [turn off up-front thinking with `between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking), the text comes back. To receive it, see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#text-between-tool-calls) in the migration guide.
97* **Safeguard categories.** The model's safeguards can decline a request in five [`stop_details` categories](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). `"cyber"` means the request could enable cyber harm. `"bio"` means it could enable biological harm. `"frontier_llm"` means it could help with the development of competing AI models. `"reasoning_extraction"` means it asks the model to reproduce its internal reasoning in the response text. `"general_harms"` means it falls under another usage-policy area. See [Refusals, fallback, and billing](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#refusals-fallback-and-billing).
95* **Effort levels are recalibrated.** An [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level doesn’t produce the same amount of thinking as it did on Claude Sonnet 5. Re-run your effort sweep rather than carrying a setting over. Start at `high` unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool use, start at `medium` for well-specified tasks and move to `high` for harder or longer ones. For chat and other latency-sensitive work, start at `medium` or `low`.
96* **Text between tool calls comes back in thinking blocks.** Between tool calls, notes longer than a sentence or two come back as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates). Shorter remarks stay `text`. At the default `display: "omitted"`, the progress-update blocks’ text is empty, so an application that streams those notes to its users goes quiet between tool calls, with no error. If you [turn off up-front thinking with `between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking), the text comes back. To receive it, see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#text-between-tool-calls) in the migration guide.
97* **Safeguard categories.** The model’s safeguards can decline a request in five [`stop_details` categories](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). `"cyber"` means the request could enable cyber harm. `"bio"` means it could enable biological harm. `"frontier_llm"` means it could help with the development of competing AI models. `"reasoning_extraction"` means it asks the model to reproduce its internal reasoning in the response text. `"general_harms"` means it falls under another usage-policy area. See [Refusals, fallback, and billing](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#refusals-fallback-and-billing).
9898
9999## Refusals, fallback, and billing
100100
101Everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies to Claude Sonnet 5.5. A declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area. Handle refusals and configure fallback. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn't retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. You can also use the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) or your own retry. Whether a refusal that arrives before any output is billed depends on its refusal category, and it counts against your rate limits either way. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
101Everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies to Claude Sonnet 5.5. A declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area. Handle refusals and configure fallback. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn’t retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. You can also use the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) or your own retry. Whether a refusal that arrives before any output is billed depends on its refusal category, and it counts against your rate limits either way. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
102102
103103## Pricing
104104
release-notes/overview Changed · +190 / -190 lines
from line 18
1818
1919### October 22, 2026
2020
21* We've launched [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), the Claude API operated by Anthropic and reached through your Google Cloud project. Google Cloud IAM controls access. Google Cloud Marketplace handles billing.
21* We’ve launched [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), the Claude API operated by Anthropic and reached through your Google Cloud project. Google Cloud IAM controls access. Google Cloud Marketplace handles billing.
2222* [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Opus 5.5 on Claude Models on Google Cloud (Anthropic managed).
2323
2424### October 21, 2026
2525
26* We've released API version `2026-10-21`. [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21) shows how to upgrade.
27* We've released new versions of the [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) and the [`ant` CLI](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) that send API version `2026-10-21` by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SDK 3.0.0, PHP SDK 1.0.0, Ruby SDK 2.0.0, and `ant` CLI 2.0.0. See [Switch to 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).
28* The new SDK and CLI versions also have breaking changes that don't depend on the API version, and they are licensed under Apache 2.0 instead of the MIT License. See [SDK and CLI changes](https://platform.claude.com/docs/en/api/migration-2026-10-21#sdk-changes).
29* We've added the `enforcement_status` and `enforcement_actions` fields to [user profiles](https://platform.claude.com/docs/en/manage-claude/user-profiles), so you can see whether Anthropic has restricted or banned one of your end customers. To find the profiles that have an open restriction or ban, [list your profiles](https://platform.claude.com/docs/en/api/user_profiles/list) with the new `enforcement_status[]` filter. See [Check whether Anthropic has restricted or banned a profile](https://platform.claude.com/docs/en/manage-claude/user-profiles#check-whether-anthropic-has-restricted-or-banned-a-profile).
26* We’ve released API version `2026-10-21`. [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21) shows how to upgrade.
27* We’ve released new versions of the [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) and the [`ant` CLI](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) that send API version `2026-10-21` by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SDK 3.0.0, PHP SDK 1.0.0, Ruby SDK 2.0.0, and `ant` CLI 2.0.0. See [Switch to 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).
28* The new SDK and CLI versions also have breaking changes that don’t depend on the API version, and they are licensed under Apache 2.0 instead of the MIT License. See [SDK and CLI changes](https://platform.claude.com/docs/en/api/migration-2026-10-21#sdk-changes).
29* We’ve added the `enforcement_status` and `enforcement_actions` fields to [user profiles](https://platform.claude.com/docs/en/manage-claude/user-profiles), so you can see whether Anthropic has restricted or banned one of your end customers. To find the profiles that have an open restriction or ban, [list your profiles](https://platform.claude.com/docs/en/api/user_profiles/list) with the new `enforcement_status[]` filter. See [Check whether Anthropic has restricted or banned a profile](https://platform.claude.com/docs/en/manage-claude/user-profiles#check-whether-anthropic-has-restricted-or-banned-a-profile).
3030
3131### October 20, 2026
3232
3333* [Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks) are out of beta for Claude Enterprise organizations.
34* We've launched [user profiles](https://platform.claude.com/docs/en/manage-claude/user-profiles), so you can tell Anthropic which of your end customers each API request is for. If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one end customer instead of your whole organization. The SDK and the `ant` CLI support the new [`/v1/user_profiles` endpoints](https://platform.claude.com/docs/en/api/user_profiles).
35* We've added [organization webhooks](https://platform.claude.com/docs/en/manage-claude/organization-webhooks) to the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api), in beta with the `webhooks-2026-10-07` beta header. Its [`/v1/organizations/webhooks` endpoints](https://platform.claude.com/docs/en/api/beta/organization/webhooks) register webhook endpoints for two event types: one for when Anthropic restricts or bans one of your organization's user profiles, and one for when the restriction or ban ends. To request access, contact your Anthropic account team.
34* We’ve launched [user profiles](https://platform.claude.com/docs/en/manage-claude/user-profiles), so you can tell Anthropic which of your end customers each API request is for. If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one end customer instead of your whole organization. The SDK and the `ant` CLI support the new [`/v1/user_profiles` endpoints](https://platform.claude.com/docs/en/api/user_profiles).
35* We’ve added [organization webhooks](https://platform.claude.com/docs/en/manage-claude/organization-webhooks) to the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api), in beta with the `webhooks-2026-10-07` beta header. Its [`/v1/organizations/webhooks` endpoints](https://platform.claude.com/docs/en/api/beta/organization/webhooks) register webhook endpoints for two event types: one for when Anthropic restricts or bans one of your organization’s user profiles, and one for when the restriction or ban ends. To request access, contact your Anthropic account team.
3636* Organization admins can now turn off web fetch for their organization on the [**Capabilities**](https://platform.claude.com/settings/capabilities) page of the Claude Console. With web fetch off, a Messages API request that includes the web fetch tool fails with a 400 error. In a Claude Managed Agents session, `web_fetch` calls return an error result to the agent instead. With web fetch on, admins can also set allowed or blocked domains for web fetch on the same page. See [How to use web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#how-to-use-web-fetch) and [Domain filtering](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools#domain-filtering).
37* In Claude Managed Agents, the [`web_fetch` tool](https://platform.claude.com/docs/en/managed-agents/tools#available-tools) now follows your organization's web fetch domain restrictions set on the [**Capabilities**](https://platform.claude.com/settings/capabilities) page of the Claude Console. A URL, including one reached by a redirect, must pass both the organization's list and the `allowed_domains` or `blocked_domains` list on the agent's `web_fetch` tool. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
38* In Claude Managed Agents, sessions follow your organization's web search settings on the [**Capabilities**](https://platform.claude.com/settings/capabilities) page of the Claude Console: the **Allow web search** setting since October 6, and its web search domain restrictions since October 14. The agent receives only the search results that both the organization's domain restrictions and the `allowed_domains` or `blocked_domains` list on the agent's [`web_search` tool](https://platform.claude.com/docs/en/managed-agents/tools#available-tools) allow. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
37* In Claude Managed Agents, the [`web_fetch` tool](https://platform.claude.com/docs/en/managed-agents/tools#available-tools) now follows your organization’s web fetch domain restrictions set on the [**Capabilities**](https://platform.claude.com/settings/capabilities) page of the Claude Console. A URL, including one reached by a redirect, must pass both the organization’s list and the `allowed_domains` or `blocked_domains` list on the agent’s `web_fetch` tool. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
38* In Claude Managed Agents, sessions follow your organization’s web search settings on the [**Capabilities**](https://platform.claude.com/settings/capabilities) page of the Claude Console: the **Allow web search** setting since October 6, and its web search domain restrictions since October 14. The agent receives only the search results that both the organization’s domain restrictions and the `allowed_domains` or `blocked_domains` list on the agent’s [`web_search` tool](https://platform.claude.com/docs/en/managed-agents/tools#available-tools) allow. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
3939
4040### October 15, 2026
4141
42* 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).
42* 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).
4343* 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).
4444* [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.
4545* [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 46
4646
4747### October 14, 2026
4848
49* We've launched [OpenTelemetry export](https://platform.claude.com/docs/en/manage-claude/opentelemetry) in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability platform. The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby. To get spans from the API, [add an OpenTelemetry destination](https://platform.claude.com/docs/en/manage-claude/opentelemetry/api#add-a-destination) in the Claude Console.
49* We’ve launched [OpenTelemetry export](https://platform.claude.com/docs/en/manage-claude/opentelemetry) in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability platform. The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby. To get spans from the API, [add an OpenTelemetry destination](https://platform.claude.com/docs/en/manage-claude/opentelemetry/api#add-a-destination) in the Claude Console.
5050* Claude Managed Agents [scheduled deployments](https://platform.claude.com/docs/en/managed-agents/scheduled-deployments) are now available on [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#claude-managed-agents).
5151
5252### October 9, 2026
5353
54* You can now let a Claude Managed Agents agent use [dynamic workflows](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#dynamic-workflows), in beta with the `managed-agents-2026-04-01` beta header. For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results. The server runs it in the background as a workflow run. To [turn dynamic workflows on](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#turn-on-dynamic-workflows), set the agent's `multiagent` field to `{"type": "multiagent_20261001", "workflows": {"type": "enabled"}}`. To guide the agent, tell it in its system prompt when to start a run. Follow each run through `workflow_run.*` events on the session's event stream. See [Workflow runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs).
54* You can now let a Claude Managed Agents agent use [dynamic workflows](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#dynamic-workflows), in beta with the `managed-agents-2026-04-01` beta header. For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results. The server runs it in the background as a workflow run. To [turn dynamic workflows on](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#turn-on-dynamic-workflows), set the agent’s `multiagent` field to `{"type": "multiagent_20261001", "workflows": {"type": "enabled"}}`. To guide the agent, tell it in its system prompt when to start a run. Follow each run through `workflow_run.*` events on the session’s event stream. See [Workflow runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs).
5555
5656### October 8, 2026
5757
from line 60
6060
6161### October 7, 2026
6262
63* 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).
64* 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-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5).
63* 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).
64* 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-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5).
6565* 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).
6666* 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).
6767* 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).
6868* 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).
69* With `limited` networking, creating a session fails with a 400 error when an enabled web tool's `allowed_domains` has an entry not within `allowed_hosts`. So does a session update that adds such an entry. An `allowed_hosts` entry matches one exact host unless it starts with `*.`, so `docs.example.com` is not within `["example.com"]`. To fix the error, add the host to `allowed_hosts` or remove the entry from `allowed_domains`. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
70* In Claude Managed Agents, the [`web_fetch` tool](https://platform.claude.com/docs/en/managed-agents/tools#available-tools) now fetches only URLs that have already appeared in the session, for example in the text of a user message, in a `web_search` result, or in a page that `web_fetch` returned earlier. This reduces the risk of data exfiltration. A URL that appears only in Claude's own output, the agent's system prompt, an attached document, or the output of a tool such as `bash`, `read`, or an MCP tool does not count: a `web_fetch` call for it returns a `url_not_in_prior_context` error result to the agent. To let the agent fetch a URL, send it in the text of a `user.message` event.
69* With `limited` networking, creating a session fails with a 400 error when an enabled web tool’s `allowed_domains` has an entry not within `allowed_hosts`. So does a session update that adds such an entry. An `allowed_hosts` entry matches one exact host unless it starts with `*.`, so `docs.example.com` is not within `["example.com"]`. To fix the error, add the host to `allowed_hosts` or remove the entry from `allowed_domains`. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
70* In Claude Managed Agents, the [`web_fetch` tool](https://platform.claude.com/docs/en/managed-agents/tools#available-tools) now fetches only URLs that have already appeared in the session, for example in the text of a user message, in a `web_search` result, or in a page that `web_fetch` returned earlier. This reduces the risk of data exfiltration. A URL that appears only in Claude’s own output, the agent’s system prompt, an attached document, or the output of a tool such as `bash`, `read`, or an MCP tool does not count: a `web_fetch` call for it returns a `url_not_in_prior_context` error result to the agent. To let the agent fetch a URL, send it in the text of a `user.message` event.
7171
7272### October 6, 2026
7373
74* We've added `capabilities.server_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 the web search and code execution tools. To check whether a model accepts the code execution tool, read `capabilities.server_tools.code_execution`. The top-level `capabilities.code_execution` reports whether code can call your request's other tools. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
74* We’ve added `capabilities.server_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 the web search and code execution tools. To check whether a model accepts the code execution tool, read `capabilities.server_tools.code_execution`. The top-level `capabilities.code_execution` reports whether code can call your request’s other tools. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
7575
7676### October 5, 2026
7777
78* We've added `capabilities.thinking.types.disabled` 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: "disabled"}`, which turns thinking off. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
78* We’ve added `capabilities.thinking.types.disabled` 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: "disabled"}`, which turns thinking off. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
7979
8080### October 1, 2026
8181
82* We've added a `line` field to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now return the model line each model belongs to. Claude Opus 4.5 and Claude Opus 4.6 both report `opus`, for example. Use `line` to group models without parsing their IDs. `line` is `null` for a model that belongs to no line. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
82* We’ve added a `line` field to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now return the model line each model belongs to. Claude Opus 4.5 and Claude Opus 4.6 both report `opus`, for example. Use `line` to group models without parsing their IDs. `line` is `null` for a model that belongs to no line. See [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).
8383* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Opus 5.5, Claude Fable 5.1, and Claude Sonnet 5.5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#limits).
8484
8585### September 30, 2026
from line 89
8989
9090### September 28, 2026
9191
92* We've launched **Claude Sonnet 5.5** (`claude-sonnet-5-5`). 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-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). For its context window, output limits, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).
93* Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways. To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`, at `high` effort or below. Forced tool use (`tool_choice` types `any` and `tool`) returns a 400 error. Thinking blocks are tied to the model and the conversation. On the Claude API and Google Cloud, the earlier `computer_20251124` computer use tool isn't accepted. The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors. See [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5) for each change and the [Claude Sonnet 5.5 migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide) for before-and-after requests. For model-specific prompting patterns, see [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
94* Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model sees it, and the request succeeds. Blocks from earlier models aren't affected. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
92* We’ve launched **Claude Sonnet 5.5** (`claude-sonnet-5-5`). 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-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). For its context window, output limits, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).
93* Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways. To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`, at `high` effort or below. Forced tool use (`tool_choice` types `any` and `tool`) returns a 400 error. Thinking blocks are tied to the model and the conversation. On the Claude API and Google Cloud, the earlier `computer_20251124` computer use tool isn’t accepted. The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors. See [What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5) for each change and the [Claude Sonnet 5.5 migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide) for before-and-after requests. For model-specific prompting patterns, see [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
94* Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model sees it, and the request succeeds. Blocks from earlier models aren’t affected. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
9595
9696### September 24, 2026
9797
98* We're resuming billing for refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`, the categories where we measure low volumes of false positives. Mid-stream refusals were already billed. Refusals billed under this change are charged like any other request, at the rates of the model that ran it. Refusals before any output in other categories are still not billed, and fallback credit is unchanged. This change applies on all platforms. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
99* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (`product_surface` values beginning with `office_agents`). See [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
98* We’re resuming billing for refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`, the categories where we measure low volumes of false positives. Mid-stream refusals were already billed. Refusals billed under this change are charged like any other request, at the rates of the model that ran it. Refusals before any output in other categories are still not billed, and fallback credit is unchanged. This change applies on all platforms. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
99* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (`product_surface` values beginning with `office_agents`). See [Sessions on users’ machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
100100* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) no longer returns file names, project document names, or artifact titles. The `filename` and `title` fields on file, project document, and artifact activities are now always empty or omitted, including on activities recorded before this change. To look up a name or title by the ID on the activity, use a Compliance Access Key with the `read:compliance_user_data` scope. See [Understand the Activity object](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed#understand-the-activity-object).
101101
102102### September 23, 2026
from line 105
105105
106106### September 22, 2026
107107
108* We've launched **Claude Opus 5.5** (`claude-opus-5-5`), a model for long-running agentic coding and knowledge work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25 USD). Claude Opus 5.5 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5) for capabilities, API changes, and migration guidance.
109* On Claude Opus 5.5, thinking can't be disabled: `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}` return a 400 error. Omit the `thinking` field and control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). `tool_choice` types `any` and `tool` also return a 400 error, as on Claude Fable 5.1; use `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). On the Claude API and Google Cloud, [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) on this model requires the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool returns a 400 error; on Amazon Bedrock, `computer_20251124` keeps working. See the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5).
108* We’ve launched **Claude Opus 5.5** (`claude-opus-5-5`), a model for long-running agentic coding and knowledge work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25 USD). Claude Opus 5.5 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5) for capabilities, API changes, and migration guidance.
109* On Claude Opus 5.5, thinking can’t be disabled: `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}` return a 400 error. Omit the `thinking` field and control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). `tool_choice` types `any` and `tool` also return a 400 error, as on Claude Fable 5.1; use `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). On the Claude API and Google Cloud, [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) on this model requires the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool returns a 400 error; on Amazon Bedrock, `computer_20251124` keeps working. See the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5).
110110* [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) (research preview) is available for Claude Opus 5.5 on the Claude API.
111* Tools can now be defined inside a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), in beta on the Claude API with the `inline-tools-2026-09-15` beta header. A `tool_addition` block can carry the tool's full definition (`tool: {"type": "tool_definition", "definition": {...}}`), so you can add a tool, change its schema, or move a server tool to a newer version without editing `tools` or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector's `mcp-client-2026-09-15` beta header as well, the definition can be an MCP toolset, and a response records each server's fetched tool list in an `mcp_tool_listing` block, which pins that list when you send it back.
111* Tools can now be defined inside a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), in beta on the Claude API with the `inline-tools-2026-09-15` beta header. A `tool_addition` block can carry the tool’s full definition (`tool: {"type": "tool_definition", "definition": {...}}`), so you can add a tool, change its schema, or move a server tool to a newer version without editing `tools` or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector’s `mcp-client-2026-09-15` beta header as well, the definition can be an MCP toolset, and a response records each server’s fetched tool list in an `mcp_tool_listing` block, which pins that list when you send it back.
112112
113113### September 18, 2026
114114
115115* For [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics), a response to a request that sends the `cache-diagnosis-2026-04-07` beta header now always includes the `diagnostics` field. The field is `null` when the request did not include the `diagnostics` object. Previously the field was omitted in that case.
116* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints now also return transcripts of Claude in Chrome sessions (`product_surface` value `claude_in_chrome`), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
116* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints now also return transcripts of Claude in Chrome sessions (`product_surface` value `claude_in_chrome`), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users’ machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
117117
118118### September 14, 2026
119119
120120* The Messages API can now [compact a conversation on demand](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand) on the Claude API, in beta with the `compact-2026-09-04` beta header. Send the top-level `compaction` parameter, and the API returns a signed `compaction` block that summarizes the messages you sent. On later requests, send that block first, in place of those messages. You choose when to compact, the request can run in the background, and you can keep recent turns word for word after the summary. On models with preserved thinking, the thinking in those kept turns can stay valid.
121* With the `thinking-binding-controls-2026-08-01` beta header, the `input_transformations` response field gains a second entry type, `thinking_mismatch_allowed`. It names a thinking block that failed the prefix check on a request where the API doesn't enforce that check: on Claude Fable 5.1, for example, a request from an account created before August 31, 2026, with `prefix_mismatch_behavior` unset. The block still reaches the model unchanged. Log these entries to find history edits in production traffic before you opt into enforcement. See [Set the mismatch behavior and read `input_transformations`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#preserved-thinking-controls).
121* With the `thinking-binding-controls-2026-08-01` beta header, the `input_transformations` response field gains a second entry type, `thinking_mismatch_allowed`. It names a thinking block that failed the prefix check on a request where the API doesn’t enforce that check: on Claude Fable 5.1, for example, a request from an account created before August 31, 2026, with `prefix_mismatch_behavior` unset. The block still reaches the model unchanged. Log these entries to find history edits in production traffic before you opt into enforcement. See [Set the mismatch behavior and read `input_transformations`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#preserved-thinking-controls).
122122
123123### September 10, 2026
124124
125125* Claude Managed Agents permission policies now include `auto`: the server evaluates each agent or MCP tool call and runs it, denies it, or pauses for your approval. `agent.tool_use` and `agent.mcp_tool_use` events report how each call was evaluated in an `evaluation` field alongside `evaluated_permission`. See [Let the server evaluate each call with `auto`](https://platform.claude.com/docs/en/managed-agents/permission-policies#let-the-server-evaluate-each-call-with-auto).
126* Version 1.32.0 of the `ant` CLI adds `ant beta:sessions connect`, which attaches your terminal to a Claude Managed Agents session. You can follow the session live, send messages, and allow or deny tool calls that are waiting for approval. Pass `--web` to serve the Claude Console's session viewer locally and open the session there instead. See [Connect to a Managed Agents session from your terminal](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/sessions-connect).
126* Version 1.32.0 of the `ant` CLI adds `ant beta:sessions connect`, which attaches your terminal to a Claude Managed Agents session. You can follow the session live, send messages, and allow or deny tool calls that are waiting for approval. Pass `--web` to serve the Claude Console’s session viewer locally and open the session there instead. See [Connect to a Managed Agents session from your terminal](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/sessions-connect).
127127
128128### September 9, 2026
129129
130* For [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics), the API now stores a request's fingerprint only when the request includes the `diagnostics` object. A request that sends only the `cache-diagnosis-2026-04-07` beta header is still accepted, but no fingerprint is stored. A later turn that points `previous_message_id` at it reports `previous_message_not_found`. Include `diagnostics` on every turn, with `"previous_message_id": null` on the first.
130* For [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics), the API now stores a request’s fingerprint only when the request includes the `diagnostics` object. A request that sends only the `cache-diagnosis-2026-04-07` beta header is still accepted, but no fingerprint is stored. A later turn that points `previous_message_id` at it reports `previous_message_not_found`. Include `diagnostics` on every turn, with `"previous_message_id": null` on the first.
131131
132132### September 3, 2026
133133
from line 136
136136
137137### September 1, 2026
138138
139* We've launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside **Claude Mythos 5.1** (`claude-mythos-5-1`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 USD per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) for capabilities, API changes, and migration guidance.
139* We’ve launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside **Claude Mythos 5.1** (`claude-mythos-5-1`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 USD per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) for capabilities, API changes, and migration guidance.
140140* Prompt cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost $0.25 USD per million tokens: 0.025x the base input price, compared with 0.1x on other models. Cache writes are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).
141* On Claude Fable 5.1 and Claude Mythos 5.1, `tool_choice` types `any` and `tool` aren't supported and return a 400 error. `auto` and `none` are unchanged. To guarantee schema-conformant tool inputs, use [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs).
142* Thinking blocks produced by Claude Fable 5.1 and Claude Mythos 5.1 are preserved only for the model that produced them or a newer one: earlier models can't read them, and the API drops one replayed to an earlier model. Claude Fable 5.1 accepts thinking blocks from Claude Opus 5, Claude Fable 5, Claude Mythos 5, and earlier Claude models. On Claude Fable 5.1, the API also [checks that nothing before a block has changed](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): for new accounts created on or after August 31, 2026, replaying one after the `system` prompt, `tools`, or an earlier message changed returns a 400 error. With the `thinking-binding-controls-2026-08-01` beta header, dropped blocks are reported in an `input_transformations` response field, and `thinking.block_binding.prefix_mismatch_behavior` chooses between rejecting and dropping blocks whose history changed. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking).
141* On Claude Fable 5.1 and Claude Mythos 5.1, `tool_choice` types `any` and `tool` aren’t supported and return a 400 error. `auto` and `none` are unchanged. To guarantee schema-conformant tool inputs, use [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs).
142* Thinking blocks produced by Claude Fable 5.1 and Claude Mythos 5.1 are preserved only for the model that produced them or a newer one: earlier models can’t read them, and the API drops one replayed to an earlier model. Claude Fable 5.1 accepts thinking blocks from Claude Opus 5, Claude Fable 5, Claude Mythos 5, and earlier Claude models. On Claude Fable 5.1, the API also [checks that nothing before a block has changed](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): for new accounts created on or after August 31, 2026, replaying one after the `system` prompt, `tools`, or an earlier message changed returns a 400 error. With the `thinking-binding-controls-2026-08-01` beta header, dropped blocks are reported in an `input_transformations` response field, and `thinking.block_binding.prefix_mismatch_behavior` chooses between rejecting and dropping blocks whose history changed. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking).
143143* Per-message effort changes are in beta on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5 on the Claude API. Add a `role: "system"` message with `output_config.effort` inside `messages` to change effort for later turns while preserving the prompt cache. Include the `mid-conversation-output-config-2026-07-01` beta header in your requests. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).
144* [Turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) are in beta (`mid-conversation-system-clear-at-2026-08-21` header). Set `clear_at: "next_user_message"` on a mid-conversation `role: "system"` message and it renders for the current turn only, then stays in the history at no token cost. Per-turn reminders don't accumulate and don't invalidate the prompt cache or later thinking blocks.
144* [Turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) are in beta (`mid-conversation-system-clear-at-2026-08-21` header). Set `clear_at: "next_user_message"` on a mid-conversation `role: "system"` message and it renders for the current turn only, then stays in the history at no token cost. Per-turn reminders don’t accumulate and don’t invalidate the prompt cache or later thinking blocks.
145145* `thinking.display` accepts a third value, `"updates"`, in beta (`thinking-display-updates-2026-08-18` header). Reasoning comes back with an empty `thinking` field, as under `"omitted"`, and the short progress updates that Claude Fable 5.1, Claude Mythos 5.1, and Claude Fable 5 write between tool calls come back as text, at most one `thinking` block before a tool call. See [Progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates).
146* Text generated by Claude Fable 5.1 and Claude Mythos 5.1 carries Anthropic's text watermark, and supported image, video, and audio files that Claude produces through the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) carry C2PA Content Credentials when you retrieve them through the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) on the Claude API. Marking requires no changes to your requests or response handling.
147* Like Claude Fable 5, both models require 30-day data retention and aren't available under zero data retention unless expressly authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
146* Text generated by Claude Fable 5.1 and Claude Mythos 5.1 carries Anthropic’s text watermark, and supported image, video, and audio files that Claude produces through the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) carry C2PA Content Credentials when you retrieve them through the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) on the Claude API. Marking requires no changes to your requests or response handling.
147* Like Claude Fable 5, both models require 30-day data retention and aren’t available under zero data retention unless expressly authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
148148* The guides for the Claude Enterprise endpoints of the [Admin API](https://platform.claude.com/docs/en/api/beta/organization) ([user management](https://platform.claude.com/docs/en/manage-claude/user-management) and [spend limits](https://platform.claude.com/docs/en/manage-claude/spend-limits-api)), the [Claude Enterprise Analytics API](https://platform.claude.com/docs/en/manage-claude/analytics-api), and the [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now show the `anthropic-version` header; send it on every request to these endpoints, as in the rest of the Claude API. See [API versions](https://platform.claude.com/docs/en/api/versioning).
149149
150150### August 27, 2026
from line 156
156156### August 26, 2026
157157
158158* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) session endpoints are out of beta for Cowork and Claude Code sessions. See [Retrieve session transcripts](https://platform.claude.com/docs/en/manage-claude/compliance-sessions).
159* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints now also return transcripts of Claude Science sessions (`product_surface` value `claude_science`) and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (`product_surface` values beginning with `office_agents`), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
159* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints now also return transcripts of Claude Science sessions (`product_surface` value `claude_science`) and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (`product_surface` values beginning with `office_agents`), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users’ machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
160160* The [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api) is now available in the `ant` CLI and the Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs under `client.beta.organization`. They cover organization info, members, invites, workspaces and workspace members, API keys, rate limits, service accounts, workload identity federation issuers and rules, and customer-managed encryption keys. Usage and cost reports and the Claude Enterprise user-management and analytics endpoints remain curl-only. The CLI and SDKs read an Admin API key from `ANTHROPIC_API_KEY` or an `org:admin` OAuth token from `ANTHROPIC_AUTH_TOKEN`.
161161
162162### August 20, 2026
163163
164* We've released **v1.0 of the [Python SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/python)**. The SDK's HTTP layer moves from `httpx` to [httpx2](https://httpx2.pydantic.dev), a maintained, API-compatible fork: build custom `http_client`, `Timeout`, and transport objects from `httpx2` (the `DefaultHttpxClient` helpers are unchanged), and call `httpx2.alias_httpx()` at startup if you rely on tracing or mocking libraries that patch `httpx`. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the `temperature`, `top_p`, and `top_k` parameters on Messages methods, and the tool runner's client-side `compaction_control`. On the async client, `.with_raw_response` results now need `await response.parse()`, and `AnthropicBedrock` now raises an error when no AWS region is configured instead of defaulting to `us-east-1`. See the [v1 migration guide](https://github.com/anthropics/anthropic-sdk-python/blob/main/MIGRATION.md) for every change with before-and-after snippets.
164* We’ve released **v1.0 of the [Python SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/python)**. The SDK’s HTTP layer moves from `httpx` to [httpx2](https://httpx2.pydantic.dev), a maintained, API-compatible fork: build custom `http_client`, `Timeout`, and transport objects from `httpx2` (the `DefaultHttpxClient` helpers are unchanged), and call `httpx2.alias_httpx()` at startup if you rely on tracing or mocking libraries that patch `httpx`. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the `temperature`, `top_p`, and `top_k` parameters on Messages methods, and the tool runner’s client-side `compaction_control`. On the async client, `.with_raw_response` results now need `await response.parse()`, and `AnthropicBedrock` now raises an error when no AWS region is configured instead of defaulting to `us-east-1`. See the [v1 migration guide](https://github.com/anthropics/anthropic-sdk-python/blob/main/MIGRATION.md) for every change with before-and-after snippets.
165165* The [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801`) are now available on [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8. Requests use the same `tools` entries as on the Claude API.
166166
167167### August 19, 2026
168168
169169* The [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) is out of beta on the Claude API as the `computer_toolset_20260801` toolset: no beta header, batch actions (several actions in one turn), `zoom` enabled by default, and per-member configuration through `configs`. Earlier beta versions remain available. Upgrading an existing integration changes the request shape and tool handling; see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).
170* We've launched the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`), a client toolset for driving a browser that your application hosts. It works inside a browser viewport rather than a whole desktop, reading the page itself (its accessibility tree, elements, forms, and tabs) and adding element references, form input, tab management, download reporting, and opt-in file upload on top of screenshot-and-click control.
170* We’ve launched the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`), a client toolset for driving a browser that your application hosts. It works inside a browser viewport rather than a whole desktop, reading the page itself (its accessibility tree, elements, forms, and tabs) and adding element references, form input, tab management, download reporting, and opt-in file upload on top of screenshot-and-click control.
171171* Both toolsets are available for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8 on the Claude API.
172172* The [Files API](https://platform.claude.com/docs/en/build-with-claude/files) is out of beta on the Claude API. Requests to the `/v1/files` endpoints, and Messages API requests that reference an uploaded file, no longer require the `files-api-2025-04-14` beta header. Requests sent without the header use the current response format: [file expiration](https://platform.claude.com/docs/en/build-with-claude/files#file-expiration) (set `expires_in_seconds` when you upload a file; file objects report `expires_at`), and `page` and `next_page` [pagination](https://platform.claude.com/docs/en/api/overview#pagination) plus an `ids[]` filter when you [list files](https://platform.claude.com/docs/en/build-with-claude/files#list-files). `/v1/files` requests that still send the beta header keep working and return the previous response format. To move an existing integration off the header, see [Migrate from `files-api-2025-04-14`](https://platform.claude.com/docs/en/build-with-claude/files#migrate-from-files-api-2025-04-14).
173173* [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) and the Skills API (`/v1/skills`) are out of beta on the Claude API. Requests no longer require the `skills-2025-10-02` beta header, including Messages API requests that load Skills through the `container` parameter. Requests that still send the header continue to work unchanged. See [Using Agent Skills with the API](https://platform.claude.com/docs/en/build-with-claude/skills-guide). To move an existing integration off the header, see [Migrate from `skills-2025-10-02`](https://platform.claude.com/docs/en/build-with-claude/skills-guide#migrate-from-skills-2025-10-02).
174174* The [Admin API](https://platform.claude.com/docs/en/api/beta/organization) user-management endpoints for **Claude Enterprise** (claude.ai) organizations (members, invites, groups, and custom roles) are out of beta. The `anthropic-beta: ce-user-management-2026-07-13` header is no longer required on group and custom-role requests; requests that still send it are accepted unchanged. See [User management](https://platform.claude.com/docs/en/manage-claude/user-management).
175* You can now restrict which sites a Claude Managed Agents agent's `web_search` and `web_fetch` tools can reach. Set `allowed_domains` or `blocked_domains` on the tool's entry in the `agent_toolset_20260401` `configs` array; `web_fetch` also accepts `max_content_tokens` and `web_search` accepts `user_location`. Each `configs` entry is identified by its `name` and typed by an optional `type`, and requests that pass only `name`, `enabled`, and `permission_policy` continue to work; in the typed SDKs, `configs` entries become [per-tool types](https://platform.claude.com/docs/en/managed-agents/tools#config-entry-types-in-the-sdks). See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
176* Claude Managed Agents sessions that run in a [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) can now attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory). The Python, TypeScript, and Go SDK workers download each attached store into the sandbox at its `mount_path` and sync the agent's changes back to the store. See [Memory stores in self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-memory).
175* You can now restrict which sites a Claude Managed Agents agent’s `web_search` and `web_fetch` tools can reach. Set `allowed_domains` or `blocked_domains` on the tool’s entry in the `agent_toolset_20260401` `configs` array; `web_fetch` also accepts `max_content_tokens` and `web_search` accepts `user_location`. Each `configs` entry is identified by its `name` and typed by an optional `type`, and requests that pass only `name`, `enabled`, and `permission_policy` continue to work; in the typed SDKs, `configs` entries become [per-tool types](https://platform.claude.com/docs/en/managed-agents/tools#config-entry-types-in-the-sdks). See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
176* Claude Managed Agents sessions that run in a [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) can now attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory). The Python, TypeScript, and Go SDK workers download each attached store into the sandbox at its `mount_path` and sync the agent’s changes back to the store. See [Memory stores in self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-memory).
177177* The session viewer in the Claude Console has been redesigned with a timeline minimap, a transcript grouped by model request, and an Inspector panel for session details and cost, raw events, per-tool statistics, mounted resources, and per-thread activity. See [Inspect a session in the Console](https://platform.claude.com/docs/en/managed-agents/session-observability#inspect-a-session-in-the-console).
178178
179179### August 18, 2026
from line 182
182182
183183### August 11, 2026
184184
185* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now returns transcripts of Cowork and Claude Code sessions that run on your users' machines, in beta for Claude Enterprise organizations. `GET /v1/compliance/apps/sessions/local` lists sessions across your organization, `GET /v1/compliance/apps/sessions/local/{session_id}` retrieves one session's metadata, and `GET /v1/compliance/apps/sessions/local/{session_id}/messages` returns its transcript, all with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
186* We've added the `anthropic-workspace-id` response header to the Claude API. It carries the `wrkspc_`-prefixed ID of the workspace that the request's API key or access token resolved to, including your organization's Default Workspace. See [Identify the workspace behind an API response](https://platform.claude.com/docs/en/manage-claude/workspaces#identify-the-workspace-behind-an-api-response).
185* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now returns transcripts of Cowork and Claude Code sessions that run on your users’ machines, in beta for Claude Enterprise organizations. `GET /v1/compliance/apps/sessions/local` lists sessions across your organization, `GET /v1/compliance/apps/sessions/local/{session_id}` retrieves one session’s metadata, and `GET /v1/compliance/apps/sessions/local/{session_id}/messages` returns its transcript, all with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users’ machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
186* We’ve added the `anthropic-workspace-id` response header to the Claude API. It carries the `wrkspc_`-prefixed ID of the workspace that the request’s API key or access token resolved to, including your organization’s Default Workspace. See [Identify the workspace behind an API response](https://platform.claude.com/docs/en/manage-claude/workspaces#identify-the-workspace-behind-an-api-response).
187187
188188### August 10, 2026
189189
from line 191
191191
192192### August 7, 2026
193193
194* You can now set a budget on a Claude Managed Agents session: a hard cap on the session's spend, priced at public list rates. A session that reaches its budget pauses with the `budget_reached` stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments accept the same budget and apply it to each session they start. See [Session budgets](https://platform.claude.com/docs/en/managed-agents/budgets).
195* You can now give a Claude Managed Agents session an advisor: a model at least as capable as the agent's own that the session's primary thread can consult mid-turn for strategic guidance. Configure it as a `{"type": "advisor"}` entry in the agent's multiagent roster, naming the `model` to consult. See [Give the session an advisor](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#give-the-session-an-advisor).
194* You can now set a budget on a Claude Managed Agents session: a hard cap on the session’s spend, priced at public list rates. A session that reaches its budget pauses with the `budget_reached` stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments accept the same budget and apply it to each session they start. See [Session budgets](https://platform.claude.com/docs/en/managed-agents/budgets).
195* You can now give a Claude Managed Agents session an advisor: a model at least as capable as the agent’s own that the session’s primary thread can consult mid-turn for strategic guidance. Configure it as a `{"type": "advisor"}` entry in the agent’s multiagent roster, naming the `model` to consult. See [Give the session an advisor](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#give-the-session-an-advisor).
196196* You can now control where model inference runs for a Claude Managed Agents agent. Set `inference_geo` inside the `model` object when you [create the agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#pin-the-inference-geo), or [override it for a single session](https://platform.claude.com/docs/en/managed-agents/sessions#pin-the-inference-geo-for-a-session). See [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency) for the available geos and pricing.
197197* Claude Managed Agents sessions can now [load skills from a GitHub repository](https://platform.claude.com/docs/en/managed-agents/skills#load-skills-from-a-github-repository). When a session [mounts a repository](https://platform.claude.com/docs/en/managed-agents/github), any skills in its root `.claude/skills` directory are discovered automatically at session start and available to the agent for that session.
198198
199199### August 5, 2026
200200
201* **Inference hooks** are now in beta for Claude Enterprise organizations. Point Claude at your organization's AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server's allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed). See [Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks).
202* We've retired the Claude Opus 4.1 model (`claude-opus-4-1-20250805`). All requests to this model on the Claude API will now return an error. We recommend upgrading to [Claude Opus 5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison). Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
201* **Inference hooks** are now in beta for Claude Enterprise organizations. Point Claude at your organization’s AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server’s allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed). See [Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks).
202* We’ve retired the Claude Opus 4.1 model (`claude-opus-4-1-20250805`). All requests to this model on the Claude API will now return an error. We recommend upgrading to [Claude Opus 5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison). Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
203203
204204### August 3, 2026
205205
206* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now returns transcripts of Cowork sessions started on claude.ai web or mobile, in beta for Claude Enterprise organizations. `GET /v1/compliance/apps/sessions/remote` lists sessions and `GET /v1/compliance/apps/sessions/remote/{session_id}/messages` returns one session's transcript, using your existing Compliance Access Key with the `read:compliance_user_data` scope. See [Sessions in the cloud](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions).
206* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now returns transcripts of Cowork sessions started on claude.ai web or mobile, in beta for Claude Enterprise organizations. `GET /v1/compliance/apps/sessions/remote` lists sessions and `GET /v1/compliance/apps/sessions/remote/{session_id}/messages` returns one session’s transcript, using your existing Compliance Access Key with the `read:compliance_user_data` scope. See [Sessions in the cloud](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions).
207207
208208### August 1, 2026
209209
from line 211
211211
212212### July 24, 2026
213213
214* We've launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for new features, behavior changes, and migration guidance, and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.
215* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview).
214* We’ve launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It’s available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for new features, behavior changes, and migration guidance, and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.
215* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What’s new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview).
216216* [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) is the primary control for steering Claude Opus 5: the model supports the full ladder (`low`, `medium`, `high`, `xhigh`, `max`), with `max` for capability-critical work.
217217* Mid-conversation tool changes are now in beta on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5: add or remove tools between turns of a conversation while preserving the prompt cache. Include the `mid-conversation-tool-changes-2026-07-01` beta header in your requests.
218* The `fallbacks` parameter now supports a `"default"` mode, which applies Anthropic's recommended fallback models by refusal category. Server-side fallback is in beta, and the `"default"` mode requires the `server-side-fallback-2026-07-01` beta header. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
219* We've removed [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.7. Requests to `claude-opus-4-7` with `speed: "fast"` now return an error; unlike Claude Opus 4.6, they do not fall back to standard speed. Claude Opus 4.7 itself remains available at standard speed. To continue using fast mode, migrate to [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) or Claude Opus 4.8. Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
218* The `fallbacks` parameter now supports a `"default"` mode, which applies Anthropic’s recommended fallback models by refusal category. Server-side fallback is in beta, and the `"default"` mode requires the `server-side-fallback-2026-07-01` beta header. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
219* We’ve removed [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.7. Requests to `claude-opus-4-7` with `speed: "fast"` now return an error; unlike Claude Opus 4.6, they do not fall back to standard speed. Claude Opus 4.7 itself remains available at standard speed. To continue using fast mode, migrate to [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) or Claude Opus 4.8. Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
220220
221221### July 22, 2026
222222
223* You can now set an `effort` level on a Claude Managed Agents agent's model configuration. Pass `effort` inside the `model` object when you [create the agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#create-an-agent). See [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels) for what each level does.
223* You can now set an `effort` level on a Claude Managed Agents agent’s model configuration. Pass `effort` inside the `model` object when you [create the agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#create-an-agent). See [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels) for what each level does.
224224* Webhooks for Claude Managed Agents now cover the environment and memory store lifecycle: four `environment.*` event types and three `memory_store.*` event types. You can react to environment and memory store lifecycle changes without polling. See the Environment events and Memory store events tabs in [Supported event types](https://platform.claude.com/docs/en/managed-agents/webhooks#supported-event-types).
225* When creating a Claude Managed Agents session, you can now [seed it with initial events](https://platform.claude.com/docs/en/managed-agents/sessions#seed-the-session-with-initial-events). Pass `initial_events` on `POST /v1/sessions` with up to 50 `user.message` and `user.define_outcome` events. A non-empty list starts the agent loop in the same call, so you don't need a separate send-events request to start work.
225* When creating a Claude Managed Agents session, you can now [seed it with initial events](https://platform.claude.com/docs/en/managed-agents/sessions#seed-the-session-with-initial-events). Pass `initial_events` on `POST /v1/sessions` with up to 50 `user.message` and `user.define_outcome` events. A non-empty list starts the agent loop in the same call, so you don’t need a separate send-events request to start work.
226226* The `version` field is now optional when [updating a Claude Managed Agents agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#update-an-agent). Supply it for optimistic concurrency (a mismatch returns a 409 error), or omit it to apply the update unconditionally. See [Update semantics](https://platform.claude.com/docs/en/managed-agents/agent-setup#update-semantics).
227* Claude Managed Agents session thread event streams now support [event deltas](https://platform.claude.com/docs/en/managed-agents/event-deltas). `GET /v1/sessions/{session_id}/threads/{thread_id}/stream` accepts the same `event_deltas[]` query parameter as the session-level stream, so you can preview a subagent's text as the model generates it. A connection previews only the thread it's reading. See [Preview session thread events](https://platform.claude.com/docs/en/managed-agents/event-deltas#preview-session-thread-events).
227* Claude Managed Agents session thread event streams now support [event deltas](https://platform.claude.com/docs/en/managed-agents/event-deltas). `GET /v1/sessions/{session_id}/threads/{thread_id}/stream` accepts the same `event_deltas[]` query parameter as the session-level stream, so you can preview a subagent’s text as the model generates it. A connection previews only the thread it’s reading. See [Preview session thread events](https://platform.claude.com/docs/en/managed-agents/event-deltas#preview-session-thread-events).
228228
229229### July 17, 2026
230230
from line 237
237237
238238### July 14, 2026
239239
240* You can now manage the people in your **Claude Enterprise** (claude.ai) organization with the [Admin API](https://platform.claude.com/docs/en/api/beta/organization), in beta for all Claude Enterprise organizations: list members and look them up by email address, change a member's role, remove members, send and withdraw invites, manage groups and their membership, and read custom roles. Group and custom-role requests require the `anthropic-beta: ce-user-management-2026-07-13` beta header; member and invite requests take no beta header. An Admin API key with the `read:org_audit` scope can also call every user-management `GET` endpoint. See [User management](https://platform.claude.com/docs/en/manage-claude/user-management).
240* You can now manage the people in your **Claude Enterprise** (claude.ai) organization with the [Admin API](https://platform.claude.com/docs/en/api/beta/organization), in beta for all Claude Enterprise organizations: list members and look them up by email address, change a member’s role, remove members, send and withdraw invites, manage groups and their membership, and read custom roles. Group and custom-role requests require the `anthropic-beta: ce-user-management-2026-07-13` beta header; member and invite requests take no beta header. An Admin API key with the `read:org_audit` scope can also call every user-management `GET` endpoint. See [User management](https://platform.claude.com/docs/en/manage-claude/user-management).
241241
242242### July 10, 2026
243243
244244* [Dreams](https://platform.claude.com/docs/en/managed-agents/dreams) (research preview) now supports Claude Fable 5 and Claude Sonnet 5. See [Supported models](https://platform.claude.com/docs/en/managed-agents/dreams#limits).
245* We've expanded the [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency) documentation of `cmek_preserve` events with a filter example, an example event payload, and two preservation reason codes (`policy_violation_investigation`, `csae_report`). The documentation now also clarifies that a preservation event is written whether the preservation was initiated by a human reviewer or an automated safety pipeline. See [CMEK content preservation](https://platform.claude.com/docs/en/manage-claude/access-transparency#cmek-content-preservation).
245* We’ve expanded the [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency) documentation of `cmek_preserve` events with a filter example, an example event payload, and two preservation reason codes (`policy_violation_investigation`, `csae_report`). The documentation now also clarifies that a preservation event is written whether the preservation was initiated by a human reviewer or an automated safety pipeline. See [CMEK content preservation](https://platform.claude.com/docs/en/manage-claude/access-transparency#cmek-content-preservation).
246246
247247### July 8, 2026
248248
249* You can now set an expiration when you create an API key or an Admin API key in the [Claude Console](https://platform.claude.com/settings/keys). Choose a preset, a custom duration, or **Never**. For keys with a lifetime of at least 7 days, Anthropic emails the creator before expiration. Existing keys are unaffected. The Admin API reports each key's expiration in the [`expires_at`](https://platform.claude.com/docs/en/api/beta/organization/api_keys/list) field. See [Key expiration in Authentication](https://platform.claude.com/docs/en/manage-claude/authentication#key-expiration).
249* You can now set an expiration when you create an API key or an Admin API key in the [Claude Console](https://platform.claude.com/settings/keys). Choose a preset, a custom duration, or **Never**. For keys with a lifetime of at least 7 days, Anthropic emails the creator before expiration. Existing keys are unaffected. The Admin API reports each key’s expiration in the [`expires_at`](https://platform.claude.com/docs/en/api/beta/organization/api_keys/list) field. See [Key expiration in Authentication](https://platform.claude.com/docs/en/manage-claude/authentication#key-expiration).
250250
251251### July 2, 2026
252252
253* We've added the `agent-memory-2026-07-22` beta header, which changes how [listing memories](https://platform.claude.com/docs/en/managed-agents/memory#list-memories) (`GET /v1/memory_stores/{memory_store_id}/memories`) behaves: results are returned in a stable, server-defined order and the `order_by` and `order` parameters are ignored; `depth` accepts only `0`, `1`, or being omitted (other values return a `400` error); and `path_prefix` must end with `/` and matches whole path segments instead of a substring. Page cursors issued without the header aren't valid with it, so restart from the first page when you adopt it. On memory store endpoints, `agent-memory-2026-07-22` replaces `managed-agents-2026-04-01`; sending both returns a `400` error. On July 22, 2026, the `managed-agents-2026-04-01` header adopts the same list behavior. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
253* We’ve added the `agent-memory-2026-07-22` beta header, which changes how [listing memories](https://platform.claude.com/docs/en/managed-agents/memory#list-memories) (`GET /v1/memory_stores/{memory_store_id}/memories`) behaves: results are returned in a stable, server-defined order and the `order_by` and `order` parameters are ignored; `depth` accepts only `0`, `1`, or being omitted (other values return a `400` error); and `path_prefix` must end with `/` and matches whole path segments instead of a substring. Page cursors issued without the header aren’t valid with it, so restart from the first page when you adopt it. On memory store endpoints, `agent-memory-2026-07-22` replaces `managed-agents-2026-04-01`; sending both returns a `400` error. On July 22, 2026, the `managed-agents-2026-04-01` header adopts the same list behavior. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
254254* The Python (0.116.0), TypeScript (0.110.0), Go (1.56.0), Java (2.48.0), Ruby (1.55.0), PHP (0.36.0), C# (12.35.0), and CLI (1.16.0) SDKs now send `agent-memory-2026-07-22` on all memory store calls instead of `managed-agents-2026-04-01`. If your code passes `betas` explicitly on memory store calls, replace `managed-agents-2026-04-01` with `agent-memory-2026-07-22` there rather than adding a second value.
255255
256256### July 1, 2026
257257
258* We've restored access to Claude Fable 5 and Claude Mythos 5. See [our statement](https://www.anthropic.com/news/redeploying-fable-5) for more information.
258* We’ve restored access to Claude Fable 5 and Claude Mythos 5. See [our statement](https://www.anthropic.com/news/redeploying-fable-5) for more information.
259259
260260### June 30, 2026
261261
262* We've launched **Claude Sonnet 5** (`claude-sonnet-5`), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 USD per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is now on by default; manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See [What's new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) for details and migration guidance. For behavioral differences and model-specific prompting patterns, see [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5).
263* Claude Managed Agents session event streams now support [event deltas](https://platform.claude.com/docs/en/managed-agents/event-deltas). Opt in with the `event_deltas[]` query parameter on `GET /v1/sessions/{session_id}/events/stream`. The `event_start` and `event_delta` events preview an agent message's text as it's generated, before the complete `agent.message` event arrives.
262* We’ve launched **Claude Sonnet 5** (`claude-sonnet-5`), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 USD per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. Three behavior changes apply when migrating: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is now on by default; manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. Claude Sonnet 5 also uses a new tokenizer that produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. See [What’s new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) for details and migration guidance. For behavioral differences and model-specific prompting patterns, see [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5).
263* Claude Managed Agents session event streams now support [event deltas](https://platform.claude.com/docs/en/managed-agents/event-deltas). Opt in with the `event_deltas[]` query parameter on `GET /v1/sessions/{session_id}/events/stream`. The `event_start` and `event_delta` events preview an agent message’s text as it’s generated, before the complete `agent.message` event arrives.
264264* [Listing sessions](https://platform.claude.com/docs/en/managed-agents/session-operations#listing-sessions) for Claude Managed Agents now supports backward pagination. `GET /v1/sessions` returns a `prev_page` cursor alongside `next_page`; pass it as the `page` parameter to return to the previous page. See [Pagination](https://platform.claude.com/docs/en/api/overview#pagination).
265* When creating a Claude Managed Agents session, you can now [override the agent's configuration for that session](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session). Pass `agent` with `type: "agent_with_overrides"` to replace the model, system prompt, tools, MCP servers, or skills for a single session. The agent itself is unchanged.
266* Claude Managed Agents vaults now support an `injection_location` setting on [environment variable credentials](https://platform.claude.com/docs/en/managed-agents/vaults#add-a-credential) (the Environment variable tab). It controls whether the credential's value is substituted, at egress, into the agent's outbound request headers, the request body, or both.
265* When creating a Claude Managed Agents session, you can now [override the agent’s configuration for that session](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session). Pass `agent` with `type: "agent_with_overrides"` to replace the model, system prompt, tools, MCP servers, or skills for a single session. The agent itself is unchanged.
266* Claude Managed Agents vaults now support an `injection_location` setting on [environment variable credentials](https://platform.claude.com/docs/en/managed-agents/vaults#add-a-credential) (the Environment variable tab). It controls whether the credential’s value is substituted, at egress, into the agent’s outbound request headers, the request body, or both.
267267* Webhooks for Claude Managed Agents now cover the agent, deployment, and deployment run lifecycle. You can react to a newly published agent version, a paused deployment, or a failed scheduled run without polling. See the Agent events, Deployment events, and Deployment run events tabs in [Supported event types](https://platform.claude.com/docs/en/managed-agents/webhooks#supported-event-types).
268268
269269### June 29, 2026
270270
271* We've removed [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.6. Requests to `claude-opus-4-6` with `speed: "fast"` no longer run at fast speed or premium pricing: they run at standard speed, are billed at standard rates, and do not return an error. The response's `usage.speed` field reports the speed used. To continue using fast mode, migrate to [Claude Opus 4.8](https://platform.claude.com/docs/en/about-claude/models/migration-guide). Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
271* We’ve removed [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.6. Requests to `claude-opus-4-6` with `speed: "fast"` no longer run at fast speed or premium pricing: they run at standard speed, are billed at standard rates, and do not return an error. The response’s `usage.speed` field reports the speed used. To continue using fast mode, migrate to [Claude Opus 4.8](https://platform.claude.com/docs/en/about-claude/models/migration-guide). Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
272272
273273### June 26, 2026
274274
275* We've raised [rate limits](https://platform.claude.com/docs/en/api/rate-limits) across the Claude API. Claude Sonnet and Claude Haiku rate limits now match Claude Opus at every usage tier, and usage tiers have been consolidated into three: Start, Build, and Scale. Most organizations move to a higher tier, no organization receives lower limits than before, and no action is required. You can view your tier and current limits in the [Claude Console](https://platform.claude.com/settings/limits).
275* We’ve raised [rate limits](https://platform.claude.com/docs/en/api/rate-limits) across the Claude API. Claude Sonnet and Claude Haiku rate limits now match Claude Opus at every usage tier, and usage tiers have been consolidated into three: Start, Build, and Scale. Most organizations move to a higher tier, no organization receives lower limits than before, and no action is required. You can view your tier and current limits in the [Claude Console](https://platform.claude.com/settings/limits).
276276
277277### June 25, 2026
278278
279* We've deprecated [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.7, with removal on July 24, 2026. After removal, requests to `claude-opus-4-7` with `speed: "fast"` will return an error. Migrate to fast mode for Claude Opus 4.8. Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
279* We’ve deprecated [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.7, with removal on July 24, 2026. After removal, requests to `claude-opus-4-7` with `speed: "fast"` will return an error. Migrate to fast mode for Claude Opus 4.8. Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
280280
281281### June 22, 2026
282282
from line 284
284284
285285### June 18, 2026
286286
287* The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for `code_execution_20260120`, the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) version that adds REPL state persistence and is the minimum version for [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling). To adopt it, set the tool's `type` to `code_execution_20260120`; no beta header is required. It's available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility) section.
287* The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for `code_execution_20260120`, the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) version that adds REPL state persistence and is the minimum version for [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling). To adopt it, set the tool’s `type` to `code_execution_20260120`; no beta header is required. It’s available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool’s [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility) section.
288288
289289### June 15, 2026
290290
291* We've retired the Claude Sonnet 4 model (`claude-sonnet-4-20250514`) and the Claude Opus 4 model (`claude-opus-4-20250514`). All requests to these models on the Claude API will now return an error. We recommend upgrading to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) and [Claude Opus 4.8](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) respectively. Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
291* We’ve retired the Claude Sonnet 4 model (`claude-sonnet-4-20250514`) and the Claude Opus 4 model (`claude-opus-4-20250514`). All requests to these models on the Claude API will now return an error. We recommend upgrading to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) and [Claude Opus 4.8](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) respectively. Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
292292
293293### June 11, 2026
294294
from line 301
301301
302302### June 9, 2026
303303
304* We've launched **Claude Fable 5** (`claude-fable-5`), our most capable model open to all customers, alongside **Claude Mythos 5** (`claude-mythos-5`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). See [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) for specifications, pricing, and availability.
304* We’ve launched **Claude Fable 5** (`claude-fable-5`), our most capable model open to all customers, alongside **Claude Mythos 5** (`claude-mythos-5`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). See [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview) for specifications, pricing, and availability.
305305* Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7. Compared to models before Claude Opus 4.7, the same text produces roughly 30% more tokens. The exact increase depends on the content and workload shape. Use the [token counting API](https://platform.claude.com/docs/en/build-with-claude/token-counting#token-counts-on-claude-fable-5) with `model: "claude-fable-5"` to measure your prompts under the new tokenizer.
306* Claude Fable 5 runs safety classifiers on requests and during response generation. When a classifier declines a request, the Messages API returns `stop_reason: "refusal"`. You are not billed for a request refused before any output is generated. An opt-in `fallbacks` parameter (in beta on the Claude API and Claude Platform on AWS; not supported on the Message Batches API) re-runs refused requests on another model, billed at the fallback model's rates. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
307* The [`stop_details.category`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) field on refusal responses now includes `"reasoning_extraction"` on Claude Fable 5, returned when a request is blocked under Anthropic's Terms of Service restrictions on reverse engineering or duplicating model outputs. The existing `"cyber"` and `"bio"` categories are unchanged. No beta header is required.
306* Claude Fable 5 runs safety classifiers on requests and during response generation. When a classifier declines a request, the Messages API returns `stop_reason: "refusal"`. You are not billed for a request refused before any output is generated. An opt-in `fallbacks` parameter (in beta on the Claude API and Claude Platform on AWS; not supported on the Message Batches API) re-runs refused requests on another model, billed at the fallback model’s rates. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
307* The [`stop_details.category`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) field on refusal responses now includes `"reasoning_extraction"` on Claude Fable 5, returned when a request is blocked under Anthropic’s Terms of Service restrictions on reverse engineering or duplicating model outputs. The existing `"cyber"` and `"bio"` categories are unchanged. No beta header is required.
308308* On Claude Fable 5 and Claude Mythos 5, [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is the only thinking mode: `thinking: {"type": "disabled"}` is not supported, and manual extended thinking budgets and assistant prefill are not supported (both return a 400 error).
309309* On Claude Fable 5 and Claude Mythos 5, `thinking.display` defaults to `"omitted"`, the same as Claude Opus 4.8, Claude Opus 4.7, and Claude Mythos Preview; set `display: "summarized"` to receive readable thinking summaries. The raw chain of thought is never returned; pass thinking blocks back unchanged in multi-turn conversations on the same model. See [Thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-output-on-claude-fable-5-and-claude-mythos-5).
310310* Claude Fable 5 requires 30-day data retention and is not available under zero data retention. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
311311* Claude Managed Agents now supports [scheduled deployments](https://platform.claude.com/docs/en/managed-agents/scheduled-deployments), letting you run sessions on a cron schedule without managing your own scheduler.
312* Claude Managed Agents vaults now support [environment variable credentials](https://platform.claude.com/docs/en/managed-agents/vaults#add-a-credential), so you can securely inject secrets into the agent's sandbox for CLIs, SDKs, and other services that authenticate through environment variables.
312* Claude Managed Agents vaults now support [environment variable credentials](https://platform.claude.com/docs/en/managed-agents/vaults#add-a-credential), so you can securely inject secrets into the agent’s sandbox for CLIs, SDKs, and other services that authenticate through environment variables.
313313* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) (`GET /v1/compliance/activities`) is now available on [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws). See [Compliance IAM actions for Claude Platform on AWS](https://platform.claude.com/docs/en/api/claude-platform-on-aws-iam-actions#compliance) for the `ListComplianceActivities` action that authorizes it.
314314* The `session.thread_*` webhook events now include a `session_thread_id` field identifying the multiagent thread that triggered the event.
315* We've released a [Swift package](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/apple-foundation-models) in beta that adds Claude as a server-side `LanguageModel` in Apple's Foundation Models framework. Call Claude through the same `LanguageModelSession` API as Apple's on-device model on iOS 27, macOS 27, visionOS 27, and watchOS 27 (beta).
315* We’ve released a [Swift package](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/apple-foundation-models) in beta that adds Claude as a server-side `LanguageModel` in Apple’s Foundation Models framework. Call Claude through the same `LanguageModelSession` API as Apple’s on-device model on iOS 27, macOS 27, visionOS 27, and watchOS 27 (beta).
316316
317317### June 5, 2026
318318
from line 320
320320
321321### June 2, 2026
322322
323* The [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) now supports a `max_tokens` parameter to cap the advisor model's output for each call, reducing latency and output token cost for workloads that don't need full-length advisor responses. Set `tools[].max_tokens` on the advisor tool definition; see [Capping advisor output](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#capping-advisor-output).
323* The [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) now supports a `max_tokens` parameter to cap the advisor model’s output for each call, reducing latency and output token cost for workloads that don’t need full-length advisor responses. Set `tools[].max_tokens` on the advisor tool definition; see [Capping advisor output](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#capping-advisor-output).
324324* On the Claude API, you are no longer billed for a request when it returns `stop_reason: "refusal"` without Claude having generated any output. See [Streaming refusals](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals) for detecting and handling refusals.
325325
326326### May 29, 2026
from line 329
329329
330330### May 28, 2026
331331
332* We've launched **Claude Opus 4.8** (claude-opus-4-8), our most capable model. Claude Opus 4.8 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default on the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7. See the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide) for baseline settings, features, and migration guidance.
333* We've launched [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). On Claude Opus 4.8, you can send `role: "system"` messages after a user turn (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)) in the `messages` array, preserving prompt cache hits when instructions change during a long-running session. No beta header is required.
332* We’ve launched **Claude Opus 4.8** (claude-opus-4-8), our most capable model. Claude Opus 4.8 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default on the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7. See the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide) for baseline settings, features, and migration guidance.
333* We’ve launched [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). On Claude Opus 4.8, you can send `role: "system"` messages after a user turn (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)) in the `messages` array, preserving prompt cache hits when instructions change during a long-running session. No beta header is required.
334334* The [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) field on refusal responses is now publicly documented; it returns a `category` (`cyber`, `bio`, or `null`) and a human-readable `explanation`, so your application can route different classes of refusal to the right next step. No beta header is required.
335335* On Claude Opus 4.8, the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) defaults to `high` across all surfaces, including Claude Code and the Messages API.
336336* On Claude Opus 4.8, the minimum cacheable prompt length for [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) is 1,024 tokens, lower than on Claude Opus 4.7.
from line 341
341341* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) now supports Claude Opus 4.8.
342342* [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.8 is available as a research preview on the Claude API only.
343343* Setting the sampling parameters `temperature`, `top_p`, or `top_k` to a non-default value returns a 400 error on Claude Opus 4.8, same as on Claude Opus 4.7. See the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide) for details.
344* In Claude Code, we've expanded Auto mode to more users for long-running tasks. See the [Claude Code documentation](https://code.claude.com/docs).
344* In Claude Code, we’ve expanded Auto mode to more users for long-running tasks. See the [Claude Code documentation](https://code.claude.com/docs).
345345* In Claude Code, Max plan users now default to [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on Claude Opus 4.8. See the [Claude Code documentation](https://code.claude.com/docs).
346346* In Claude Code, Workflows are available as a research preview, letting you define and run multistep agentic plans. See the [Claude Code documentation](https://code.claude.com/docs).
347* We've deprecated [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.6, with removal approximately 30 days after launch. Migrate to fast mode for Claude Opus 4.8 or Claude Opus 4.7. Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
347* We’ve deprecated [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) for Claude Opus 4.6, with removal approximately 30 days after launch. Migrate to fast mode for Claude Opus 4.8 or Claude Opus 4.7. Read more in [Fast mode model availability](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
348348* For updates to claude.ai, Cowork, Claude for Microsoft 365, and other Claude apps in this release, see the [release notes for Claude Apps](https://support.claude.com/en/articles/12138966-release-notes).
349349
350350### May 27, 2026
from line 354
354354### May 19, 2026
355355
356356* [MCP tunnels](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/overview) is now available as a research preview, so you can connect to MCP servers in your private network.
357* Self-hosted sandboxes are now available for Claude Managed Agents, as an alternative to running tool execution in Anthropic's infrastructure. See [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes).
358* With Claude Managed Agents, you can now update the agent's MCP server and tool configurations associated with an active session.
357* Self-hosted sandboxes are now available for Claude Managed Agents, as an alternative to running tool execution in Anthropic’s infrastructure. See [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes).
358* With Claude Managed Agents, you can now update the agent’s MCP server and tool configurations associated with an active session.
359359* With Claude Managed Agents, large outputs from `agent_toolset` and MCP tools exceeding 100K characters (about 25K tokens) are now automatically spilled to a file in the sandbox. The model receives a truncated preview with the file path and can read the full content from there.
360360
361361### May 18, 2026
from line 364
364364
365365### May 13, 2026
366366
367* We've launched [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) in beta. Pass `diagnostics.previous_message_id` on a Messages request and the API reports a `cache_miss_reason` explaining where the prompt cache prefix diverged from the previous turn. Include the `cache-diagnosis-2026-04-07` beta header in your requests.
367* We’ve launched [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) in beta. Pass `diagnostics.previous_message_id` on a Messages request and the API reports a `cache_miss_reason` explaining where the prompt cache prefix diverged from the previous turn. Include the `cache-diagnosis-2026-04-07` beta header in your requests.
368368
369369### May 12, 2026
370370
from line 372
372372
373373### May 11, 2026
374374
375* We've launched **Claude Platform on AWS**, bringing the Claude API to Anthropic-managed infrastructure accessible through AWS, with AWS billing and IAM authentication. Access the full Messages API, Files API, Message Batches API, Claude Managed Agents, Agent Skills, code execution, and tool use through native AWS endpoints. Learn more in [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws).
375* We’ve launched **Claude Platform on AWS**, bringing the Claude API to Anthropic-managed infrastructure accessible through AWS, with AWS billing and IAM authentication. Access the full Messages API, Files API, Message Batches API, Claude Managed Agents, Agent Skills, code execution, and tool use through native AWS endpoints. Learn more in [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws).
376376
377377### May 6, 2026
378378
from line 384
384384
385385### May 4, 2026
386386
387* We've launched [Workload Identity Federation](https://platform.claude.com/docs/en/manage-claude/workload-identity-federation). Authenticate workloads to the Claude API with short-lived OIDC tokens from your own identity provider (AWS IAM, Google Cloud, GitHub Actions, Kubernetes, Microsoft Entra ID, Okta, SPIFFE, and more) instead of long-lived static API keys. Configure issuers and federation rules in the Claude Console, and the SDK handles token exchange and refresh automatically. See [Authentication](https://platform.claude.com/docs/en/manage-claude/authentication).
387* We’ve launched [Workload Identity Federation](https://platform.claude.com/docs/en/manage-claude/workload-identity-federation). Authenticate workloads to the Claude API with short-lived OIDC tokens from your own identity provider (AWS IAM, Google Cloud, GitHub Actions, Kubernetes, Microsoft Entra ID, Okta, SPIFFE, and more) instead of long-lived static API keys. Configure issuers and federation rules in the Claude Console, and the SDK handles token exchange and refresh automatically. See [Authentication](https://platform.claude.com/docs/en/manage-claude/authentication).
388388
389389### April 30, 2026
390390
391* We've retired the 1M token context window beta (`context-1m-2025-08-07`) for Claude Sonnet 4.5 and Claude Sonnet 4. The beta header now has no effect on these models, and requests exceeding the standard 200k-token context window return an error. To use the 1M context window, migrate to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) or [Claude Opus 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison), where it's included at standard pricing with no beta header required.
391* We’ve retired the 1M token context window beta (`context-1m-2025-08-07`) for Claude Sonnet 4.5 and Claude Sonnet 4. The beta header now has no effect on these models, and requests exceeding the standard 200k-token context window return an error. To use the 1M context window, migrate to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) or [Claude Opus 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison), where it’s included at standard pricing with no beta header required.
392392
393393### April 29, 2026
394394
395* We've released the [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill), an open-source [Agent Skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) that gives Claude up-to-date reference material for building on the Messages API and Claude Managed Agents across 8 languages. The skill is bundled with Claude Code and available in the [Anthropic skills repository](https://github.com/anthropics/skills/tree/main/skills/claude-api).
395* We’ve released the [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill), an open-source [Agent Skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) that gives Claude up-to-date reference material for building on the Messages API and Claude Managed Agents across 8 languages. The skill is bundled with Claude Code and available in the [Anthropic skills repository](https://github.com/anthropics/skills/tree/main/skills/claude-api).
396396
397397### April 24, 2026
398398
399* We've released the [Rate Limits API](https://platform.claude.com/docs/en/manage-claude/rate-limits-api), allowing administrators to programmatically query the rate limits configured for their organization and workspaces.
399* We’ve released the [Rate Limits API](https://platform.claude.com/docs/en/manage-claude/rate-limits-api), allowing administrators to programmatically query the rate limits configured for their organization and workspaces.
400400
401401### April 23, 2026
402402
from line 404
404404
405405### April 20, 2026
406406
407* We've retired the Claude Haiku 3 model (`claude-3-haiku-20240307`). All requests to this model will now return an error. We recommend upgrading to [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison).
407* We’ve retired the Claude Haiku 3 model (`claude-3-haiku-20240307`). All requests to this model will now return an error. We recommend upgrading to [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison).
408408
409409### April 16, 2026
410410
411* We've launched [Claude Opus 4.7](https://www.anthropic.com/news/claude-opus-4-7), our most capable model for complex reasoning and agentic coding, at the same $5 / $25 USD per MTok pricing as Opus 4.6. See [What's new in Claude Opus 4.7](https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-7) for capability improvements, new features, and the updated tokenizer. Opus 4.7 includes API breaking changes versus Opus 4.6; see the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide) before upgrading.
411* We’ve launched [Claude Opus 4.7](https://www.anthropic.com/news/claude-opus-4-7), our most capable model for complex reasoning and agentic coding, at the same $5 / $25 USD per MTok pricing as Opus 4.6. See [What’s new in Claude Opus 4.7](https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-7) for capability improvements, new features, and the updated tokenizer. Opus 4.7 includes API breaking changes versus Opus 4.6; see the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide) before upgrading.
412412* [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) is now open to all Amazon Bedrock customers. Claude Opus 4.7 and Claude Haiku 4.5 are available self-serve from the Bedrock console through the Messages API endpoint at `/anthropic/v1/messages`, in 27 AWS regions with global and regional endpoints.
413* We've launched [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) in beta on Claude Opus 4.7. Give Claude an advisory token budget for a full agentic loop (thinking, tool calls, tool results, and output) and the model sees a running countdown, using it to prioritize work and finish gracefully as the budget is consumed. Include the `task-budgets-2026-03-13` beta header in your requests.
413* We’ve launched [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) in beta on Claude Opus 4.7. Give Claude an advisory token budget for a full agentic loop (thinking, tool calls, tool results, and output) and the model sees a running countdown, using it to prioritize work and finish gracefully as the budget is consumed. Include the `task-budgets-2026-03-13` beta header in your requests.
414414* Claude Opus 4.7 supports [high-resolution image input](https://platform.claude.com/docs/en/build-with-claude/vision#high-resolution-image-support-on-claude-opus-4-7), raising the maximum image resolution from 1568 to 2576 pixels on the long edge for improved performance on computer use, screenshot understanding, and document analysis. High-resolution support is automatic and requires no beta header; images may use up to approximately 3x more image tokens than on prior models.
415* We've added the `xhigh` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level on Claude Opus 4.7. `xhigh` sits between `high` and `max` and is tuned for long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions. No beta header is required.
415* We’ve added the `xhigh` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level on Claude Opus 4.7. `xhigh` sits between `high` and `max` and is tuned for long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions. No beta header is required.
416416
417417### April 14, 2026
418418
from line 420
420420
421421### April 9, 2026
422422
423* We've launched the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) in beta. Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation, so long-horizon agentic workloads get close to advisor-solo quality while the bulk of token generation happens at executor-model rates. Include the beta header `advisor-tool-2026-03-01` in your requests.
423* We’ve launched the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) in beta. Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation, so long-horizon agentic workloads get close to advisor-solo quality while the bulk of token generation happens at executor-model rates. Include the beta header `advisor-tool-2026-03-01` in your requests.
424424
425425### April 8, 2026
426426
427* We've launched **Claude Managed Agents** in beta, a fully managed agent harness for running Claude as an autonomous agent with secure sandboxing, built-in tools, and server-sent event streaming. Create agents, configure containers, and run sessions through the API. All endpoints require the `managed-agents-2026-04-01` beta header. Learn more in [Claude Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview).
428* We've launched the **`ant` CLI**, a command-line client for the Claude API that enables faster interaction with the Claude API, native integration with Claude Code, and versioning of API resources in YAML files. Learn more in the [CLI quickstart](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart).
427* We’ve launched **Claude Managed Agents** in beta, a fully managed agent harness for running Claude as an autonomous agent with secure sandboxing, built-in tools, and server-sent event streaming. Create agents, configure containers, and run sessions through the API. All endpoints require the `managed-agents-2026-04-01` beta header. Learn more in [Claude Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview).
428* We’ve launched the **`ant` CLI**, a command-line client for the Claude API that enables faster interaction with the Claude API, native integration with Claude Code, and versioning of API resources in YAML files. Learn more in the [CLI quickstart](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart).
429429
430430### April 7, 2026
431431
from line 434
434434
435435### March 30, 2026
436436
437* We've raised the `max_tokens` cap to 300k on the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta) for Claude Opus 4.6 and Sonnet 4.6. Include the `output-300k-2026-03-24` beta header to generate longer single-turn outputs for long-form content, structured data, and large code generation tasks.
438* We're retiring the 1M token context window beta for Claude Sonnet 4.5 and Claude Sonnet 4 on **April 30, 2026**. After that date, the `context-1m-2025-08-07` beta header will have no effect on these models, and requests that exceed the standard 200k-token context window will return an error. To continue using 1M context windows, migrate to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) or [Claude Opus 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison), which support the full 1M token context window at standard pricing with no beta header required.
437* We’ve raised the `max_tokens` cap to 300k on the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta) for Claude Opus 4.6 and Sonnet 4.6. Include the `output-300k-2026-03-24` beta header to generate longer single-turn outputs for long-form content, structured data, and large code generation tasks.
438* We’re retiring the 1M token context window beta for Claude Sonnet 4.5 and Claude Sonnet 4 on **April 30, 2026**. After that date, the `context-1m-2025-08-07` beta header will have no effect on these models, and requests that exceed the standard 200k-token context window will return an error. To continue using 1M context windows, migrate to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) or [Claude Opus 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison), which support the full 1M token context window at standard pricing with no beta header required.
439439
440440### March 18, 2026
441441
442* We've added model capability fields to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now return `max_input_tokens`, `max_tokens`, and a `capabilities` object. Query the API to discover what each model supports.
442* We’ve added model capability fields to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now return `max_input_tokens`, `max_tokens`, and a `capabilities` object. Query the API to discover what each model supports.
443443
444444### March 16, 2026
445445
446* We've launched the `display` field for extended thinking, letting you omit thinking content from responses for faster streaming. Set `thinking.display: "omitted"` to receive thinking blocks with an empty `thinking` field and the `signature` preserved for multi-turn continuity. Billing is unchanged. Learn more in [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).
446* We’ve launched the `display` field for extended thinking, letting you omit thinking content from responses for faster streaming. Set `thinking.display: "omitted"` to receive thinking blocks with an empty `thinking` field and the `signature` preserved for multi-turn continuity. Billing is unchanged. Learn more in [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).
447447
448448### March 13, 2026
449449
450450* The [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is out of beta for Claude Opus 4.6 and Sonnet 4.6, at standard pricing. Requests over 200k tokens work automatically for these models with no beta header required. The 1M token context window remains in beta for Claude Sonnet 4.5 and Sonnet 4.
451* We've removed the dedicated 1M rate limits for all supported models. Your standard account limits now apply across every context length.
452* We've raised the media limit from 100 to 600 images or PDF pages for each request when using the 1M token context window.
451* We’ve removed the dedicated 1M rate limits for all supported models. Your standard account limits now apply across every context length.
452* We’ve raised the media limit from 100 to 600 images or PDF pages for each request when using the 1M token context window.
453453
454454### February 19, 2026
455455
456* We've launched **automatic caching** for the Messages API. Add a single `cache_control` field to your request body and the system automatically caches the last cacheable block, moving the cache point forward as conversations grow. No manual breakpoint management required. Works alongside existing block-level cache control for fine-grained optimization. Available on the Claude API and Microsoft Foundry (preview). Learn more in [Automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching).
457* We've retired the Claude Sonnet 3.7 model (`claude-3-7-sonnet-20250219`) and the Claude Haiku 3.5 model (`claude-3-5-haiku-20241022`). All requests to Claude Sonnet 3.7 will now return an error. Requests to Claude Haiku 3.5 on the Claude API will now return an error; it remains available on Amazon Bedrock and Google Cloud. We recommend upgrading to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) and [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) respectively. Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
456* We’ve launched **automatic caching** for the Messages API. Add a single `cache_control` field to your request body and the system automatically caches the last cacheable block, moving the cache point forward as conversations grow. No manual breakpoint management required. Works alongside existing block-level cache control for fine-grained optimization. Available on the Claude API and Microsoft Foundry (preview). Learn more in [Automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching).
457* We’ve retired the Claude Sonnet 3.7 model (`claude-3-7-sonnet-20250219`) and the Claude Haiku 3.5 model (`claude-3-5-haiku-20241022`). All requests to Claude Sonnet 3.7 will now return an error. Requests to Claude Haiku 3.5 on the Claude API will now return an error; it remains available on Amazon Bedrock and Google Cloud. We recommend upgrading to [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) and [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) respectively. Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
458458* We announced the deprecation of the Claude Haiku 3 model (`claude-3-haiku-20240307`), with retirement scheduled for April 20, 2026. We recommend migrating to [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison). Read more in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
459459
460460### February 17, 2026
461461
462* We've [launched Claude Sonnet 4.6](https://www.anthropic.com/news/claude-sonnet-4-6), our latest balanced model combining speed and intelligence for everyday tasks. Sonnet 4.6 delivers improved agentic search performance while consuming fewer tokens. Sonnet 4.6 supports [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) and a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (beta). See [Models & Pricing](https://platform.claude.com/docs/en/models/overview) for details.
462* We’ve [launched Claude Sonnet 4.6](https://www.anthropic.com/news/claude-sonnet-4-6), our latest balanced model combining speed and intelligence for everyday tasks. Sonnet 4.6 delivers improved agentic search performance while consuming fewer tokens. Sonnet 4.6 supports [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) and a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (beta). See [Models & Pricing](https://platform.claude.com/docs/en/models/overview) for details.
463463* API [code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) is now **free when used with web search or web fetch**. Sandboxed code execution improves model capability and token efficiency. See the [pricing details](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#usage-and-pricing) for standalone usage.
464464* The [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) and [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) are available with no beta header required. Web search and web fetch now support [dynamic filtering](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool#dynamic-filtering), which uses code execution to filter results before they reach the context window for better performance and reduced token cost.
465465* The [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool), [web fetch tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool), [tool search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool), [tool use examples](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#providing-tool-use-examples), and [memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) no longer require a beta header.
from line 466
466466
467467### February 7, 2026
468468
469* We've launched [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) in research preview for Opus 4.6, providing significantly faster output token generation through the `speed` parameter. Fast mode is up to 2.5x as fast at premium pricing. Interested customers should join the [waitlist](https://claude.com/fast-mode).
469* We’ve launched [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) in research preview for Opus 4.6, providing significantly faster output token generation through the `speed` parameter. Fast mode is up to 2.5x as fast at premium pricing. Interested customers should join the [waitlist](https://claude.com/fast-mode).
470470
471471### February 5, 2026
472472
473* We've [launched Claude Opus 4.6](https://www.anthropic.com/news/claude-opus-4-6), our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`); manual thinking (`type: "enabled"` with `budget_tokens`) is deprecated. Opus 4.6 does not support prefilling assistant messages. Learn more in [What's new in Claude 4.6](https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-6).
473* We’ve [launched Claude Opus 4.6](https://www.anthropic.com/news/claude-opus-4-6), our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`); manual thinking (`type: "enabled"` with `budget_tokens`) is deprecated. Opus 4.6 does not support prefilling assistant messages. Learn more in [What’s new in Claude 4.6](https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-6).
474474* The [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) no longer requires a beta header and now supports Claude Opus 4.6. Effort replaces `budget_tokens` for controlling thinking depth on new models.
475* We've launched the [compaction API](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) in beta, providing server-side context summarization for effectively infinite conversations. Available on Opus 4.6.
476* We've introduced [data residency controls](https://platform.claude.com/docs/en/manage-claude/data-residency), allowing you to specify where model inference runs with the `inference_geo` parameter. US-only inference is available at 1.1x pricing for models released after February 1, 2026.
475* We’ve launched the [compaction API](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) in beta, providing server-side context summarization for effectively infinite conversations. Available on Opus 4.6.
476* We’ve introduced [data residency controls](https://platform.claude.com/docs/en/manage-claude/data-residency), allowing you to specify where model inference runs with the `inference_geo` parameter. US-only inference is available at 1.1x pricing for models released after February 1, 2026.
477477* The [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is now available in beta for Claude Opus 4.6, in addition to Sonnet 4.5 and Sonnet 4. [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing) applies to requests exceeding 200k input tokens.
478478* [Fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) no longer requires a beta header on any model or platform.
479479
from line 487
487487
488488### January 5, 2026
489489
490* We've retired the Claude Opus 3 model (`claude-3-opus-20240229`). All requests to this model will now return an error. We recommend upgrading to [Claude Opus 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison), which offers significantly improved intelligence at a third of the cost. Researchers can request ongoing access to Claude Opus 3 on the API through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
490* We’ve retired the Claude Opus 3 model (`claude-3-opus-20240229`). All requests to this model will now return an error. We recommend upgrading to [Claude Opus 4.5](https://platform.claude.com/docs/en/models/overview#latest-models-comparison), which offers significantly improved intelligence at a third of the cost. Researchers can request ongoing access to Claude Opus 3 on the API through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
491491
492492### December 19, 2025
493493
from line 499
499499
500500### November 24, 2025
501501
502* We've [launched Claude Opus 4.5](https://www.anthropic.com/news/claude-opus-4-5), our most intelligent model combining maximum capability with practical performance. Ideal for complex specialized tasks, professional software engineering, and advanced agents. Features step-change improvements in vision, coding, and computer use at a more accessible price point than previous Opus models. Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
503* We've launched [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) in beta, allowing Claude to call tools from within code execution to reduce latency and token usage in multi-tool workflows.
504* We've launched the [tool search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) in beta, enabling Claude to dynamically discover and load tools on-demand from large tool catalogs.
505* We've launched the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) in beta for Claude Opus 4.5, allowing you to control token usage by trading off between response thoroughness and efficiency.
506* We've added [client-side compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk) to our Python and TypeScript SDKs, automatically managing conversation context through summarization when using `tool_runner`.
502* We’ve [launched Claude Opus 4.5](https://www.anthropic.com/news/claude-opus-4-5), our most intelligent model combining maximum capability with practical performance. Ideal for complex specialized tasks, professional software engineering, and advanced agents. Features step-change improvements in vision, coding, and computer use at a more accessible price point than previous Opus models. Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
503* We’ve launched [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) in beta, allowing Claude to call tools from within code execution to reduce latency and token usage in multi-tool workflows.
504* We’ve launched the [tool search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) in beta, enabling Claude to dynamically discover and load tools on-demand from large tool catalogs.
505* We’ve launched the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) in beta for Claude Opus 4.5, allowing you to control token usage by trading off between response thoroughness and efficiency.
506* We’ve added [client-side compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk) to our Python and TypeScript SDKs, automatically managing conversation context through summarization when using `tool_runner`.
507507
508508### November 21, 2025
509509
from line 511
511511
512512### November 19, 2025
513513
514* We've launched a **new documentation platform** at [platform.claude.com/docs](https://platform.claude.com/docs). Our documentation now lives side by side with the Claude Console, providing a unified developer experience. The previous docs site at docs.claude.com will redirect to the new location.
514* We’ve launched a **new documentation platform** at [platform.claude.com/docs](https://platform.claude.com/docs). Our documentation now lives side by side with the Claude Console, providing a unified developer experience. The previous docs site at docs.claude.com will redirect to the new location.
515515
516516### November 18, 2025
517517
518* We've launched **Claude in Microsoft Foundry**, bringing Claude models to Azure customers with Azure billing and OAuth authentication. Access the full Messages API including extended thinking, prompt caching (5-minute and 1-hour), PDF support, Files API, Agent Skills, and tool use. Learn more in [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry).
518* We’ve launched **Claude in Microsoft Foundry**, bringing Claude models to Azure customers with Azure billing and OAuth authentication. Access the full Messages API including extended thinking, prompt caching (5-minute and 1-hour), PDF support, Files API, Agent Skills, and tool use. Learn more in [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry).
519519
520520### November 14, 2025
521521
522* We've launched [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) in beta, providing guaranteed schema conformance for Claude's responses. Use JSON outputs for structured data responses or strict tool use for validated tool inputs. Available for Claude Sonnet 4.5 and Claude Opus 4.1. To enable, use the beta header `structured-outputs-2025-11-13`.
522* We’ve launched [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) in beta, providing guaranteed schema conformance for Claude’s responses. Use JSON outputs for structured data responses or strict tool use for validated tool inputs. Available for Claude Sonnet 4.5 and Claude Opus 4.1. To enable, use the beta header `structured-outputs-2025-11-13`.
523523
524524### October 28, 2025
525525
526526* We announced the deprecation of the Claude Sonnet 3.7 model. Read more in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
527* We've retired the Claude Sonnet 3.5 models. All requests to these models will now return an error.
528* We've expanded context editing with thinking block clearing (`clear_thinking_20251015`), enabling automatic management of thinking blocks. Learn more in [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing).
527* We’ve retired the Claude Sonnet 3.5 models. All requests to these models will now return an error.
528* We’ve expanded context editing with thinking block clearing (`clear_thinking_20251015`), enabling automatic management of thinking blocks. Learn more in [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing).
529529
530530### October 16, 2025
531531
532* We've [launched Agent Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) (`skills-2025-10-02` beta), a new way to extend Claude's capabilities. Skills are organized folders of instructions, scripts, and resources that Claude loads dynamically to perform specialized tasks. The initial release includes:
532* We’ve [launched Agent Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) (`skills-2025-10-02` beta), a new way to extend Claude’s capabilities. Skills are organized folders of instructions, scripts, and resources that Claude loads dynamically to perform specialized tasks. The initial release includes:
533533
534534 * **Anthropic-managed Skills**: Pre-built Skills for working with PowerPoint (.pptx), Excel (.xlsx), Word (.docx), and PDF files
535535 * **Custom Skills**: Upload your own Skills through the Skills API (`/v1/skills` endpoints) to package domain expertise and organizational workflows
from line 538
538538
539539### October 15, 2025
540540
541* We've [launched Claude Haiku 4.5](https://www.anthropic.com/news/claude-haiku-4-5), our fastest and most intelligent Haiku model with near-frontier performance. Ideal for real-time applications, high-volume processing, and cost-sensitive deployments requiring strong reasoning. Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
541* We’ve [launched Claude Haiku 4.5](https://www.anthropic.com/news/claude-haiku-4-5), our fastest and most intelligent Haiku model with near-frontier performance. Ideal for real-time applications, high-volume processing, and cost-sensitive deployments requiring strong reasoning. Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
542542
543543### September 29, 2025
544544
545* We've launched [Claude Sonnet 4.5](https://www.anthropic.com/news/claude-sonnet-4-5), our best model for complex agents and coding, with the highest intelligence across most tasks. Learn more in the [models overview](https://platform.claude.com/docs/en/models/overview).
546* We've introduced [global endpoint pricing](https://platform.claude.com/docs/en/about-claude/pricing#cloud-platform-pricing) for Amazon Bedrock and Vertex AI. The Claude API (1P) pricing is unaffected.
547* We've introduced a new stop reason `model_context_window_exceeded` that allows you to request the maximum possible tokens without calculating input size. Learn more in [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
548* We've launched the memory tool in beta, enabling Claude to store and consult information across conversations. Learn more in [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool).
549* We've launched context editing in beta, providing strategies to automatically manage conversation context. The initial release supports clearing older tool results and calls when approaching token limits. Learn more in [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing).
545* We’ve launched [Claude Sonnet 4.5](https://www.anthropic.com/news/claude-sonnet-4-5), our best model for complex agents and coding, with the highest intelligence across most tasks. Learn more in the [models overview](https://platform.claude.com/docs/en/models/overview).
546* We’ve introduced [global endpoint pricing](https://platform.claude.com/docs/en/about-claude/pricing#cloud-platform-pricing) for Amazon Bedrock and Vertex AI. The Claude API (1P) pricing is unaffected.
547* We’ve introduced a new stop reason `model_context_window_exceeded` that allows you to request the maximum possible tokens without calculating input size. Learn more in [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
548* We’ve launched the memory tool in beta, enabling Claude to store and consult information across conversations. Learn more in [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool).
549* We’ve launched context editing in beta, providing strategies to automatically manage conversation context. The initial release supports clearing older tool results and calls when approaching token limits. Learn more in [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing).
550550
551551### September 17, 2025
552552
553* We've launched tool helpers in beta for the Python and TypeScript SDKs, simplifying tool creation and execution with type-safe input validation and a tool runner for automated tool handling in conversations. For details, see the documentation for [the Python SDK](https://github.com/anthropics/anthropic-sdk-python/blob/main/tools.md) and [the TypeScript SDK](https://github.com/anthropics/anthropic-sdk-typescript/blob/main/helpers.md#tool-helpers).
553* We’ve launched tool helpers in beta for the Python and TypeScript SDKs, simplifying tool creation and execution with type-safe input validation and a tool runner for automated tool handling in conversations. For details, see the documentation for [the Python SDK](https://github.com/anthropics/anthropic-sdk-python/blob/main/tools.md) and [the TypeScript SDK](https://github.com/anthropics/anthropic-sdk-typescript/blob/main/helpers.md#tool-helpers).
554554
555555### September 16, 2025
556556
557* We've unified our developer offerings under the Claude brand. You should see updated naming and URLs across our platform and documentation, but **our developer interfaces will remain the same**. Here are some notable changes:
557* We’ve unified our developer offerings under the Claude brand. You should see updated naming and URLs across our platform and documentation, but **our developer interfaces will remain the same**. Here are some notable changes:
558558
559559 * Claude Console ([console.anthropic.com](https://console.anthropic.com)) → Claude Console ([platform.claude.com](https://platform.claude.com)). The console will be available at both URLs until January 12, 2026. After that date, [console.anthropic.com](https://console.anthropic.com) will automatically redirect to [platform.claude.com](https://platform.claude.com).
560560 * Anthropic Docs ([docs.anthropic.com](https://docs.anthropic.com)) → Claude Docs ([docs.claude.com](https://docs.claude.com))
from line 563
563563
564564### September 10, 2025
565565
566* We've launched the web fetch tool in beta, allowing Claude to retrieve full content from specified web pages and PDF documents. Learn more in [Web fetch tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool).
567* We've launched the [Claude Code Analytics API](https://platform.claude.com/docs/en/manage-claude/claude-code-analytics-api), enabling organizations to programmatically access daily aggregated usage metrics for Claude Code, including productivity metrics, tool usage statistics, and cost data.
566* We’ve launched the web fetch tool in beta, allowing Claude to retrieve full content from specified web pages and PDF documents. Learn more in [Web fetch tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool).
567* We’ve launched the [Claude Code Analytics API](https://platform.claude.com/docs/en/manage-claude/claude-code-analytics-api), enabling organizations to programmatically access daily aggregated usage metrics for Claude Code, including productivity metrics, tool usage statistics, and cost data.
568568
569569### September 8, 2025
570570
from line 572
572572
573573### September 5, 2025
574574
575* We've launched [rate limit charts](https://platform.claude.com/docs/en/api/rate-limits#monitoring-your-rate-limits-in-the-console) in the Console [Usage](https://console.anthropic.com/settings/usage) page, allowing you to monitor your API rate limit usage and caching rates over time.
575* We’ve launched [rate limit charts](https://platform.claude.com/docs/en/api/rate-limits#monitoring-your-rate-limits-in-the-console) in the Console [Usage](https://console.anthropic.com/settings/usage) page, allowing you to monitor your API rate limit usage and caching rates over time.
576576
577577### September 3, 2025
578578
579* We've launched support for citable documents in client-side tool results. Learn more in [Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls).
579* We’ve launched support for citable documents in client-side tool results. Learn more in [Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls).
580580
581581### September 2, 2025
582582
583* We've launched v2 of the [Code Execution Tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) in beta, replacing the original Python-only tool with Bash command execution and direct file manipulation capabilities, including writing code in other languages.
583* We’ve launched v2 of the [Code Execution Tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) in beta, replacing the original Python-only tool with Bash command execution and direct file manipulation capabilities, including writing code in other languages.
584584
585585### August 27, 2025
586586
from line 588
588588
589589### August 26, 2025
590590
591* We've increased rate limits on the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) for Claude Sonnet 4 on the Claude API.
591* We’ve increased rate limits on the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) for Claude Sonnet 4 on the Claude API.
592592* The 1M token context window is now available on Vertex AI. For more information, see [Claude on Vertex AI](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed).
593593
594594### August 19, 2025
from line 597
597597
598598### August 18, 2025
599599
600* We've released the [Usage & Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api), allowing administrators to programmatically monitor their organization's usage and cost data.
601* We've added a new endpoint to the Admin API for retrieving organization information. For details, see the [Organization Info Admin API reference](https://platform.claude.com/docs/en/api/beta/organization/retrieve).
600* We’ve released the [Usage & Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api), allowing administrators to programmatically monitor their organization’s usage and cost data.
601* We’ve added a new endpoint to the Admin API for retrieving organization information. For details, see the [Organization Info Admin API reference](https://platform.claude.com/docs/en/api/beta/organization/retrieve).
602602
603603### August 13, 2025
604604
from line 607
607607
608608### August 12, 2025
609609
610* We've launched beta support for a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) in Claude Sonnet 4 on the Claude API and Amazon Bedrock.
610* We’ve launched beta support for a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) in Claude Sonnet 4 on the Claude API and Amazon Bedrock.
611611
612612### August 11, 2025
613613
from line 619
619619
620620### August 5, 2025
621621
622* We've launched [Claude Opus 4.1](https://www.anthropic.com/news/claude-opus-4-1), an incremental update to Claude Opus 4 with enhanced capabilities and performance improvements.\* Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
622* We’ve launched [Claude Opus 4.1](https://www.anthropic.com/news/claude-opus-4-1), an incremental update to Claude Opus 4 with enhanced capabilities and performance improvements.\* Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
623623
624624*\*Opus 4.1 does not allow both `temperature` and `top_p` parameters to be specified. Please use only one.*
625625
626626### July 28, 2025
627627
628* We've released `text_editor_20250728`, an updated text editor tool that fixes some issues from the previous versions and adds an optional `max_characters` parameter that allows you to control the truncation length when viewing large files.
628* We’ve released `text_editor_20250728`, an updated text editor tool that fixes some issues from the previous versions and adds an optional `max_characters` parameter that allows you to control the truncation length when viewing large files.
629629
630630### July 24, 2025
631631
632* We've increased [rate limits](https://platform.claude.com/docs/en/api/rate-limits) for Claude Opus 4 on the Claude API to give you more capacity to build and scale with Claude. For customers with [usage tier 1-4 rate limits](https://platform.claude.com/docs/en/api/rate-limits#rate-limits), these changes apply immediately to your account - no action needed.
632* We’ve increased [rate limits](https://platform.claude.com/docs/en/api/rate-limits) for Claude Opus 4 on the Claude API to give you more capacity to build and scale with Claude. For customers with [usage tier 1-4 rate limits](https://platform.claude.com/docs/en/api/rate-limits#rate-limits), these changes apply immediately to your account - no action needed.
633633
634634### July 21, 2025
635635
636* We've retired the Claude 2.0, Claude 2.1, and Claude Sonnet 3 models. All requests to these models will now return an error. Read more in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
636* We’ve retired the Claude 2.0, Claude 2.1, and Claude Sonnet 3 models. All requests to these models will now return an error. Read more in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
637637
638638### July 17, 2025
639639
640* We've increased [rate limits](https://platform.claude.com/docs/en/api/rate-limits) for Claude Sonnet 4 on the Claude API to give you more capacity to build and scale with Claude. For customers with [usage tier 1-4 rate limits](https://platform.claude.com/docs/en/api/rate-limits#rate-limits), these changes apply immediately to your account - no action needed.
640* We’ve increased [rate limits](https://platform.claude.com/docs/en/api/rate-limits) for Claude Sonnet 4 on the Claude API to give you more capacity to build and scale with Claude. For customers with [usage tier 1-4 rate limits](https://platform.claude.com/docs/en/api/rate-limits#rate-limits), these changes apply immediately to your account - no action needed.
641641
642642### July 3, 2025
643643
644* We've launched search result content blocks in beta, enabling natural citations for RAG applications. Tools can now return search results with proper source attribution, and Claude will automatically cite these sources in its responses - matching the citation quality of web search. This eliminates the need for document workarounds in custom knowledge base applications. Learn more in [Search results](https://platform.claude.com/docs/en/build-with-claude/search-results). To enable this feature, use the beta header `search-results-2025-06-09`.
644* We’ve launched search result content blocks in beta, enabling natural citations for RAG applications. Tools can now return search results with proper source attribution, and Claude will automatically cite these sources in its responses - matching the citation quality of web search. This eliminates the need for document workarounds in custom knowledge base applications. Learn more in [Search results](https://platform.claude.com/docs/en/build-with-claude/search-results). To enable this feature, use the beta header `search-results-2025-06-09`.
645645
646646### June 30, 2025
647647
from line 653
653653
654654### June 11, 2025
655655
656* We've launched [fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) in beta, a feature that enables Claude to stream tool use parameters without buffering / JSON validation. To enable fine-grained tool streaming, use the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `fine-grained-tool-streaming-2025-05-14`.
656* We’ve launched [fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) in beta, a feature that enables Claude to stream tool use parameters without buffering / JSON validation. To enable fine-grained tool streaming, use the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `fine-grained-tool-streaming-2025-05-14`.
657657
658658### May 22, 2025
659659
660* We've launched [Claude Opus 4 and Claude Sonnet 4](https://www.anthropic.com/news/claude-4), our latest models with extended thinking capabilities. Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
661* The default behavior of [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) in Claude 4 models returns a summary of Claude's full thinking process, with the full thinking encrypted and returned in the `signature` field of `thinking` block output.
662* We've launched [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking) in beta, a feature that enables Claude to think in between tool calls. To enable interleaved thinking, use the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `interleaved-thinking-2025-05-14`.
663* We've launched the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) in beta, enabling you to upload files and reference them in the Messages API and code execution tool.
664* We've launched the [Code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) in beta, a tool that enables Claude to execute Python code in a secure, sandboxed environment.
665* We've launched the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) in beta, a feature that allows you to connect to remote MCP servers directly from the Messages API.
666* To increase answer quality and decrease tool errors, we've changed the default value for the `top_p` [nucleus sampling](https://en.wikipedia.org/wiki/Top-p_sampling) parameter in the Messages API from 0.999 to 0.99 for all models. To revert this change, set `top_p` to 0.999. Additionally, when extended thinking is enabled, you can now set `top_p` to values between 0.95 and 1.
660* We’ve launched [Claude Opus 4 and Claude Sonnet 4](https://www.anthropic.com/news/claude-4), our latest models with extended thinking capabilities. Learn more in [Models overview](https://platform.claude.com/docs/en/models/overview).
661* The default behavior of [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) in Claude 4 models returns a summary of Claude’s full thinking process, with the full thinking encrypted and returned in the `signature` field of `thinking` block output.
662* We’ve launched [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking) in beta, a feature that enables Claude to think in between tool calls. To enable interleaved thinking, use the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `interleaved-thinking-2025-05-14`.
663* We’ve launched the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) in beta, enabling you to upload files and reference them in the Messages API and code execution tool.
664* We’ve launched the [Code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) in beta, a tool that enables Claude to execute Python code in a secure, sandboxed environment.
665* We’ve launched the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) in beta, a feature that allows you to connect to remote MCP servers directly from the Messages API.
666* To increase answer quality and decrease tool errors, we’ve changed the default value for the `top_p` [nucleus sampling](https://en.wikipedia.org/wiki/Top-p_sampling) parameter in the Messages API from 0.999 to 0.99 for all models. To revert this change, set `top_p` to 0.999. Additionally, when extended thinking is enabled, you can now set `top_p` to values between 0.95 and 1.
667667* Our [Go SDK](https://github.com/anthropics/anthropic-sdk-go) has moved from beta to its first stable release.
668* We've added minute and hour level granularity to the [Usage](https://console.anthropic.com/settings/usage) page of Console alongside 429 error rates on the Usage page.
668* We’ve added minute and hour level granularity to the [Usage](https://console.anthropic.com/settings/usage) page of Console alongside 429 error rates on the Usage page.
669669
670670### May 21, 2025
671671
from line 673
673673
674674### May 7, 2025
675675
676* We've launched a web search tool in the API, allowing Claude to access up-to-date information from the web. Learn more in [Web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool).
676* We’ve launched a web search tool in the API, allowing Claude to access up-to-date information from the web. Learn more in [Web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool).
677677
678678### May 1, 2025
679679
from line 686
686686### March 31st, 2025
687687
688688* Our [Java SDK](https://github.com/anthropics/anthropic-sdk-java) has moved from beta to its first stable release.
689* We've moved our [Go SDK](https://github.com/anthropics/anthropic-sdk-go) from alpha to beta.
689* We’ve moved our [Go SDK](https://github.com/anthropics/anthropic-sdk-go) from alpha to beta.
690690
691691### February 27th, 2025
692692
693* We've added URL source blocks for images and PDFs in the Messages API. You can now reference images and PDFs directly through a URL instead of having to base64-encode them. Learn more in [Vision](https://platform.claude.com/docs/en/build-with-claude/vision) and [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support).
694* We've added support for a `none` option to the `tool_choice` parameter in the Messages API that prevents Claude from calling any tools. Additionally, you're no longer required to provide any `tools` when including `tool_use` and `tool_result` blocks.
695* We've launched an OpenAI-compatible API endpoint, allowing you to test Claude models by changing just your API key, base URL, and model name in existing OpenAI integrations. This compatibility layer supports core chat completions functionality. Learn more in [OpenAI SDK compatibility](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk).
693* We’ve added URL source blocks for images and PDFs in the Messages API. You can now reference images and PDFs directly through a URL instead of having to base64-encode them. Learn more in [Vision](https://platform.claude.com/docs/en/build-with-claude/vision) and [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support).
694* We’ve added support for a `none` option to the `tool_choice` parameter in the Messages API that prevents Claude from calling any tools. Additionally, you’re no longer required to provide any `tools` when including `tool_use` and `tool_result` blocks.
695* We’ve launched an OpenAI-compatible API endpoint, allowing you to test Claude models by changing just your API key, base URL, and model name in existing OpenAI integrations. This compatibility layer supports core chat completions functionality. Learn more in [OpenAI SDK compatibility](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk).
696696
697697### February 24th, 2025
698698
699* We've launched [Claude Sonnet 3.7](https://www.anthropic.com/news/claude-3-7-sonnet), our most intelligent model yet. Claude Sonnet 3.7 can produce near-instant responses or show its extended thinking step-by-step. One model, two ways to think. Learn more about all Claude models in [Models overview](https://platform.claude.com/docs/en/models/overview).
699* We’ve launched [Claude Sonnet 3.7](https://www.anthropic.com/news/claude-3-7-sonnet), our most intelligent model yet. Claude Sonnet 3.7 can produce near-instant responses or show its extended thinking step-by-step. One model, two ways to think. Learn more about all Claude models in [Models overview](https://platform.claude.com/docs/en/models/overview).
700700
701* We've added vision support to Claude Haiku 3.5, enabling the model to analyze and understand images.
701* We’ve added vision support to Claude Haiku 3.5, enabling the model to analyze and understand images.
702702
703* We've released a token-efficient tool use implementation, improving overall performance when using tools with Claude. Learn more in [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
703* We’ve released a token-efficient tool use implementation, improving overall performance when using tools with Claude. Learn more in [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
704704
705* We've changed the default temperature in the [Console](https://console.anthropic.com/workbench) for new prompts from 0 to 1 for consistency with the default temperature in the API. Existing saved prompts are unchanged.
705* We’ve changed the default temperature in the [Console](https://console.anthropic.com/workbench) for new prompts from 0 to 1 for consistency with the default temperature in the API. Existing saved prompts are unchanged.
706706
707* We've released updated versions of our tools that decouple the text edit and bash tools from the computer use system prompt:
707* We’ve released updated versions of our tools that decouple the text edit and bash tools from the computer use system prompt:
708708
709709 * `bash_20250124`: Same functionality as previous version but is independent from computer use. Does not require a beta header.
710710 * `text_editor_20250124`: Same functionality as previous version but is independent from computer use. Does not require a beta header.
711 * `computer_20250124`: Updated computer use tool with new command options including "hold\_key", "left\_mouse\_down", "left\_mouse\_up", "scroll", "triple\_click", and "wait". This tool requires the "computer-use-2025-01-24" anthropic-beta header. Learn more in [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
711 * `computer_20250124`: Updated computer use tool with new command options including `hold_key`, `left_mouse_down`, `left_mouse_up`, `scroll`, `triple_click`, and `wait`. This tool requires the `computer-use-2025-01-24` anthropic-beta header. Learn more in [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
712712
713713### February 10th, 2025
714714
715* We've added the `anthropic-organization-id` response header to all API responses. This header provides the organization ID associated with the API key used in the request.
715* We’ve added the `anthropic-organization-id` response header to all API responses. This header provides the organization ID associated with the API key used in the request.
716716
717717### January 31st, 2025
718718
719* We've moved our [Java SDK](https://github.com/anthropics/anthropic-sdk-java) from alpha to beta.
719* We’ve moved our [Java SDK](https://github.com/anthropics/anthropic-sdk-java) from alpha to beta.
720720
721721### January 23rd, 2025
722722
723* We've launched citations capability in the API, allowing Claude to provide source attribution for information. Learn more in [Citations](https://platform.claude.com/docs/en/build-with-claude/citations).
724* We've added support for plain text documents and custom content documents in the Messages API.
723* We’ve launched citations capability in the API, allowing Claude to provide source attribution for information. Learn more in [Citations](https://platform.claude.com/docs/en/build-with-claude/citations).
724* We’ve added support for plain text documents and custom content documents in the Messages API.
725725
726726### January 21st, 2025
727727
from line 729
729729
730730### January 15th, 2025
731731
732* We've updated [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) to be easier to use. Now, when you set a cache breakpoint, we'll automatically read from your longest previously cached prefix.
733* You can now put words in Claude's mouth when using tools.
732* We’ve updated [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) to be easier to use. Now, when you set a cache breakpoint, we’ll automatically read from your longest previously cached prefix.
733* You can now put words in Claude’s mouth when using tools.
734734
735735### January 10th, 2025
736736
737* We've optimized support for [prompt caching in the Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#using-prompt-caching-with-message-batches) to improve cache hit rate.
737* We’ve optimized support for [prompt caching in the Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#using-prompt-caching-with-message-batches) to improve cache hit rate.
738738
739739### December 19th, 2024
740740
741* We've added support for a [delete endpoint](https://platform.claude.com/docs/en/api/messages/batches/delete) in the Message Batches API.
741* We’ve added support for a [delete endpoint](https://platform.claude.com/docs/en/api/messages/batches/delete) in the Message Batches API.
742742
743743### December 17th, 2024
744744
from line 757
757757
758758### December 4th, 2024
759759
760* We've added the ability to group by API key on the [Usage](https://console.anthropic.com/settings/usage) and [Cost](https://console.anthropic.com/settings/cost) pages of the [Developer Console](https://console.anthropic.com).
761* We've added two new **Last used at** and **Cost** columns and the ability to sort by any column on the [API keys](https://console.anthropic.com/settings/keys) page of the [Developer Console](https://console.anthropic.com).
760* We’ve added the ability to group by API key on the [Usage](https://console.anthropic.com/settings/usage) and [Cost](https://console.anthropic.com/settings/cost) pages of the [Developer Console](https://console.anthropic.com).
761* We’ve added two new **Last used at** and **Cost** columns and the ability to sort by any column on the [API keys](https://console.anthropic.com/settings/keys) page of the [Developer Console](https://console.anthropic.com).
762762
763763### November 21st, 2024
764764
765* We've released the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api), allowing users to programmatically manage their organization's resources.
765* We’ve released the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api), allowing users to programmatically manage their organization’s resources.
766766
767767### November 20th, 2024
768768
769* 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).
770* 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).
769* 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).
770* 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).
771771
772772### November 13th, 2024
773773
774* We've added PDF support for all Claude Sonnet 3.5 models. Read more in [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support).
774* We’ve added PDF support for all Claude Sonnet 3.5 models. Read more in [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support).
775775
776776### November 6th, 2024
777777
778* We've retired the Claude 1 and Instant models. Read more in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
778* We’ve retired the Claude 1 and Instant models. Read more in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
779779
780780### November 4th, 2024
781781
from line 783
783783
784784### November 1st, 2024
785785
786* We've added PDF support for use with the new Claude Sonnet 3.5. Read more in [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support).
787* We've also added token counting, which allows you to determine the total number of tokens in a Message prior to sending it to Claude. Read more in [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting).
786* We’ve added PDF support for use with the new Claude Sonnet 3.5. Read more in [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support).
787* We’ve also added token counting, which allows you to determine the total number of tokens in a Message prior to sending it to Claude. Read more in [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting).
788788
789789### October 22nd, 2024
790790
791* We've added Anthropic-defined computer use tools to our API for use with the new Claude Sonnet 3.5. Read more in [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool).
791* We’ve added Anthropic-defined computer use tools to our API for use with the new Claude Sonnet 3.5. Read more in [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool).
792792* Claude Sonnet 3.5, our most intelligent model yet, just got an upgrade and is now available on the Claude API. Read more in the [Claude Sonnet documentation](https://www.anthropic.com/claude/sonnet).
793793
794794### October 8th, 2024
795795
796796* The Message Batches API is now available in beta. Process large batches of queries asynchronously in the Claude API for 50% less cost. Read more in [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing).
797* We've loosened restrictions on the ordering of `user`/`assistant` turns in our Messages API. Consecutive `user`/`assistant` messages will be combined into a single message instead of erroring, and we no longer require the first input message to be a `user` message.
798* We've deprecated the Build and Scale plans in favor of a standard feature suite (formerly referred to as Build), along with additional features that are available through sales. Read more in our [API pricing information](https://claude.com/platform/api).
797* We’ve loosened restrictions on the ordering of `user`/`assistant` turns in our Messages API. Consecutive `user`/`assistant` messages will be combined into a single message instead of erroring, and we no longer require the first input message to be a `user` message.
798* We’ve deprecated the Build and Scale plans in favor of a standard feature suite (formerly referred to as Build), along with additional features that are available through sales. Read more in our [API pricing information](https://claude.com/platform/api).
799799
800800### October 3rd, 2024
801801
802* We've added the ability to disable parallel tool use in the API. Set `disable_parallel_tool_use: true` in the `tool_choice` field to ensure that Claude uses at most one tool. Read more in [Parallel tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use).
802* We’ve added the ability to disable parallel tool use in the API. Set `disable_parallel_tool_use: true` in the `tool_choice` field to ensure that Claude uses at most one tool. Read more in [Parallel tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use).
803803
804804### September 10th, 2024
805805
806* We've added Workspaces to the [Developer Console](https://console.anthropic.com). Workspaces allow you to set custom spend or rate limits, group API keys, track usage by project, and control access with user roles. Read more in our [Workspaces blog post](https://www.anthropic.com/news/workspaces).
806* We’ve added Workspaces to the [Developer Console](https://console.anthropic.com). Workspaces allow you to set custom spend or rate limits, group API keys, track usage by project, and control access with user roles. Read more in our [Workspaces blog post](https://www.anthropic.com/news/workspaces).
807807
808808### September 4th, 2024
809809
from line 811
811811
812812### August 22nd, 2024
813813
814* We've added support for usage of the SDK in browsers by returning CORS headers in the API responses. Set `dangerouslyAllowBrowser: true` in the SDK instantiation to enable this feature.
814* We’ve added support for usage of the SDK in browsers by returning CORS headers in the API responses. Set `dangerouslyAllowBrowser: true` in the SDK instantiation to enable this feature.
815815
816816### August 19th, 2024
817817
test-and-evaluate/develop-tests Changed · +18 / -18 lines
from line 14
1414
1515Good success criteria are:
1616
17* **Specific:** Clearly define what you want to achieve. Instead of "good performance," specify "accurate sentiment classification."
17* **Specific:** Clearly define what you want to achieve. Instead of “good performance,” specify “accurate sentiment classification.”
1818
1919* **Measurable:** Use quantitative metrics or well-defined qualitative scales. Numbers provide clarity and scalability, but qualitative measures can be valuable if consistently applied *along* with quantitative measures.
2020
21 * Even "hazy" topics such as ethics and safety can be quantified:
21 * Even “hazy” topics such as ethics and safety can be quantified:
2222
2323 | | Safety criteria |
2424 | ---- | ------------------------------------------------------------------------------------------ |
from line 40
4040
4141 **Qualitative scales:**
4242
43 * Likert scales: "Rate coherence from 1 (nonsensical) to 5 (perfectly logical)"
43 * Likert scales: “Rate coherence from 1 (nonsensical) to 5 (perfectly logical)”
4444 * Expert rubrics: Linguists rating translation quality on defined criteria
4545 </Accordion>
4646
4747* **Achievable:** Base your targets on industry benchmarks, prior experiments, AI research, or expert knowledge. Your success metrics should not be unrealistic to current frontier model capabilities.
4848
49* **Relevant:** Align your criteria with your application's purpose and user needs. Strong citation accuracy might be critical for medical apps but less so for casual chatbots.
49* **Relevant:** Align your criteria with your application’s purpose and user needs. Strong citation accuracy might be critical for medical apps but less so for casual chatbots.
5050
5151<Accordion title="Example task fidelity criteria for sentiment analysis">
5252 | | Criteria |
from line 67
6767 </Accordion>
6868
6969 <Accordion title="Consistency">
70 How similar do the model's responses need to be for similar types of input? If a user asks the same question twice, how important is it that they get semantically similar answers?
70 How similar do the model’s responses need to be for similar types of input? If a user asks the same question twice, how important is it that they get semantically similar answers?
7171 </Accordion>
7272
7373 <Accordion title="Relevance and coherence">
74 How well does the model directly address the user's questions or instructions? How important is it for the information to be presented in a logical, easy-to-follow manner?
74 How well does the model directly address the user’s questions or instructions? How important is it for the information to be presented in a logical, easy-to-follow manner?
7575 </Accordion>
7676
7777 <Accordion title="Tone and style">
78 How well does the model's output style match expectations? How appropriate is its language for the target audience?
78 How well does the model’s output style match expectations? How appropriate is its language for the target audience?
7979 </Accordion>
8080
8181 <Accordion title="Privacy preservation">
from line 87
8787 </Accordion>
8888
8989 <Accordion title="Latency">
90 What is the acceptable response time for the model? This depends on your application's real-time requirements and user expectations.
90 What is the acceptable response time for the model? This depends on your application’s real-time requirements and user expectations.
9191 </Accordion>
9292
9393 <Accordion title="Price">
from line 103
103103 | Bad | The model should classify sentiments well |
104104 | Good | On a held-out test set of 10,000 diverse Twitter posts, the sentiment analysis model should achieve:<br />- an F1 score of at least 0.85<br />- 99.5% non-toxic outputs<br />- 90% of errors would cause inconvenience, not egregious error\*<br />- 95% response time \< 200ms |
105105
106 \*In reality, you would also define what "inconvenience" and "egregious" mean.
106 \*In reality, you would also define what “inconvenience” and “egregious” mean.
107107</Accordion>
108108
109109***
from line 112
112112
113113### Eval design principles
114114
1151. **Be task-specific:** Design evals that mirror your real-world task distribution. Don't forget to factor in edge cases!
1151. **Be task-specific:** Design evals that mirror your real-world task distribution. Don’t forget to factor in edge cases!
116116 <Accordion title="Example edge cases">
117117 * Irrelevant or nonexistent input data
118118 * Overly long input data or user input
from line 126
126126
127127<AccordionGroup>
128128 <Accordion title="Task fidelity (sentiment analysis): exact match evaluation">
129 **What it measures:** Exact match evals measure whether the model's output matches a predefined correct answer, typically after normalizing whitespace and case. It's a simple, unambiguous metric that's perfect for tasks with clear-cut, categorical answers such as sentiment analysis (positive, negative, neutral).
129 **What it measures:** Exact match evals measure whether the model’s output matches a predefined correct answer, typically after normalizing whitespace and case. It’s a simple, unambiguous metric that’s perfect for tasks with clear-cut, categorical answers such as sentiment analysis (positive, negative, neutral).
130130
131131 **Example eval test cases:** 1,000 tweets with human-labeled sentiments.
132132
from line 488
488488 </Accordion>
489489
490490 <Accordion title="Consistency (FAQ bot): cosine similarity evaluation">
491 **What it measures:** Cosine similarity measures the similarity between two vectors (in this case, sentence embeddings of the model's output using [Sentence-BERT (SBERT)](https://sbert.net/)) by computing the cosine of the angle between them. Values closer to 1 indicate higher similarity. It's ideal for evaluating consistency because similar questions should yield semantically similar answers, even if the wording varies.
491 **What it measures:** Cosine similarity measures the similarity between two vectors (in this case, sentence embeddings of the model’s output using [Sentence-BERT (SBERT)](https://sbert.net/)) by computing the cosine of the angle between them. Values closer to 1 indicate higher similarity. It’s ideal for evaluating consistency because similar questions should yield semantically similar answers, even if the wording varies.
492492
493493 **Example eval test cases:** 50 groups with a few paraphrased versions each.
494494
from line 1561
15611561 </Accordion>
15621562
15631563 <Accordion title="Tone and style (customer service): LLM-based Likert scale">
1564 **What it measures:** The LLM-based Likert scale is a psychometric scale that uses an LLM to judge subjective attitudes or perceptions. Here, it's used to rate the tone of responses on a scale from 1 to 5. It's ideal for evaluating nuanced aspects such as empathy, professionalism, or patience that are difficult to quantify with traditional metrics.
1564 **What it measures:** The LLM-based Likert scale is a psychometric scale that uses an LLM to judge subjective attitudes or perceptions. Here, it’s used to rate the tone of responses on a scale from 1 to 5. It’s ideal for evaluating nuanced aspects such as empathy, professionalism, or patience that are difficult to quantify with traditional metrics.
15651565
15661566 **Example eval test cases:** 100 customer inquiries with target tone (empathetic, patient, professional).
15671567
from line 2032
20322032 </Accordion>
20332033
20342034 <Accordion title="Privacy preservation (medical chatbot): LLM-based binary classification">
2035 **What it measures:** Binary classification determines if an input belongs to one of two classes. Here, it's used to classify whether a response contains PHI. This method can account for context and identify subtle or implicit forms of PHI that rule-based systems might miss.
2035 **What it measures:** Binary classification determines if an input belongs to one of two classes. Here, it’s used to classify whether a response contains PHI. This method can account for context and identify subtle or implicit forms of PHI that rule-based systems might miss.
20362036
20372037 **Example eval test cases:** 500 simulated patient queries, some with PHI.
20382038
from line 2585
25852585 </Accordion>
25862586
25872587 <Accordion title="Context utilization (conversation assistant): LLM-based ordinal scale">
2588 **What it measures:** Similar to the Likert scale, the ordinal scale measures on a fixed, ordered scale (1–5). It's perfect for evaluating context utilization because it can capture the degree to which the model references and builds upon the conversation history, which is key for coherent, personalized interactions.
2588 **What it measures:** Similar to the Likert scale, the ordinal scale measures on a fixed, ordered scale (1–5). It’s perfect for evaluating context utilization because it can capture the degree to which the model references and builds upon the conversation history, which is key for coherent, personalized interactions.
25892589
25902590 **Example eval test cases:** 100 multi-turn conversations with context-dependent questions.
25912591
from line 3216
32163216</Tip>
32173217
32183218<Tip>
3219 If you don't know what eval methods might be useful to assess for your success criteria, you can also brainstorm with Claude!
3219 If you don’t know what eval methods might be useful to assess for your success criteria, you can also brainstorm with Claude!
32203220</Tip>
32213221
32223222***
from line 3236
32363236
32373237### Tips for LLM-based grading
32383238
3239* **Have detailed, clear rubrics:** "The answer should always mention 'Acme Inc.' in the first sentence. If it does not, the answer is automatically graded as 'incorrect.'"
3239* **Have detailed, clear rubrics:** “The answer should always mention ‘Acme Inc.’ in the first sentence. If it does not, the answer is automatically graded as ‘incorrect.’”
32403240 <Note>
32413241 A given use case, or even a specific success criterion for that use case, might require several rubrics for holistic evaluation.
32423242 </Note>
3243* **Be empirical or specific:** For example, instruct the LLM to output only 'correct' or 'incorrect', or to judge from a scale of 1–5. Purely qualitative evaluations are hard to assess quickly and at scale.
3243* **Be empirical or specific:** For example, instruct the LLM to output only ‘correct’ or ‘incorrect’, or to judge from a scale of 1–5. Purely qualitative evaluations are hard to assess quickly and at scale.
32443244* **Encourage reasoning:** Use a grader model with [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on, so that it reasons before it produces an evaluation score. This increases evaluation performance, particularly for tasks requiring complex judgment.
32453245
32463246<Accordion title="Example: LLM-based grading">
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals Changed · +8 / -8 lines
from line 4
44description: Detect and handle refusal stop reasons in streaming responses, and retry refused requests on a fallback model.
55---
66
7Starting with Claude 4 models, streaming responses from Claude's API return **`stop_reason`: `"refusal"`** when streaming classifiers intervene to handle potential policy violations. This safety feature helps maintain content compliance during real-time streaming.
7Starting with Claude 4 models, streaming responses from Claude’s API return **`stop_reason`: `"refusal"`** when streaming classifiers intervene to handle potential policy violations. This safety feature helps maintain content compliance during real-time streaming.
88
99<Tip>
1010 This page covers how refusals appear in streaming responses. For every `stop_reason` value and how to handle it, see [Stop reasons and fallback](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons). To retry refused requests on another Claude model, see [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
from line 12
1212
1313## API response format
1414
15When streaming classifiers detect content that violates Anthropic's policies, the API returns this response:
15When streaming classifiers detect content that violates Anthropic’s policies, the API returns this response:
1616
1717```json
1818{
from line 54
5454
5555## Implementation guide
5656
57Here's how to detect and handle streaming refusals in your application:
57Here’s how to detect and handle streaming refusals in your application:
5858
5959<CodeGroup exclude="shell:cURL, shell:CLI">
6060 <CodeGroupItem language="cURL">
from line 305
305305* **Monitor for refusals:** Include **`stop_reason`: `refusal`** checks in your error handling.
306306* **Reset automatically:** Implement automatic context reset when refusals are detected.
307307* **Fall back to another model:** Configure [server-side fallback or the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) so refused requests are retried on another Claude model instead of surfacing a refusal to the user. Claude Haiku 5.5 has no server-side fallback, so set up its retry in your client.
308* **Redeem fallback credit on manual retries:** If you build the retry yourself, pass the refusal's [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) token so the retry doesn't pay the prompt-cache cost twice. Claude Haiku 5.5 refusals carry no fallback credit.
308* **Redeem fallback credit on manual retries:** If you build the retry yourself, pass the refusal’s [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) token so the retry doesn’t pay the prompt-cache cost twice. Claude Haiku 5.5 refusals carry no fallback credit.
309309* **Provide custom messaging:** Create user-friendly messages for better UX when refusals occur.
310310* **Track refusal patterns:** Monitor refusal frequency to identify potential issues with your prompts.
311311
312312## Migration notes
313313
314If you built refusal handling when this feature first shipped, or you're adding it to an existing integration, check the following:
314If you built refusal handling when this feature first shipped, or you’re adding it to an existing integration, check the following:
315315
316* **Refusals are responses, not errors.** A refusal arrives as a successful HTTP 200 response with `stop_reason`: `"refusal"`, so monitoring built only on error rates won't surface it. Track refusals as their own signal.
316* **Refusals are responses, not errors.** A refusal arrives as a successful HTTP 200 response with `stop_reason`: `"refusal"`, so monitoring built only on error rates won’t surface it. Track refusals as their own signal.
317317* **Refusals include structured detail.** On every model, a refusal also includes a `stop_details` object that identifies the policy category behind the decline. See [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the full response shape.
318318* **Retry on a different model.** Re-sending a refused request to the same model usually results in another refusal. Instead of only resetting context, retry on a fallback model with [server-side fallback, the SDK middleware, or a manual retry](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback), and redeem [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) when you build the retry yourself. Claude Haiku 5.5 has no server-side fallback, and its refusals carry no fallback credit, so set up its retry in your client.
319319* **Check batch results for refusals.** A refused request in a [Message Batch](https://platform.claude.com/docs/en/build-with-claude/batch-processing) is returned as a succeeded result with `stop_reason`: `"refusal"`, not as an errored result.
from line 335
335335 </Card>
336336
337337 <Card title="Multilingual support" icon="text-aa" href="https://platform.claude.com/docs/en/build-with-claude/multilingual-support">
338 Serve users across languages with Claude's cross-lingual capabilities.
338 Serve users across languages with Claude’s cross-lingual capabilities.
339339 </Card>
340340</CardGroup>
341341
test-and-evaluate/strengthen-guardrails/increase-consistency Changed · +7 / -7 lines
## Prefill Claude’s response ## Prefill Claude's response
from line 12
1212 The techniques below are useful for general output consistency or when you need flexibility beyond strict JSON schemas.
1313</Tip>
1414
15Here's how to make Claude's responses more consistent:
15Here’s how to make Claude’s responses more consistent:
1616
1717## Specify the output format you want
1818
from line 55
5555 ```
5656</Accordion>
5757
58## Prefill Claude's response
58## Prefill Claude’s response
5959
6060<Note>
6161 Prefilling is not supported on Claude 4.6 and later models and
from line 69
6969 on models that support it, or system prompt instructions, instead.
7070</Note>
7171
72Prefill the `Assistant` turn with the format you want. This trick bypasses Claude's friendly preamble and enforces your structure.
72Prefill the `Assistant` turn with the format you want. This trick bypasses Claude’s friendly preamble and enforces your structure.
7373
7474<Accordion title="Example: Daily sales report">
7575 ```text User wrap
from line 249
249249
250250## Use retrieval for contextual consistency
251251
252For tasks requiring consistent context (for example, chatbots, knowledge bases), use retrieval to ground Claude's responses in a fixed information set.
252For tasks requiring consistent context (for example, chatbots, knowledge bases), use retrieval to ground Claude’s responses in a fixed information set.
253253
254254<Accordion title="Example: Enhancing IT support consistency">
255255 ```text User wrap
from line 322
322322
323323For role-based applications, maintaining consistent character requires deliberate prompting.
324324
325* **Use system prompts to set the role:** Use [system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role) to define Claude's role and personality. This sets a strong foundation for consistent responses.
325* **Use system prompts to set the role:** Use [system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role) to define Claude’s role and personality. This sets a strong foundation for consistent responses.
326326 <Tip>
327 When setting up the character, provide detailed information about the personality, background, and any specific traits or quirks. This helps the model better emulate and generalize the character's traits.
327 When setting up the character, provide detailed information about the personality, background, and any specific traits or quirks. This helps the model better emulate and generalize the character’s traits.
328328 </Tip>
329* **Prepare Claude for possible scenarios:** Provide a list of common scenarios and expected responses in your prompts. This "trains" Claude to handle diverse situations without breaking character.
329* **Prepare Claude for possible scenarios:** Provide a list of common scenarios and expected responses in your prompts. This “trains” Claude to handle diverse situations without breaking character.
330330
331331<Accordion title="Example: Enterprise chatbot for role prompting">
332332 ```text System wrap
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks Changed · +15 / -15 lines
from line 4
44description: Defend your application against jailbreaks and prompt injection with input screening, hardened system prompts, and safe handling of untrusted tool content.
55---
66
7Jailbreaking and prompt injection are attempts to make Claude ignore its guidelines or your instructions. Although Claude is inherently resilient to such attacks, the additional steps on this page strengthen your guardrails, particularly against uses that violate Anthropic's [Terms of Service](https://www.anthropic.com/legal/commercial-terms) or [Usage Policy](https://www.anthropic.com/legal/aup).
7Jailbreaking and prompt injection are attempts to make Claude ignore its guidelines or your instructions. Although Claude is inherently resilient to such attacks, the additional steps on this page strengthen your guardrails, particularly against uses that violate Anthropic’s [Terms of Service](https://www.anthropic.com/legal/commercial-terms) or [Usage Policy](https://www.anthropic.com/legal/aup).
88
99These attacks fall into two categories with different threat models:
1010
from line 13
1313
1414## Jailbreaks and direct prompt injection
1515
16In this threat model, a user is deliberately crafting inputs to manipulate your application into producing content or taking actions you don't want it to. These mitigations strengthen your application's guardrails:
16In this threat model, a user is deliberately crafting inputs to manipulate your application into producing content or taking actions you don’t want it to. These mitigations strengthen your application’s guardrails:
1717
1818* **Harmlessness screens:** Use a lightweight model such as Claude Haiku 5.5 to pre-screen user input before it reaches your main conversation. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) to constrain the response to a simple classification. Claude Haiku 5.5 runs [safety classifiers](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) that can decline the screening request itself, so treat a response with `stop_reason: "refusal"` as a harmful verdict.
1919
from line 66
6666 ```
6767 </Accordion>
6868
69* **Respond to repeat offenders:** Adjust responses and consider throttling or banning users who repeatedly attempt to circumvent your application's guardrails. For example, if a particular user triggers the same kind of refusal multiple times (such as "output blocked by content filtering policy"), tell the user that their actions violate the relevant usage policies and take action accordingly.
69* **Respond to repeat offenders:** Adjust responses and consider throttling or banning users who repeatedly attempt to circumvent your application’s guardrails. For example, if a particular user triggers the same kind of refusal multiple times (such as “output blocked by content filtering policy”), tell the user that their actions violate the relevant usage policies and take action accordingly.
7070
7171## Indirect prompt injection
7272
73In this threat model, you're protecting your users from instructions embedded in content that Claude reads on their behalf: the body of an inbound email, a fetched webpage, OCR output from an uploaded file, or the result of a tool call. An attacker who can influence that content might embed instructions that try to redirect Claude.
73In this threat model, you’re protecting your users from instructions embedded in content that Claude reads on their behalf: the body of an inbound email, a fetched webpage, OCR output from an uploaded file, or the result of a tool call. An attacker who can influence that content might embed instructions that try to redirect Claude.
7474
7575Structure your application so that Claude can reliably distinguish untrusted content from your instructions:
7676
7777* **Put untrusted content only in tool results.** Deliver third-party content to Claude inside `tool_result` blocks, never in `system` prompts or plain user `text` blocks. Claude is trained to treat instructions that appear inside tool results with appropriate skepticism. See [Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls) for the `tool_result` format.
7878
79* **Tell Claude what the content is and where it came from.** In the tool's `description`, or in the structure of the result itself, make the nature and source of the content explicit: for example, that it is the body of an inbound email from an unknown sender, or OCR text extracted from a user-uploaded image. This context helps Claude calibrate how much to trust embedded directives.
79* **Tell Claude what the content is and where it came from.** In the tool’s `description`, or in the structure of the result itself, make the nature and source of the content explicit: for example, that it is the body of an inbound email from an unknown sender, or OCR text extracted from a user-uploaded image. This context helps Claude calibrate how much to trust embedded directives.
8080
81* **State the policy in your system prompt.** Tell Claude explicitly that content returned from tools, documents, or searches is untrusted data and must never override the system prompt or the user's original request.
81* **State the policy in your system prompt.** Tell Claude explicitly that content returned from tools, documents, or searches is untrusted data and must never override the system prompt or the user’s original request.
8282
8383 <Accordion title="Example: System prompt guidance for a document-processing agent">
8484 ```text System wrap
from line 92
9292 ```
9393 </Accordion>
9494
95* **JSON-encode untrusted content.** Where possible, wrap third-party strings in a JSON object rather than concatenating them into free-form text. JSON escaping provides unambiguous delimiters between the untrusted payload and the surrounding structure, so an attacker cannot close a quote or tag to "break out" into an instruction context.
95* **JSON-encode untrusted content.** Where possible, wrap third-party strings in a JSON object rather than concatenating them into free-form text. JSON escaping provides unambiguous delimiters between the untrusted payload and the surrounding structure, so an attacker cannot close a quote or tag to “break out” into an instruction context.
9696
9797 <Accordion title="Example: JSON-encoded tool result for an inbound email">
9898 ```json
from line 111
111111 The email body is a JSON string inside a JSON object. Even though it contains text that looks like an instruction, the encoding makes it unambiguous that this is data, not a directive.
112112 </Accordion>
113113
114* **Don't put your own instructions in tool results.** Because Claude treats tool-result content as untrusted data, instructions you place there might be ignored or flagged as a potential injection. Send your instructions in a `user` turn that follows the `tool_result` block. On supported models, you can also use a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
114* **Don’t put your own instructions in tool results.** Because Claude treats tool-result content as untrusted data, instructions you place there might be ignored or flagged as a potential injection. Send your instructions in a `user` turn that follows the `tool_result` block. On supported models, you can also use a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
115115
116* **Limit Claude's access to sensitive data and actions.** Apply the principle of least privilege so that a successful injection can do minimal damage: don't give Claude access to secrets it doesn't need, run tools in sandboxed environments, and scope permissions as narrowly as possible.
116* **Limit Claude’s access to sensitive data and actions.** Apply the principle of least privilege so that a successful injection can do minimal damage: don’t give Claude access to secrets it doesn’t need, run tools in sandboxed environments, and scope permissions as narrowly as possible.
117117
118* **Screen tool outputs before Claude acts on them.** Apply the same lightweight-model screening pattern you use for user input to the content your tools return. Run each tool, pass its raw output to a small classifier call with Claude Haiku 5.5, and only return the content as a `tool_result` block if the screen reports no injection attempt. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) so the classifier's verdict is a parseable value your application can branch on.
118* **Screen tool outputs before Claude acts on them.** Apply the same lightweight-model screening pattern you use for user input to the content your tools return. Run each tool, pass its raw output to a small classifier call with Claude Haiku 5.5, and only return the content as a `tool_result` block if the screen reports no injection attempt. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) so the classifier’s verdict is a parseable value your application can branch on.
119119
120120 <Accordion title="Example: Injection screen for tool output">
121121 ```text User wrap
from line 155
155155* **Red-team your own agent.** Before deploying, test your workflow with documents, emails, and tool outputs that deliberately contain injection attempts, and confirm that Claude ignores them and that your screening and confirmation steps catch the rest.
156156
157157<Note>
158 If you're using the
158 If you’re using the
159159
160160 [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool)
161161
from line 172
172172
173173## Advanced: Chain safeguards
174174
175Combine strategies for robust protection. Here's an enterprise-grade example with tool use:
175Combine strategies for robust protection. Here’s an enterprise-grade example with tool use:
176176
177177<Accordion title="Example: Multilayered protection for a financial advisor chatbot">
178178 ### Bot system prompt
test-and-evaluate/strengthen-guardrails/reduce-hallucinations Changed · +5 / -5 lines
from line 4
44description: Minimize hallucinations in Claude's outputs by allowing uncertainty, grounding responses in direct quotes, and verifying claims with citations.
55---
66
7Even the most advanced language models, such as Claude, can sometimes generate text that is factually incorrect or inconsistent with the given context. This phenomenon, known as "hallucination," can undermine the reliability of your AI-driven solutions. This guide explores techniques to minimize hallucinations and ensure Claude's outputs are accurate and trustworthy.
7Even the most advanced language models, such as Claude, can sometimes generate text that is factually incorrect or inconsistent with the given context. This phenomenon, known as “hallucination,” can undermine the reliability of your AI-driven solutions. This guide explores techniques to minimize hallucinations and ensure Claude’s outputs are accurate and trustworthy.
88
99## Basic hallucination minimization strategies
1010
11* **Allow Claude to say "I don't know":** Explicitly give Claude permission to admit uncertainty. This technique can drastically reduce false information.
11* **Allow Claude to say “I don’t know”:** Explicitly give Claude permission to admit uncertainty. This technique can drastically reduce false information.
1212
1313<Accordion title="Example: Analyzing a merger and acquisition report">
1414 ```text User wrap
from line 37
3737 ```
3838</Accordion>
3939
40* **Verify with citations:** Make Claude's response auditable by having it cite quotes and sources for each of its claims. You can also have Claude verify each claim by finding a supporting quote after it generates a response. If it can't find a quote, it must retract the claim.
40* **Verify with citations:** Make Claude’s response auditable by having it cite quotes and sources for each of its claims. You can also have Claude verify each claim by finding a supporting quote after it generates a response. If it can’t find a quote, it must retract the claim.
4141
4242<Accordion title="Example: Drafting a press release on a product launch">
4343 ```text User wrap
from line 58
5858
5959* **Best-of-N verification:** Run Claude through the same prompt multiple times and compare the outputs. Inconsistencies across outputs could indicate hallucinations.
6060
61* **Iterative refinement:** Use Claude's outputs as inputs for follow-up prompts, asking it to verify or expand on previous statements. This can catch and correct inconsistencies.
61* **Iterative refinement:** Use Claude’s outputs as inputs for follow-up prompts, asking it to verify or expand on previous statements. This can catch and correct inconsistencies.
6262
6363* **External knowledge restriction:** Explicitly instruct Claude to only use information from provided documents and not its general knowledge.
6464
6565<Note>
66 Remember, although these techniques significantly reduce hallucinations, they don't eliminate them entirely. Always validate critical information, especially for high-stakes decisions.
66 Remember, although these techniques significantly reduce hallucinations, they don’t eliminate them entirely. Always validate critical information, especially for high-stakes decisions.
6767</Note>
6868
test-and-evaluate/strengthen-guardrails/reduce-latency Changed · +7 / -7 lines
from line 7
77Latency refers to the time it takes for the model to process a prompt and generate an output. Latency can be influenced by various factors, such as the size of the model, the complexity of the prompt, and the underlying infrastructure supporting the model and point of interaction.
88
99<Note>
10 It's always better to first engineer a prompt that works well without model or prompt constraints, and then try latency reduction strategies afterward. Trying to reduce latency prematurely might prevent you from discovering what top performance looks like.
10 It’s always better to first engineer a prompt that works well without model or prompt constraints, and then try latency reduction strategies afterward. Trying to reduce latency prematurely might prevent you from discovering what top performance looks like.
1111</Note>
1212
1313***
from line 16
1616
1717When discussing latency, you might come across several terms and measurements:
1818
19* **Baseline latency:** This is the time taken by the model to process the prompt and generate the response, without considering the input and output tokens per second. It provides a general idea of the model's speed.
20* **Time to first token (TTFT):** This metric measures the time it takes for the model to generate the first token of the response, from when the prompt was sent. It's particularly relevant when you're using streaming (more on that later) and want to provide a responsive experience to your users.
19* **Baseline latency:** This is the time taken by the model to process the prompt and generate the response, without considering the input and output tokens per second. It provides a general idea of the model’s speed.
20* **Time to first token (TTFT):** This metric measures the time it takes for the model to generate the first token of the response, from when the prompt was sent. It’s particularly relevant when you’re using streaming (more on that later) and want to provide a responsive experience to your users.
2121
2222For a more in-depth understanding of these terms, see the [glossary](https://platform.claude.com/docs/en/about-claude/glossary).
2323
from line 226
226226
227227### 3. Stream responses
228228
229Streaming is a feature that allows the model to start sending back its response before the full output is complete. This can significantly improve the perceived responsiveness of your application, as users can see the model's output in real time.
229Streaming is a feature that allows the model to start sending back its response before the full output is complete. This can significantly improve the perceived responsiveness of your application, as users can see the model’s output in real time.
230230
231With streaming enabled, you can process the model's output as it arrives, updating your user interface or performing other tasks in parallel.
231With streaming enabled, you can process the model’s output as it arrives, updating your user interface or performing other tasks in parallel.
232232
233233Visit [Streaming messages](https://platform.claude.com/docs/en/build-with-claude/streaming) to learn about how you can implement streaming for your use case.
234234
from line 238
238238
239239<CardGroup cols={2}>
240240 <Card title="Reduce hallucinations" icon="shield" href="https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-hallucinations">
241 Minimize hallucinations in Claude's outputs by allowing uncertainty, grounding responses in direct quotes, and verifying claims with citations.
241 Minimize hallucinations in Claude’s outputs by allowing uncertainty, grounding responses in direct quotes, and verifying claims with citations.
242242 </Card>
243243
244244 <Card title="Streaming messages" icon="bolt" href="https://platform.claude.com/docs/en/build-with-claude/streaming">
test-and-evaluate/strengthen-guardrails/reduce-prompt-leak Changed · +5 / -5 lines
from line 4
44description: Reduce the risk of prompt leaks by separating context from user queries, filtering Claude's outputs, and auditing prompts, without degrading task performance.
55---
66
7Prompt leaks can expose sensitive information that you expect to be "hidden" in your prompt. Although no method is foolproof, the following strategies can significantly reduce the risk.
7Prompt leaks can expose sensitive information that you expect to be “hidden” in your prompt. Although no method is foolproof, the following strategies can significantly reduce the risk.
88
99## Before you try to reduce prompt leak
1010
from line 49
4949 ```
5050</Accordion>
5151
52* **Use post-processing:** Filter Claude's outputs for keywords that might indicate a leak. Techniques include using regular expressions, keyword filtering, or other text processing methods.
52* **Use post-processing:** Filter Claude’s outputs for keywords that might indicate a leak. Techniques include using regular expressions, keyword filtering, or other text processing methods.
5353 <Note>
5454 You can also use a prompted LLM to filter outputs for more nuanced leaks.
5555 </Note>
56* **Avoid unnecessary proprietary details:** If Claude doesn't need it to perform the task, don't include it. Extra content reduces Claude's adherence to "no leak" instructions.
57* **Audit regularly:** Periodically review your prompts and Claude's outputs for potential leaks.
56* **Avoid unnecessary proprietary details:** If Claude doesn’t need it to perform the task, don’t include it. Extra content reduces Claude’s adherence to “no leak” instructions.
57* **Audit regularly:** Periodically review your prompts and Claude’s outputs for potential leaks.
5858
59Remember, the goal is not just to prevent leaks but to maintain Claude's performance. Overly complex leak-prevention can degrade results. Balance is key.
59Remember, the goal is not just to prevent leaks but to maintain Claude’s performance. Overly complex leak-prevention can degrade results. Balance is key.
6060
about-claude/model-deprecations Changed · +2 / -2 lines
from line 21
2121 Deprecated models are likely to be less reliable than active models. Move workloads to active models to maintain the highest level of support and reliability.
2222</Warning>
2323
24The dates on this page apply to Anthropic-operated platforms: the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). Partner-operated platforms, Amazon Bedrock and Claude Models on Google Cloud (Google managed), set their own retirement schedules, so a model's lifecycle status and dates can differ. See the [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#supported-models), [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed#api-model-ids) model tables.
24The dates on this page apply to Anthropic-operated platforms: the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). Partner-operated platforms, Amazon Bedrock and Claude Models on Google Cloud (Google managed), set their own retirement schedules, so a model’s lifecycle status and dates can differ. See the [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#supported-models), [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed#api-model-ids) model tables.
2525
2626## Migrating to replacements
2727
from line 33
3333
3434## Notifications
3535
36Anthropic notifies customers with active deployments for models with upcoming retirements, providing at least 60 days' notice before model retirement for publicly released models.
36Anthropic notifies customers with active deployments for models with upcoming retirements, providing at least 60 days’ notice before model retirement for publicly released models.
3737
3838## Auditing model usage
3939
agents-and-tools/remote-mcp-servers Changed · +1 / -1 lines
from line 7
77Several companies have deployed remote MCP servers that developers can connect to by using the Anthropic MCP connector API. These servers expand the capabilities available to developers and end users by providing remote access to various services and tools through the MCP protocol.
88
99<Note>
10 The remote MCP servers listed later on this page are third-party services designed to work with the Claude API. These servers are not owned, operated, or endorsed by Anthropic. Users should only connect to remote MCP servers they trust and should review each server's security practices and terms before connecting.
10 The remote MCP servers listed later on this page are third-party services designed to work with the Claude API. These servers are not owned, operated, or endorsed by Anthropic. Users should only connect to remote MCP servers they trust and should review each server’s security practices and terms before connecting.
1111</Note>
1212
1313## Connecting to remote MCP servers
agents-and-tools/tool-use/fine-grained-tool-streaming Changed · +2 / -2 lines
from line 8
88 To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
99</Note>
1010
11Fine-grained tool streaming delivers a tool's input to your client as Claude generates it, without server-side buffering or JSON validation. Skipping the buffering step reduces the time to the first fragment of a large parameter, such as a document or a block of code, and the fragments arrive through the same [Streaming messages](https://platform.claude.com/docs/en/build-with-claude/streaming) events as standard tool use.
11Fine-grained tool streaming delivers a tool’s input to your client as Claude generates it, without server-side buffering or JSON validation. Skipping the buffering step reduces the time to the first fragment of a large parameter, such as a document or a block of code, and the fragments arrive through the same [Streaming messages](https://platform.claude.com/docs/en/build-with-claude/streaming) events as standard tool use.
1212
1313<Warning>
14 Because the API does not buffer or validate a tool's input before streaming it, you might receive partial or invalid JSON. A response that ends with the [stop reason](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons) `max_tokens` can also cut a parameter off midway. Accumulate the fragments, guard the parse, and see [Handling invalid JSON in tool responses](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#handling-invalid-json-in-tool-responses) for how to return unparseable input to Claude.
14 Because the API does not buffer or validate a tool’s input before streaming it, you might receive partial or invalid JSON. A response that ends with the [stop reason](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons) `max_tokens` can also cut a parameter off midway. Accumulate the fragments, guard the parse, and see [Handling invalid JSON in tool responses](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#handling-invalid-json-in-tool-responses) for how to return unparseable input to Claude.
1515</Warning>
1616
1717## How to use fine-grained tool streaming
api/service-tiers Changed · +2 / -2 lines
from line 20
2020
2121## Priority Tier
2222
23The API prioritizes requests in this tier over all other requests. This prioritization helps minimize ["server overloaded" errors](https://platform.claude.com/docs/en/api/errors#http-errors), even during peak times.
23The API prioritizes requests in this tier over all other requests. This prioritization helps minimize [“server overloaded” errors](https://platform.claude.com/docs/en/api/errors#http-errors), even during peak times.
2424
2525For more information, see [Existing Priority Tier commitments](https://platform.claude.com/docs/en/api/service-tiers#existing-priority-tier-commitments).
2626
from line 183
183183The `service_tier` parameter accepts the following values:
184184
185185* `"auto"` (default) - Uses the Priority Tier capacity if available, falling back to your other capacity if not
186* `"standard_only"` - Uses only standard tier capacity, useful if you don't want to use your Priority Tier capacity
186* `"standard_only"` - Uses only standard tier capacity, useful if you don’t want to use your Priority Tier capacity
187187
188188The response `usage` object also includes the service tier assigned to the request:
189189
api/supported-regions Changed · +1 / -1 lines
from line 40
4040* Comoros
4141* Congo, Republic of the
4242* Costa Rica
43* Côte d'Ivoire
43* Côte d’Ivoire
4444* Croatia
4545* Cyprus
4646* Czechia (Czech Republic)
api/versioning Changed · +2 / -2 lines
from line 26
2626
2727 * [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21) shows how to upgrade.
2828
29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide for API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).
29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it’s available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide for API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).
3030
3131 * Messages API:
3232
from line 40
4040 * [RBAC group members](https://platform.claude.com/docs/en/api/beta/organization/rbac_groups/members/list), and the response to removing one, no longer return `group_id`. Use `rbac_group_id` instead.
4141 * [RBAC roles](https://platform.claude.com/docs/en/api/beta/organization/rbac_roles/list) no longer return `name`. Use `display_name` instead.
4242 * [Organization](https://platform.claude.com/docs/en/api/organization/rate_limits/list) and [workspace](https://platform.claude.com/docs/en/api/organization/workspaces/rate_limits/list) rate-limit entries no longer return `group_type`. Use `group.type` instead.
43 * [API keys](https://platform.claude.com/docs/en/api/organization/api_keys/list) no longer return `workspace_id`. Use `scope.workspace_id` instead, which gives the workspace's real ID even for the Default Workspace (an all-workspaces key has no `workspace_id` in `scope`).
43 * [API keys](https://platform.claude.com/docs/en/api/organization/api_keys/list) no longer return `workspace_id`. Use `scope.workspace_id` instead, which gives the workspace’s real ID even for the Default Workspace (an all-workspaces key has no `workspace_id` in `scope`).
4444
4545 * Claude Enterprise Analytics API:
4646
build-with-claude/compaction-keep-recent-turns Changed · +2 / -2 lines
from line 491
491491* **Picking the cut:** The program keeps the last two turns, where a turn is one `user` message and the reply to it. It splits the history four messages from the end, so the kept turns start with a `user` message.
492492* **Deciding when to compact:** The size check also requires that the conversation has more turns than the program keeps, so the older part is never empty.
493493* **The compaction request:** Where the loop sends the whole history, this version sends only the older messages.
494* **The swap:** Where the loop replaces the whole history with the returned message, this version's new history is the returned message followed by the kept turns.
494* **The swap:** Where the loop replaces the whole history with the returned message, this version’s new history is the returned message followed by the kept turns.
495495
496496The `stop_reason` check and every request after the swap are unchanged from the loop.
497497
from line 499
499499
500500If you send thinking blocks back on a model with [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking), the thinking in the kept turns stays valid only while the [conditions for kept thinking](https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks#conditions-for-kept-thinking-to-stay-valid) hold, and one of them limits where the cut can fall.
501501
502The program's cut, between a reply and the next `user` message, meets that condition. So does a cut at the end of a request you already made: compact exactly that request's `messages`, and keep everything your history has gained since.
502The program’s cut, between a reply and the next `user` message, meets that condition. So does a cut at the end of a request you already made: compact exactly that request’s `messages`, and keep everything your history has gained since.
503503
build-with-claude/extended-thinking Changed · +2 / -2 lines
from line 306
306306
307307How platforms treat the beta header differs. The Claude API and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) accept `interleaved-thinking-2025-05-14` on any model and ignore it where unsupported. Acceptance is not the same as effect: on models that reject `type: "enabled"` (4.7 and later) or lack manual-mode interleaving (Claude Opus 4.6), the header has no manual-mode effect; adaptive thinking interleaves automatically there.
308308
309Partner-operated platforms, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), likewise accept the header on any model without returning an error, and ignore it on models that don't support interleaved thinking.
309Partner-operated platforms, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), likewise accept the header on any model without returning an error, and ignore it on models that don’t support interleaved thinking.
310310
311311## Turn structure in manual mode
312312
from line 384
384384
385385`effort: "high"` is the default on Claude Sonnet 4.6, so omitting it here produces identical behavior; it appears only to show where the depth control lives in adaptive mode. Claude Opus 5.5 and Claude Haiku 5.5 default to `"medium"`, and other models that support effort default to `"high"` (see [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels)).
386386
387Expect a behavioral difference, not just a syntax change. With a fixed budget, Claude thinks on every request. With adaptive thinking, Claude determines whether and how much to think on each request, and at lower [effort](https://platform.claude.com/docs/en/build-with-claude/effort) settings it might skip thinking entirely on easy inputs. You can also remove the `interleaved-thinking-2025-05-14` beta header after migrating: adaptive thinking interleaves automatically, and the Claude API ignores the header on these models. Thinking block preservation changes too: Claude Opus 4.5 and models numbered 4.6 and higher keep prior turns' thinking blocks in context and bill them as input, where Claude Sonnet 4.5 (deprecated), Claude Haiku 4.5, and earlier models strip them; see [thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).
387Expect a behavioral difference, not just a syntax change. With a fixed budget, Claude thinks on every request. With adaptive thinking, Claude determines whether and how much to think on each request, and at lower [effort](https://platform.claude.com/docs/en/build-with-claude/effort) settings it might skip thinking entirely on easy inputs. You can also remove the `interleaved-thinking-2025-05-14` beta header after migrating: adaptive thinking interleaves automatically, and the Claude API ignores the header on these models. Thinking block preservation changes too: Claude Opus 4.5 and models numbered 4.6 and higher keep prior turns’ thinking blocks in context and bill them as input, where Claude Sonnet 4.5 (deprecated), Claude Haiku 4.5, and earlier models strip them; see [thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).
388388
389389Switching modes is a thinking-configuration change, so the first request after the switch invalidates cache breakpoints, as described in [Prompt caching in manual mode](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#extended-thinking-with-prompt-caching).
390390