One read of Claude Developer Platformapi-20260928T183714Z
65 pages moved out of 637 read.
Pages moved
65
significant first
Pages read
637
in this capture
Captured
18:37 UTC
Corpus hash
5998d0f2c1b1
corpus-hash
What this read moved
1-25 of 65, page 1 of 3This capture is too large to show at once. Changes 1-25 of 65 are below, significant first; the rest are on the following screens.
about-claude/models/choosing-a-model Changed · +6 / -2 lines
from line 67
6767| ------------------------------------------------------------------------- | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------- |
6868| The highest available capability | Claude Fable 5.1 | Agent sessions that run for hours, multistep deep research, analysis carried through to a finished document, spreadsheet, or deck |
6969| Complex agentic coding and enterprise work | Claude Opus 5.5 | Multihour autonomous coding agents, large-scale refactoring, complex systems engineering, vision-heavy workflows, computer use |
70| Speed and capability for everyday coding, agent, and enterprise workloads | Claude Sonnet 5 | Code generation, data analysis, content creation, visual understanding, agentic tool use |
70| Speed and capability for everyday coding, agent, and enterprise workloads | Claude Sonnet 5.5 | Code generation, data analysis, content creation, visual understanding, agentic tool use |
7171| The lowest latency and price, with extended thinking | Claude Haiku 4.5 | Real-time applications, high-volume intelligent processing, cost-sensitive deployments needing strong reasoning, sub-agent tasks |
7272
7373***
from line 107
107107 The latest Opus model: breaking changes, new features, and behavior differences
108108 </Card>
109109
110 <Card title="What's new in Claude Sonnet 5.5" icon="sparkle" href="https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5">
111 The latest Sonnet model: breaking changes, new features, and behavior differences
112 </Card>
113
110114 <Card title="What's new in Claude Sonnet 5" icon="sparkle" href="https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5">
111 For everyday workloads that balance speed and capability
115 New features and behavior changes in Claude Sonnet 5
112116 </Card>
113117
114118 <Card title="Start building" icon="code" href="https://platform.claude.com/docs/en/get-started">
agents-and-tools/agent-skills/claude-api-skill Changed · +3 / -3 lines
from line 26
2626* **Streaming patterns:** Implementation details for building chat UIs and handling incremental display
2727* **Batch processing:** Offline batch processing at 50% cost
2828* **Prompt caching:** Prefix-stability design, breakpoint placement, and silent-invalidator audit
29* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5) and [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide))
29* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), and [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide))
3030* **Current model information:** Model IDs, context window sizes, and pricing
3131* **Common pitfalls:** Detailed guidance on avoiding frequent mistakes when integrating with the API
3232
from line 124
124124* **Effort calibration**, recommending an `output_config.effort` starting point for the target model (for example, the default `high` on Claude Opus 5, and `xhigh` for coding and agentic use cases on Claude Opus 4.8 and Claude Opus 4.7)
125125* **Prompt-behavior tuning**, flagging length-control, tool-triggering, subagent, and instruction-following prompts that may behave differently on the target model
126126* **Silent default handling**, opting back into thinking summarization (`thinking.display: "summarized"`) when reasoning is surfaced to users on Claude Opus 4.8 and Claude Opus 4.7
127* **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) when the target is Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5 (the server-side `fallbacks` parameter, typically in its `"default"` mode, the SDK refusal-fallback middleware, or a fallback-credit retry), and updating fallback code written against earlier preview shapes
127* **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) when the target is Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5 (the server-side `fallbacks` parameter, typically in its `"default"` mode, the SDK refusal-fallback middleware, or a fallback-credit retry), and updating fallback code written against earlier preview shapes
128128
129129As it edits, the skill explains each change and its motivation inline. On completion, it produces a checklist of items that require manual verification (typically integration tests, length-control prompt tuning, and cost/rate-limit re-baselining).
130130
131For the full list of model-specific changes the skill applies, see [Migrating 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), [Migrating to Claude Opus 5.5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), and [Migrating to Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide).
131For the full list of model-specific changes the skill applies, see [Migrating 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), [Migrating to Claude Opus 5.5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Migrating to Claude Sonnet 5.5 from Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), and [Migrating to Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide).
132132
133133## Setting up a Managed Agent
134134
agents-and-tools/tool-use/advisor-tool Changed · +17 / -16 lines
from line 341
341341| `advisor_redacted_result` | `encrypted_content`, `stop_reason` | The advisor model returns encrypted output. |
342342
343343<Note>
344 Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 advisors return the encrypted `advisor_redacted_result`. Every other advisor model in the [compatibility table](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) returns the plaintext `advisor_result`. To read the advice text in your own responses, use an advisor that returns plaintext, such as `claude-opus-4-8`, where your executor's row in the [compatibility table](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) lists one. Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 executors pair only with advisors that return the encrypted form, so on those executors the advice text isn't readable in the response.
344 Claude Sonnet 5.5, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 advisors return the encrypted `advisor_redacted_result`. Every other advisor model in the [compatibility table](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) returns the plaintext `advisor_result`. To read the advice text in your own responses, use an advisor that returns plaintext, such as `claude-opus-4-8`, where your executor's row in the [compatibility table](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) lists one. Claude Sonnet 5.5, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 executors pair only with advisors that return the encrypted form, so on those executors the advice text isn't readable in the response.
345345</Note>
346346
347347Here is the same request sent twice, identical except for the advisor `model` in the tool definition, showing both variants.
from line 1235
12351235
12361236The plain-text nudge is highly salient on Haiku and Sonnet executors: 74 percent (Sonnet) to 98 percent (Haiku) of nudged attempts in Anthropic's testing called the advisor immediately at turn 2. If that lands before your executor has read the problem or gathered context, the resulting advisor call is low-context and can displace a better-timed later call. Measure your executor's baseline first-call turn before adding the nudge. If the executor already calls the advisor reliably and its first call typically lands at turn N, set `NUDGE_TURN` greater than N. In Anthropic's testing, a turn-2 nudge on workloads where the baseline first call was turn 7 or later correlated with a 3 to 4 percentage-point task-performance drop. On a browse workload where the baseline call rate was 86 percent, the same nudge raised engagement with no task-performance cost.
12371237
1238To force a consult on a specific request instead of nudging, set `tool_choice` to `{"type": "tool", "name": "advisor"}`, subject to the constraints in [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use). Forcing tool use cannot be combined with manual extended thinking (`thinking: {type: "enabled"}`): the API returns a `400 invalid_request_error` if you enable both. Adaptive thinking supports forced tool use. Claude Opus 5.5, Claude Fable 5.1, and Claude Mythos 5.1 executors reject `tool_choice` types `tool` and `any`, so use the prompt nudge on those models instead.
1238To force a consult on a specific request instead of nudging, set `tool_choice` to `{"type": "tool", "name": "advisor"}`, subject to the constraints in [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use). Forcing tool use cannot be combined with manual extended thinking (`thinking: {type: "enabled"}`): the API returns a `400 invalid_request_error` if you enable both. Adaptive thinking supports forced tool use. Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 executors reject `tool_choice` types `tool` and `any`, so use the prompt nudge on those models instead.
12391239
12401240## Streaming
12411241
from line 1807
18071807
18081808The executor model (the top-level `model` field) and the advisor model (the `model` field inside the tool definition) must form a valid pair. The advisor must be Claude Sonnet 4.6 or a more capable model, and it must be at least as capable as the executor. Models of equal capability (for example, Claude Opus 4.7 and Claude Opus 4.8) can advise each other.
18091809
1810| Executor models | Advisor models |
1811| ------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1812| Claude Haiku 4.5 (claude-haiku-4-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Opus 4.6 (claude-opus-4-6) Claude Sonnet 5 (claude-sonnet-5) Claude Sonnet 4.6 (claude-sonnet-4-6) |
1813| Claude Sonnet 4.6 (claude-sonnet-4-6) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Opus 4.6 (claude-opus-4-6) Claude Sonnet 5 (claude-sonnet-5) Claude Sonnet 4.6 (claude-sonnet-4-6) |
1814| Claude Sonnet 5 (claude-sonnet-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Sonnet 5 (claude-sonnet-5) |
1815| Claude Opus 4.6 (claude-opus-4-6) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Opus 4.6 (claude-opus-4-6) Claude Sonnet 5 (claude-sonnet-5) |
1816| Claude Opus 4.7 (claude-opus-4-7) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) |
1817| Claude Opus 4.8 (claude-opus-4-8) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) |
1818| Claude Opus 5 (claude-opus-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1819| Claude Opus 5.5 (claude-opus-5-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1820| Claude Fable 5 (claude-fable-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1821| Claude Mythos 5 (claude-mythos-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1822| Claude Fable 5.1 (claude-fable-5-1) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) |
1823| Claude Mythos 5.1 (claude-mythos-5-1) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) |
1810| Executor models | Advisor models |
1811| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1812| Claude Haiku 4.5 (claude-haiku-4-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Opus 4.6 (claude-opus-4-6) Claude Sonnet 5.5 (claude-sonnet-5-5) Claude Sonnet 5 (claude-sonnet-5) Claude Sonnet 4.6 (claude-sonnet-4-6) |
1813| Claude Sonnet 4.6 (claude-sonnet-4-6) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Opus 4.6 (claude-opus-4-6) Claude Sonnet 5.5 (claude-sonnet-5-5) Claude Sonnet 5 (claude-sonnet-5) Claude Sonnet 4.6 (claude-sonnet-4-6) |
1814| Claude Sonnet 5 (claude-sonnet-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Sonnet 5.5 (claude-sonnet-5-5) Claude Sonnet 5 (claude-sonnet-5) |
1815| Claude Sonnet 5.5 (claude-sonnet-5-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Sonnet 5.5 (claude-sonnet-5-5) |
1816| Claude Opus 4.6 (claude-opus-4-6) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Opus 4.6 (claude-opus-4-6) Claude Sonnet 5.5 (claude-sonnet-5-5) Claude Sonnet 5 (claude-sonnet-5) |
1817| Claude Opus 4.7 (claude-opus-4-7) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Sonnet 5.5 (claude-sonnet-5-5) |
1818| Claude Opus 4.8 (claude-opus-4-8) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) Claude Opus 4.8 (claude-opus-4-8) Claude Opus 4.7 (claude-opus-4-7) Claude Sonnet 5.5 (claude-sonnet-5-5) |
1819| Claude Opus 5 (claude-opus-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1820| Claude Opus 5.5 (claude-opus-5-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1821| Claude Fable 5 (claude-fable-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1822| Claude Mythos 5 (claude-mythos-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opus-5) |
1823| Claude Fable 5.1 (claude-fable-5-1) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) |
1824| Claude Mythos 5.1 (claude-mythos-5-1) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) |
18241825
18251826If you request an invalid pair, the API returns a `400 invalid_request_error` naming the unsupported combination.
18261827
agents-and-tools/tool-use/computer-use-tool Changed · +5 / -4 lines
from line 14
1414 - claude-mythos-5
1515 - claude-opus-5-5
1616 - claude-opus-5
17 - claude-sonnet-5-5
1718 - claude-sonnet-5
1819 - claude-opus-4-8
1920 supportedPlatforms:
from line 25
2425 Microsoft Foundry: beta
2526 details:
2627 - On the Claude API and Google Cloud, Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier `computer_20251124` tool version. To move an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).
27 - On Amazon Bedrock, Claude Opus 5.5 accepts the earlier `computer_20251124` tool version as Claude Opus 5 does.
28 - On Amazon Bedrock, Claude Opus 5.5 and Claude Sonnet 5.5 accept the earlier `computer_20251124` tool version as Claude Opus 5 and Claude Sonnet 5 do.
2829 - Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 support computer use only through the earlier `computer_20251124` tool version, which requires a beta header; see [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
2930 - Platforms other than the Claude API and Google Cloud currently offer only the [earlier beta tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
3031---
from line 1829
18281829
18291830* Place one `cache_control` breakpoint after the system prompt and tool definitions, and up to three more on the last `tool_result` block of each of the most recent turns, advancing them each turn. Within a [batch action](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#batch-actions), markers on several blocks act as a single breakpoint but each still counts toward the limit of four, so use one per turn.
18301831* Prune old screenshots in *batches*, not one each turn. Dropping a screenshot every turn changes the prefix every turn and invalidates the cache. A reasonable default is to keep the last three screenshots and prune every 25 turns, so the prefix stays byte-identical between prune events; if your screenshots exceed 2000 px on either side, choose an interval that keeps each request at 20 or fewer images.
1831* On Claude Fable 5.1 and Claude Opus 5.5, avoid pruning on the client: removing an earlier screenshot [invalidates every later thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in every request that still carries those turns. Resize screenshots to 2000 px or less per side instead, and use server-side [tool result clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#tool-result-clearing) to drop old ones from the context. If you must prune, keep [`prefix_mismatch_behavior: "drop_block"`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) set from then on; after each prune, Claude continues without the thinking produced since the pruned screenshot, on that request and every later one.
1832* On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, avoid pruning on the client: removing an earlier screenshot [invalidates every later thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in every request that still carries those turns. Resize screenshots to 2000 px or less per side instead, and use server-side [tool result clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#tool-result-clearing) to drop old ones from the context. If you must prune, keep [`prefix_mismatch_behavior: "drop_block"`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) set from then on; after each prune, Claude continues without the thinking produced since the pruned screenshot, on that request and every later one. On Claude Sonnet 5.5, `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.
18321833
18331834### Diagnose click issues
18341835
from line 2116
21152116
21162117## Migrate from `computer_20251124`
21172118
2118Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) keep accepting it with its beta header, so an existing integration keeps working until you change it. Claude 5.5 and later models are the exception on the Claude API and Google Cloud: there they accept only the toolset. Upgrade an integration before you move it to one of them. On Amazon Bedrock, Claude Opus 5.5 keeps accepting `computer_20251124`. To upgrade, make the following changes together:
2119Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) keep accepting it with its beta header, so an existing integration keeps working until you change it. Claude 5.5 and later models are the exception on the Claude API and Google Cloud: there they accept only the toolset. Upgrade an integration before you move it to one of them. On Amazon Bedrock, Claude Opus 5.5 and Claude Sonnet 5.5 keep accepting `computer_20251124`. To upgrade, make the following changes together:
21192120
212021211. **Remove the beta header.** Drop `anthropic-beta: computer-use-2025-11-24` from your requests. In the SDKs, remove the `betas` parameter and call the Messages API through the standard client rather than the beta namespace.
212121222. **Change the `tools` entry.** Set `type` to `computer_toolset_20260801` and delete `name`, `display_width_px`, `display_height_px`, `display_number`, and `enable_zoom`. The toolset rejects each of these fields.
from line 2178
21772178
21782179| Tool version | Beta header | Use with | Parameters |
21792180| ------------------- | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- |
2180| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5; on Amazon Bedrock, also Claude Opus 5.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
2181| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5; on Amazon Bedrock, also Claude Opus 5.5 and Claude Sonnet 5.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
21812182| `computer_20250124` | `computer-use-2025-01-24` | Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
21822183
21832184***
api/errors Changed · +33 / -5 lines
from line 487
487487"thinking.type.disabled" is not supported for this model. Thinking defaults to adaptive mode when not specified; use "thinking.type.enabled" with "budget_tokens" for extended thinking.
488488```
489489
490On Claude Sonnet 5.5, thinking can't be set to `disabled`. Use `thinking: {"type": "between_tools"}` for the lowest thinking setting, which turns off up-front thinking. Sending `thinking: {"type": "disabled"}` returns a 400 `invalid_request_error` with this message:
491
492```text wrap
493"thinking.type.disabled" is not supported for this model. Use "thinking.type.between_tools" for the lowest thinking setting, or "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.
494```
495
496At `xhigh` or `max` [effort](https://platform.claude.com/docs/en/build-with-claude/effort), a request with `between_tools` also returns a 400 `invalid_request_error`. The message says thinking is disabled because `between_tools` has no up-front thinking:
497
498```text wrap
499output_config.effort 'xhigh' is not supported when thinking is disabled on this model. Use effort 'high' or below, or enable thinking.
500```
501
502With `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. The error names the position of the message that set the new level:
503
504```text wrap
505messages.N: output_config.effort 'low' differs from the 'high' in effect before it; effort cannot change when thinking is disabled on this model. Use effort 'high', or enable thinking.
506```
507
508In both messages, "enable thinking" means adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. Claude Sonnet 5.5 rejects `"enabled"` with a 400 error. To vary effort per turn, use adaptive thinking.
509
510Sending `thinking: {"type": "between_tools"}` to any model other than Claude Sonnet 5.5 returns a 400 `invalid_request_error`:
511
512```text wrap
513"thinking.type.between_tools" is not supported for this model.
514```
515
516For the fixes, see [Troubleshooting thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-type-between-tools), which covers the `between_tools` and effort errors.
517
490518Omit the `thinking` parameter and the request runs with adaptive thinking. To keep thinking content out of responses without turning thinking off, set `display: "omitted"` on the thinking configuration. See [Troubleshooting thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-type-disabled).
491519
492520### Forced tool use not supported
493521
494Claude Opus 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://anthropic.com/glasswing) don't support forced tool use. Sending `tool_choice: {"type": "any"}` or `tool_choice: {"type": "tool", "name": "..."}` to any of these models, including on the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting), returns a 400 `invalid_request_error`:
522Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://anthropic.com/glasswing) don't support forced tool use. Sending `tool_choice: {"type": "any"}` or `tool_choice: {"type": "tool", "name": "..."}` to any of these models, including on the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting), returns a 400 `invalid_request_error`:
495523
496524```text wrap
497525tool_choice: type "tool" and "any" are not supported for this model.
from line 529
501529
502530### Computer use tool version not supported
503531
504On the Claude API and Google Cloud, Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) only as the `computer_toolset_20260801` toolset. On those platforms, sending it a `tools` entry of the earlier `computer_20251124` type (with that tool's beta header) returns a 400 `invalid_request_error`. The message names the rejected type, then lists the tool types the model does accept after `Did you mean one of`; it begins:
532On the Claude API and Google Cloud, Claude Opus 5.5 and Claude Sonnet 5.5 support [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) only as the `computer_toolset_20260801` toolset. On those platforms, sending either model a `tools` entry of the earlier `computer_20251124` type (with that tool's beta header) returns a 400 `invalid_request_error`. The message names the rejected type, then lists the tool types the model does accept after `Did you mean one of`. For Claude Opus 5.5, it begins:
505533
506534```text wrap
507535'claude-opus-5-5' does not support tool types: computer_20251124.
508536```
509537
510The API returns the same message for any Anthropic-defined tool type that the requested model doesn't support. Declare `{"type": "computer_toolset_20260801"}` without the beta header and update your agent loop as described in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). Earlier models that support the toolset keep accepting `computer_20251124`, as does Claude Opus 5.5 on Amazon Bedrock.
538The API returns the same message for any Anthropic-defined tool type that the requested model doesn't support. Declare `{"type": "computer_toolset_20260801"}` without the beta header and update your agent loop as described in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). Earlier models that support the toolset keep accepting `computer_20251124`, as do Claude Opus 5.5 and Claude Sonnet 5.5 on Amazon Bedrock.
511539
512540### Thinking block no longer matches the conversation
513541
514On Claude Fable 5.1 and Claude Opus 5.5, the API accepts a replayed thinking block only while the `system` prompt, `tools`, and messages that preceded it are unchanged. For new accounts created on or after August 31, 2026, and for any request that sets `thinking.block_binding.prefix_mismatch_behavior` to `"error"`, a replayed block whose earlier history changed is rejected with a 400 `invalid_request_error` (with `"drop_block"`, the API drops the block and the request succeeds). The message starts with the position of the first failing block:
542On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, the API accepts a replayed thinking block only while the `system` prompt, `tools`, and messages that preceded it are unchanged. For new accounts created on or after August 31, 2026, and for any request that sets `thinking.block_binding.prefix_mismatch_behavior` to `"error"`, a replayed block whose earlier history changed is rejected with a 400 `invalid_request_error` (with `"drop_block"`, the API drops the block and the request succeeds). The message starts with the position of the first failing block:
515543
516544```text wrap
517545messages.{i}.content.{j}: Invalid `signature` in `thinking` block. The block is bound to a different conversation. Remove the block, or set `thinking.block_binding.prefix_mismatch_behavior` to "drop_block".
518546```
519547
520Without the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and continue. A block from a model the target model can't read is dropped rather than rejected. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) and [Troubleshooting thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-block-signature).
548Without the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and continue. On Claude Sonnet 5.5, `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. A block from a model the target model can't read is dropped rather than rejected. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) and [Troubleshooting thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-block-signature).
521549
522550Sending `thinking.block_binding` without the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers) returns a 400 `invalid_request_error` whose message ends in:
523551
api/rate-limits Changed · +4 / -1 lines
from line 142
142142 | Claude Opus 5.5 | 1,000 | 2,000,000 | 400,000 |
143143 | Claude Opus 5 | 1,000 | 2,000,000 | 400,000 |
144144 | Claude Opus 4.x2 | 1,000 | 2,000,000 | 400,000 |
145 | Claude Sonnet 5.5 | 1,000 | 2,000,000 | 400,000 |
145146 | Claude Sonnet 5 | 1,000 | 2,000,000 | 400,000 |
146147 | Claude Sonnet 4.x3 | 1,000 | 2,000,000 | 400,000 |
147148 | Claude Haiku 4.5 | 1,000 | 2,000,000 | 400,000 |
from line 156
155156 | Claude Opus 5.5 | 5,000 | 5,000,000 | 1,000,000 |
156157 | Claude Opus 5 | 5,000 | 5,000,000 | 1,000,000 |
157158 | Claude Opus 4.x2 | 5,000 | 5,000,000 | 1,000,000 |
159 | Claude Sonnet 5.5 | 5,000 | 5,000,000 | 1,000,000 |
158160 | Claude Sonnet 5 | 5,000 | 5,000,000 | 1,000,000 |
159161 | Claude Sonnet 4.x3 | 5,000 | 5,000,000 | 1,000,000 |
160162 | Claude Haiku 4.5 | 5,000 | 5,000,000 | 1,000,000 |
from line 170
168170 | Claude Opus 5.5 | 10,000 | 10,000,000 | 2,000,000 |
169171 | Claude Opus 5 | 10,000 | 10,000,000 | 2,000,000 |
170172 | Claude Opus 4.x2 | 10,000 | 10,000,000 | 2,000,000 |
173 | Claude Sonnet 5.5 | 10,000 | 10,000,000 | 2,000,000 |
171174 | Claude Sonnet 5 | 10,000 | 10,000,000 | 2,000,000 |
172175 | Claude Sonnet 4.x3 | 10,000 | 10,000,000 | 2,000,000 |
173176 | Claude Haiku 4.5 | 10,000 | 10,000,000 | 2,000,000 |
from line 186
183186
184187*2 Opus rate limit is a total limit that applies to combined traffic across Claude Opus 4.8, Opus 4.7, Opus 4.6, and Opus 4.5. Claude Opus 5.5 and Claude Opus 5 each have a separate rate limit and are not part of this combined bucket.*
185188
186*3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5. Claude Sonnet 5 has a separate rate limit and is not part of this combined bucket.*
189*3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5. Claude Sonnet 5.5 and Claude Sonnet 5 each have a separate rate limit and are not part of this combined bucket.*
187190
188191*4 Limit counts `cache_read_input_tokens` toward ITPM usage.*
189192
build-with-claude/claude-in-microsoft-foundry Changed · +6 / -3 lines
from line 4
44description: Access Claude models through Microsoft Foundry with Azure-native endpoints and authentication.
55---
66
7This guide shows you how to set up and make API calls to Claude in Microsoft Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you access Claude in Microsoft Foundry, you are billed for Claude usage in the Azure Marketplace. You can use Claude models including Claude Fable 5.1, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Sonnet 5, and features such as the [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), while managing costs through your Azure subscription.
7This guide shows you how to set up and make API calls to Claude in Microsoft Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you access Claude in Microsoft Foundry, you are billed for Claude usage in the Azure Marketplace. You can use Claude models including Claude Fable 5.1, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Sonnet 5.5, and Claude Sonnet 5, and features such as the [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), while managing costs through your Azure subscription.
88
99Claude is available in Global Standard and US Data Zone Standard deployment types in Foundry resources, billed in Claude Consumption Units through the Azure Marketplace. Visit [Claude in Microsoft Foundry pricing](https://platform.claude.com/docs/en/about-claude/pricing#claude-in-microsoft-foundry-pricing) for details.
1010
from line 19
1919| Deployment types | Global Standard, US Data Zone Standard | Global Standard |
2020| Recommended for | Most workloads | [Access to features or models not yet hosted on Azure](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure) |
2121
22Claude Sonnet 5.5 supports only Global Standard deployments.
23
2224<Note>
2325 Anthropic acts as an independent processor for Microsoft. Customers using Claude through Microsoft Foundry are subject to Anthropic's data use terms. For deployments hosted on Azure, prompts and completions remain within Azure. Only usage metadata and content flagged by Anthropic's safety systems egress to Anthropic. Anthropic continues to provide its safety and data commitments.
2426</Note>
from line 157
1551575. Configure the deployment:
156158
157159 * **Deployment name:** Defaults to the model ID, but you can customize it (for example, `my-claude-deployment`). The deployment name cannot be changed after creation.
158 * **Region scope:** Select Global, or for models hosted on Azure, Data Zone. Selecting Data Zone creates a US Data Zone Standard deployment, which keeps inference within the United States and is equivalent to setting [`inference_geo: "us"`](https://platform.claude.com/docs/en/manage-claude/data-residency#inference-geo) on the Claude API.
160 * **Region scope:** Select Global, or for models hosted on Azure, Data Zone. Selecting Data Zone creates a US Data Zone Standard deployment, which keeps inference within the United States and is equivalent to setting [`inference_geo: "us"`](https://platform.claude.com/docs/en/manage-claude/data-residency#inference-geo) on the Claude API. For Claude Sonnet 5.5, select Global.
159161 * **Model version:** Expand **Model version settings** and select a version from the **Model version** dropdown menu. Each [hosting option](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options) is listed as a separate model version, labeled with its hosting option (for example, version 1 for Hosted on Anthropic, version 2 for Hosted on Azure).
160162
1611636. Select **Deploy** and wait for provisioning to complete.
from line 640
638640
639641### Context window
640642
641Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Microsoft Foundry. Other Claude models, including Claude Sonnet 4.5, have a 200k-token context window.
643Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Microsoft Foundry. Other Claude models, including Claude Sonnet 4.5, have a 200k-token context window.
642644
643645### Claude features not supported for Claude in Microsoft Foundry
644646
from line 689
687689| Claude Opus 4.7 | `claude-opus-4-7` | | ✓ |
688690| Claude Opus 4.6 | `claude-opus-4-6` | | ✓ |
689691| Claude Opus 4.5 | `claude-opus-4-5` | | ✓ |
692| Claude Sonnet 5.5 | `claude-sonnet-5-5` | ✓ | ✓ |
690693| Claude Sonnet 5 | `claude-sonnet-5` | ✓ | ✓ |
691694| Claude Sonnet 4.6 | `claude-sonnet-4-6` | | ✓ |
692695| Claude Sonnet 4.5 | `claude-sonnet-4-5` | | ✓ |
build-with-claude/claude-on-amazon-bedrock-legacy Changed · +3 / -3 lines
from line 131
131131#### API model IDs
132132
133133<Note>
134 Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, and Claude Opus 4.7 are reachable through `InvokeModel` on `bedrock-runtime`. These requests are served by the same infrastructure as the [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) endpoint. For the native Messages API request shape and full feature parity, use that page. These models are omitted from the model table on this page because they do not have ARN-versioned model IDs.
134 Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, and Claude Opus 4.7 are reachable through `InvokeModel` on `bedrock-runtime`. These requests are served by the same infrastructure as the [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) endpoint. For the native Messages API request shape and full feature parity, use that page. These models are omitted from the model table on this page because they do not have ARN-versioned model IDs.
135135</Note>
136136
137137Lifecycle terms (Deprecated, Retired) are defined in [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations). Lifecycle dates on partner-operated platforms are set by the partner and can differ from the Claude API schedule. For the current retirement date of any model on Amazon Bedrock, see [Amazon Bedrock's model lifecycle page](https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html).
from line 756
756756
757757### Mid-conversation system messages on Bedrock
758758
759[Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available through the InvokeModel API for Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8. As described in the note under [API model IDs](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids), these requests are served by the same infrastructure as the [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) endpoint. No beta header is required. This feature is not available on Claude Sonnet 5. Use the top-level `system` field instead. It is not available for the ARN-versioned models in the model table on this page.
759[Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available through the InvokeModel API for Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Sonnet 5.5. As described in the note under [API model IDs](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#api-model-ids), these requests are served by the same infrastructure as the [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) endpoint. No beta header is required. This feature is not available on Claude Sonnet 5. Use the top-level `system` field instead. It is not available for the ARN-versioned models in the model table on this page.
760760
761761**For Converse API users:** the Converse API accepts system instructions through its top-level [`system` parameter](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html). To add system instructions mid-conversation, use the InvokeModel API.
762762
763763### Context window
764764
765Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Amazon Bedrock. Other Claude models, including Sonnet 4.5 and Sonnet 4 (deprecated), have a 200k-token context window.
765Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Amazon Bedrock. Other Claude models, including Sonnet 4.5 and Sonnet 4 (deprecated), have a 200k-token context window.
766766
767767Bedrock limits request payloads to 20 MB. When sending large documents or many images, you may reach this limit before the token limit.
768768
build-with-claude/compaction-threshold Changed · +3 / -2 lines
from line 19
1919 - claude-opus-4-8
2020 - claude-opus-4-7
2121 - claude-opus-4-6
22 - claude-sonnet-5-5
2223 - claude-sonnet-5
2324 - claude-sonnet-4-6
2425 supportedPlatforms:
from line 1711
17101711* Keep the original messages in your list and let the API handle removing the compacted content
17111712* Manually drop the compacted messages and only include the compaction block onwards
17121713
1713On Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5.5, thinking blocks from before a `compaction` block aren't carried forward, so the summary is all the model has of that earlier work. If you write your own `instructions`, tell the model what the summary must retain; see [Tell the model what to preserve in compaction summaries](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#tell-the-model-what-to-preserve-in-compaction-summaries).
1714On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, thinking blocks from before a `compaction` block aren't carried forward, so the summary is all the model has of that earlier work. If you write your own `instructions`, tell the model what the summary must retain; see [Tell the model what to preserve in compaction summaries](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#tell-the-model-what-to-preserve-in-compaction-summaries).
17141715
17151716### Streaming
17161717
from line 2895
28942895 ```
28952896</CodeGroup>
28962897
2897On Claude Fable 5.1 and Claude Opus 5.5, remove the `thinking` and `redacted_thinking` blocks from any assistant turn you re-insert after the compaction block, or send `thinking.block_binding.prefix_mismatch_behavior: "drop_block"` with the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers). Those blocks were produced when the full history was present, so they no longer pass the [conversation check](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation). Where the check is enforced, the continuation request is rejected with a 400 error. The preserved text and tool blocks can stay as they are. Letting the API summarize everything, without re-inserting earlier turns, avoids this.
2898On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, remove the `thinking` and `redacted_thinking` blocks from any assistant turn you re-insert after the compaction block, or send `thinking.block_binding.prefix_mismatch_behavior: "drop_block"` with the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers). Those blocks were produced when the full history was present, so they no longer pass the [conversation check](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation). Where the check is enforced, the continuation request is rejected with a 400 error. The preserved text and tool blocks can stay as they are. Letting the API summarize everything, without re-inserting earlier turns, avoids this. On Claude Sonnet 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, remove the blocks instead.
28982899
28992900Here's an example that uses `pause_after_compaction` to preserve the prior exchange and the current user message (three messages total) verbatim instead of summarizing them:
29002901
build-with-claude/effort Changed · +18 / -9 lines
### Recommended effort levels for Claude Sonnet 5.5
from line 19
1919 - claude-opus-4-7
2020 - claude-opus-4-6
2121 - claude-opus-4-5-20251101
22 - claude-sonnet-5-5
2223 - claude-sonnet-5
2324 - claude-sonnet-4-6
2425 supportedPlatforms:
from line 237
236237
237238### Effort levels
238239
239| Level | Description | Typical use case |
240| -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
241| `max` | Absolute maximum capability with no constraints on token spending. Available on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, and Claude Sonnet 4.6. | Tasks requiring the deepest possible reasoning and most thorough analysis |
242| `xhigh` | Extended capability for long-horizon work. Available on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5. | Long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions |
243| `high` | Spends as many tokens as the task needs for excellent results. The default on every model that supports effort except Claude Opus 5.5. | Complex reasoning, difficult coding problems, agentic tasks |
244| `medium` | Balanced approach with moderate token savings. The default on Claude Opus 5.5. | Agentic tasks that require a balance of speed, cost, and performance |
245| `low` | Most efficient. Significant token savings with some capability reduction. | Simpler tasks that need the best speed and lowest costs, such as subagents |
240| Level | Description | Typical use case |
241| -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
242| `max` | Absolute maximum capability with no constraints on token spending. Available on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6. | Tasks requiring the deepest possible reasoning and most thorough analysis |
243| `xhigh` | Extended capability for long-horizon work. Available on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5.5, and Claude Sonnet 5. | Long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions |
244| `high` | Spends as many tokens as the task needs for excellent results. The default on every model that supports effort except Claude Opus 5.5. | Complex reasoning, difficult coding problems, agentic tasks |
245| `medium` | Balanced approach with moderate token savings. The default on Claude Opus 5.5. | Agentic tasks that require a balance of speed, cost, and performance |
246| `low` | Most efficient. Significant token savings with some capability reduction. | Simpler tasks that need the best speed and lowest costs, such as subagents |
246247
247248Not every model that supports `max` supports `xhigh`.
248249
from line 309
308309
309310When running Claude Opus 4.7 at `xhigh` or `max` effort, set a large `max_tokens` so the model has room to think and act across subagents and tool calls. Starting at 64k tokens and tuning from there is a reasonable default.
310311
312### Recommended effort levels for Claude Sonnet 5.5
313
314Claude Sonnet 5.5 supports all five effort levels, and `high` is the default on the Claude API. Its levels are recalibrated, so a level doesn't produce the same amount of thinking as the same level on Claude Sonnet 5. Run a fresh effort sweep on your evals rather than carrying over the setting you used on Claude Sonnet 5. Start with `high` unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool use, start with `medium` for well-specified tasks and move to `high` for harder or longer ones. For chat and other latency-sensitive work, start with `medium` or `low`. Use `xhigh` or `max` only where your evals show a quality gain. Set `max_tokens` with room for thinking and the reply. Thinking counts toward `max_tokens` even when the thinking content isn't returned. For agentic coding, set `max_tokens` to 128,000, the model's maximum, and [stream](https://platform.claude.com/docs/en/build-with-claude/streaming) the response.
315
316To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It's the lowest thinking setting on Claude Sonnet 5.5, and it works at `low`, `medium`, and `high` effort. At `xhigh` or `max`, a request with it returns a 400 error, so use adaptive thinking at those levels: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. 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).
317
318Claude Sonnet 5.5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message `output_config`, which preserves the prompt cache. With `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 per turn, use adaptive thinking. See [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#calibrate-effort).
319
311320### Recommended effort levels for Claude Sonnet 5
312321
313322Claude Sonnet 5 defaults to `high` effort on the Claude API and Claude Code.
from line 364
355364
356365## Change effort mid-conversation
357366
358You can run later turns of a conversation at a different effort level in two ways. On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, and Claude Opus 5, use a per-message effort change, which keeps the prompt cache. On other models, set a new top-level value on the next request, which starts the cache over.
367You can run later turns of a conversation at a different effort level in two ways. On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5, use a per-message effort change, which keeps the prompt cache. On other models, set a new top-level value on the next request, which starts the cache over.
359368
360369### Per-message effort (beta)
361370
362Per-message effort is in beta and requires the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `mid-conversation-output-config-2026-07-01`. Models without per-message effort, including Claude Fable 5, return a 400 error: `output_config.effort requires a model that supports per-turn effort; this model does not`.
371Per-message effort is in beta and requires the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `mid-conversation-output-config-2026-07-01`. Models without per-message effort, including Claude Fable 5, return a 400 error: `output_config.effort requires a model that supports per-turn effort; this model does not`. On Claude Sonnet 5.5 with `thinking: {"type": "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 per turn, use adaptive thinking.
363372
364373Add a `role: "system"` message with empty `content` and the new level in `output_config.effort`. The new level takes effect from the next `user` turn and holds until a later message changes it. Everything before that message is unchanged, so the cached prefix still matches.
365374
build-with-claude/mid-conversation-system-messages Changed · +5 / -5 lines
from line 15
1515<Note>
1616 Mid-conversation system messages are available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai).
1717
18 This feature is available on Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, and Claude Opus 5. No beta header is required for mid-conversation system messages. This feature is not available on Claude Sonnet 5. Use the top-level `system` field there instead.
18 This feature is available on Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, Claude Opus 5, and Claude Sonnet 5.5. No beta header is required for mid-conversation system messages. This feature is not available on Claude Sonnet 5. Use the top-level `system` field there instead.
1919
2020 [Mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) are in beta on the same models. On the Claude API, send the `inline-tools-2026-09-15` beta header, which also covers [defining a tool inside a `tool_addition` block](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta). [Adding an MCP server that way](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#add-an-mcp-server-mid-conversation-beta) needs a second beta header, `mcp-client-2026-09-15`, which is available on the Claude API. The `mid-conversation-tool-changes-2026-07-01` header works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, and Google Cloud.
2121
from line 1642
16421642
16431643You can still set the top-level `system` field for instructions that should apply to the entire conversation. Reserve mid-conversation system messages for instructions that only become relevant later, or that you want to add without invalidating the cached prefix.
16441644
1645A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level from the next `user` turn on. This is in beta on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, and Claude Opus 5 on the Claude API and Google Cloud, and requires the `mid-conversation-output-config-2026-07-01` beta header. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).
1645A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level from the next `user` turn on. This is in beta on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5 on the Claude API and Google Cloud, and requires the `mid-conversation-output-config-2026-07-01` beta header. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).
16461646
16471647<CodeGroup>
16481648 ```bash cURL
from line 2000
20002000}
20012001```
20022002
2003The main use is a per-turn reminder in a tool loop. Append the reminder after the `tool_result` message each time you want the model to see it, and leave every earlier copy where it is. The model sees only the copies that come after the last user message, so the reminder never piles up. Nothing earlier in `messages` changes, so the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) keeps matching. On Claude Fable 5.1 and Claude Opus 5.5 this also keeps later [thinking blocks valid](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): deleting an earlier reminder would change the conversation before those blocks and fail the conversation check, while a cleared message stays in the array and leaves that conversation unchanged.
2003The main use is a per-turn reminder in a tool loop. Append the reminder after the `tool_result` message each time you want the model to see it, and leave every earlier copy where it is. The model sees only the copies that come after the last user message, so the reminder never piles up. Nothing earlier in `messages` changes, so the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) keeps matching. On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 this also keeps later [thinking blocks valid](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): deleting an earlier reminder would change the conversation before those blocks and fail the conversation check, while a cleared message stays in the array and leaves that conversation unchanged.
20042004
20052005The following request is a later step of an agent loop. `messages[3]` rendered on the earlier request, when it was the last message in the array. Once `messages[5]` (a later user message) exists, `messages[3]` is cleared: the cleared message stays in the array, so the conversation before the thinking block in `messages[4]` is unchanged, but the model no longer sees its text. `messages[6]` and `messages[7]` both render, in order.
20062006
from line 2077
20772077
20782078Rules for turn-scoped messages:
20792079
2080* **Re-send cleared messages verbatim.** A cleared message is still part of the conversation history. Rebuilding it from current state (a fresh token count, a timestamp), dropping it as redundant, or changing its `clear_at` value is an edit to an earlier message. The prompt cache misses from that point, and on Claude Fable 5.1 and Claude Opus 5.5 every thinking block produced after it fails the [conversation check](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation).
2080* **Re-send cleared messages verbatim.** A cleared message is still part of the conversation history. Rebuilding it from current state (a fresh token count, a timestamp), dropping it as redundant, or changing its `clear_at` value is an edit to an earlier message. The prompt cache misses from that point, and on Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 every thinking block produced after it fails the [conversation check](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation).
20812081* **Text only.** `content` is one or more `text` blocks (or a string). `tool_addition` and `tool_removal` blocks return a 400 error on a turn-scoped message, and so does `output_config`. Use a separate `role: "system"` message without `clear_at` for those.
20822082* **No `cache_control` on its blocks.** A cleared message is never part of a cache key, so a breakpoint on it could never match. Put the breakpoint on the last block of the preceding user turn instead, as the example does. The top-level [automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching) field skips turn-scoped messages when it picks a breakpoint. On the request that clears a message, the reusable cached prefix ends at the user turn before it, so only the one assistant turn between that message and the new user message is reprocessed.
20832083* **Placement rules still apply**, cleared or not. A turn-scoped message must follow a `user` turn (or an `assistant` turn ending in a server tool result) and precede an `assistant` turn or end the array, like any mid-conversation system message. One that ends the array always renders. One followed directly by another `user` message is a 400 error, not a cleared message: put all of a tool round's results in one user message and the reminders after it.
from line 2334
23342334* **Append the system message after the breakpoint.** Because it comes after the cached prefix, it does not change the prefix hash and the cache still hits.
23352335* **A mid-conversation system message is itself cacheable.** Once it is in the conversation, it becomes part of the stable history. On the next turn you can move your cache breakpoint past it (or rely on [automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching) to do so) and the system message is read from cache like any other turn.
23362336
2337Avoid editing or removing a mid-conversation system message that has already been sent. Like any other change to earlier messages, that invalidates the cache from that point forward. On Claude Fable 5.1 and Claude Opus 5.5 it also invalidates the [thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in every later assistant turn. For guidance that should apply to one turn only, use a [turn-scoped system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) and leave it in place. If the instruction needs to evolve, append a new system message rather than rewriting the old one. Consecutive system messages are accepted and treated as a single system section, which follows the same placement rule as a whole.
2337Avoid editing or removing a mid-conversation system message that has already been sent. Like any other change to earlier messages, that invalidates the cache from that point forward. On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 it also invalidates the [thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in every later assistant turn. For guidance that should apply to one turn only, use a [turn-scoped system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) and leave it in place. If the instruction needs to evolve, append a new system message rather than rewriting the old one. Consecutive system messages are accepted and treated as a single system section, which follows the same placement rule as a whole.
23382338
23392339## Limitations
23402340
build-with-claude/preserved-thinking Changed · +22 / -9 lines
## Thinking blocks stay with the account that produced them
from line 9
99* **The model can read the block.** Each model reads its own thinking blocks and those of a fixed set of other models. Claude Fable 5.1 reads blocks from Claude Opus 5 and, on the Claude API, from Claude Opus 5.5; neither Claude Opus 5 nor Claude Opus 5.5 reads blocks from Claude Fable 5.1. If the current model can't read a block, the API drops it from that request without an error. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
1010* **Nothing before the thinking block has changed.** The top-level `system` prompt, `tools`, and `messages` before the block are its prefix. If the prefix differs from what you sent when the block was produced, that block and every later thinking block are invalid, and the API rejects the request with a 400 error or drops the invalid blocks, whichever you choose. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
1111
12Claude Sonnet 5.5's thinking blocks are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) for where the API enforces this.
13
1214The model check applies to every account. The API enforces the prefix check by default for accounts created on or after August 31, 2026, 00:00 UTC. On older accounts, it enforces the prefix check only on requests that set `thinking.block_binding.prefix_mismatch_behavior`. **Make your integration append-only regardless of your account's age**, so the same code works on every account, including newer accounts enforced by default.
1315
1416## Who needs to change anything
from line 30
2830
2931On an older account, none of these produces an error unless the request sets `prefix_mismatch_behavior`, so a run with no errors on your own key doesn't show whether your code is affected. If people run your tool with their own API keys, those on newer accounts get the 400 error before you do. To see what they see without changing how your requests behave, send the `thinking-binding-controls-2026-08-01` beta header. On an older account, each response then flags blocks that fail the check, and the model still reads them (see [Set the mismatch behavior and read `input_transformations`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#preserved-thinking-controls)).
3032
33Also check your integration if it sends Claude Sonnet 5.5 thinking blocks from one account in a request made by a different account. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
34
3135## Switching models mid-conversation
3236
3337Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks produced by each other and by earlier Claude models. No earlier model reads thinking blocks from Claude Fable 5.1 or Claude Mythos 5.1.
from line 38
3438
3539Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and earlier Opus, Sonnet, and Haiku models, 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. So a conversation that moves from Claude Opus 5 onto Claude Opus 5.5 keeps its reasoning, and so does one that moves from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API. One that moves from Claude Fable 5.1 or Claude Mythos 5.1 to Claude Opus 5.5, or from Claude Opus 5.5 to any model other than those two, runs the turns after the switch without the previous model's reasoning. The blocks are dropped, not rejected, as described below.
3640
41Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. No other model reads thinking blocks from Claude Sonnet 5.5. So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5 keeps its reasoning. One that moves onto Claude Sonnet 5.5 from Claude Opus 5, Claude Opus 5.5, or a Claude Fable or Claude Mythos model runs the turns after the switch without the previous model's reasoning. So does one that moves from Claude Sonnet 5.5 to any other model, for example in a [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback).
42
3743* **A conversation that moves to Claude Fable 5.1 from an earlier model, or from Claude Opus 5.5 on the Claude API, keeps its reasoning.** The earlier model's thinking blocks stay readable, so the model thinks as usual from the first turn after the switch.
3844* **A conversation that moves down to an earlier model loses Claude Fable 5.1's reasoning for that request.** This happens when a router sends a turn to a cheaper model, after a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback), or during a [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback). The API removes the unreadable blocks before the prompt reaches the model. They aren't billed and don't count toward `input_tokens`.
3945
from line 63
5763
5864Without the header, the drop is silent. This entry isn't a bug in your integration, and `prefix_mismatch_behavior` has no effect on it: a block the current model can't read is always dropped.
5965
66## Thinking blocks stay with the account that produced them
67
68Thinking 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. The model answers without the reasoning in the dropped blocks. Blocks from earlier models aren't affected.
69
70On the Claude API and Google Cloud, with the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers), the response lists each dropped block in `input_transformations` as a `thinking_dropped` entry with `reason: "organization_binding_mismatch"`. Without the header, the drop is silent.
71
6072## Keeping the prefix unchanged
6173
62On Claude Fable 5.1 and Claude Opus 5.5, a thinking block stays valid only while everything you sent before it is unchanged on later requests. The checked prefix has three parts:
74On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, a thinking block stays valid only while everything you sent before it is unchanged on later requests. The checked prefix has three parts:
6375
6476* The top-level `system` prompt
6577* The set of `tools`
from line 118
106118
107119#### Handle the error in code
108120
109This is the 400 `invalid_request_error` shown earlier in this section. Don't resend the same body: it fails the same way every time. Retry once with the beta header and `prefix_mismatch_behavior: "drop_block"`, and store that choice with the session so every later request sends it too, including after a restart. If you can't send the beta header, remove every `thinking` and `redacted_thinking` block from the history once, leave them out, and continue. Then fix the edit that caused the mismatch.
121This is the 400 `invalid_request_error` shown earlier in this section. Don't resend the same body: it fails the same way every time. Retry once with the beta header and `prefix_mismatch_behavior: "drop_block"`, and store that choice with the session so every later request sends it too, including after a restart. On Claude Sonnet 5.5, `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. If you can't send the beta header, remove every `thinking` and `redacted_thinking` block from the history once, leave them out, and continue. Then fix the edit that caused the mismatch.
110122
111123### Set the mismatch behavior and read `input_transformations`
112124
from line 127
115127* A top-level `input_transformations` array on every response
116128* A `block_binding` object on the `thinking` configuration, whose one field is `prefix_mismatch_behavior`
117129
118`block_binding` is accepted alongside `thinking.type: "adaptive"` and `thinking.type: "enabled"`. Sending it without the beta header returns a 400 error whose message ends `block_binding: Extra inputs are not permitted`. Models that don't run the prefix check accept the object and report only model-check drops, so one request body works across models. The API reference calls the prefix check the conversation check.
130`block_binding` is accepted alongside `thinking.type: "adaptive"` and `thinking.type: "enabled"`. On Claude Sonnet 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. Sending it with `between_tools` returns a 400 error. Sending it without the beta header returns a 400 error whose message ends `block_binding: Extra inputs are not permitted`. Models that don't run the prefix check accept the object and report only model-check drops, so one request body works across models. The API reference calls the prefix check the conversation check.
119131
120132The following request opts into dropping rather than rejecting. On a first turn there's nothing to replay, so `input_transformations` comes back empty:
121133
from line 385
373385
374386Under the beta header, every response from a thinking-capable model carries `input_transformations`. Each entry names one thinking block by its `path` (for example `messages.1.content.0`) and gives a `reason`. There are two entry types:
375387
376* **`thinking_dropped`:** the API drops the block before the model reads it, and the block isn't billed. The `reason` is `prefix_binding_mismatch` or `model_binding_mismatch` (see [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)).
388* **`thinking_dropped`:** the API drops the block before the model reads it, and the block isn't billed. The `reason` is `prefix_binding_mismatch` or `model_binding_mismatch` (see [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). The `reason` can also be `organization_binding_mismatch`, which means the block came from another account (see [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking)).
377389* **`thinking_mismatch_allowed`:** the block fails the prefix check, but the API doesn't enforce that check for this request, so the block reaches the model unchanged and is billed. The `reason` is always `prefix_binding_mismatch`. This entry appears only on requests where the API doesn't enforce the check by default, such as those from an older account (see [When the API enforces the check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement)). Setting `prefix_mismatch_behavior` to either value opts the request into enforcement, so a request that sets it never gets this entry.
378390
379391The array is empty when no block was dropped and none failed the prefix check. Ignore entries whose `type` or `reason` you don't recognize, because later checks add values.
from line 394
382394
383395### When the API enforces the check
384396
385The API enforces the prefix check on Claude Fable 5.1 and Claude Opus 5.5 for new accounts.
397The API enforces the prefix check on Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 for new accounts.
386398
387* **Accounts created on or after August 31, 2026, 00:00 UTC:** the API checks Claude Fable 5.1 and Claude Opus 5.5 requests and applies `"error"` unless you set `"drop_block"`. The same definition of a new account applies to the Claude API and to cloud platforms.
399* **Accounts created on or after August 31, 2026, 00:00 UTC:** the API checks Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 requests and applies `"error"` unless you set `"drop_block"`. The same definition of a new account applies to the Claude API and to cloud platforms.
388400* **Older accounts:** the API enforces the check only on requests that set `prefix_mismatch_behavior`. Setting the field opts a request in, so you can see what a new account sees without creating one. On requests that leave it unset, the API still runs the check but lets failing blocks through to the model. With the beta header, the response lists each one in `input_transformations` as `thinking_mismatch_allowed`, so you can find prefix edits without changing what the model receives.
389401
390402To find out which group your account is in, take a Claude Fable 5.1 conversation that contains a thinking block, change something before that block, and send it to Claude Fable 5.1 without the beta header or the `block_binding` field. A 400 response that names the header means your account is enforced by default. A 200 response means it isn't. To confirm, send the same request again with the beta header, still without `block_binding`: the response lists every thinking block after your edit in `input_transformations` as `thinking_mismatch_allowed`.
from line 791
779791* **Empty on every turn of a session that contains `thinking` blocks:** your integration keeps the prefix intact.
780792* **`reason: "prefix_binding_mismatch"`:** something before the block at `path` changed since the previous request. Diff `system`, `tools`, and `messages` up to that turn to find it, or resend the request with `"error"`: the 400 usually ends with a sentence naming what changed. Then find the matching replacement in [Make changes without editing the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#replace-prefix-edits).
781793* **`reason: "model_binding_mismatch"`:** the conversation moved to a model that can't read the earlier model's blocks. This isn't a prefix edit. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
794* **`reason: "organization_binding_mismatch"`:** the block came from another account. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
782795
783796To see a failure on purpose, send a third turn from the earlier example and add a `system` prompt to that request only, so that it differs from the first two requests, which had none. With `"drop_block"`, the dropped count is no longer 0: the response has one entry for each thinking block in the history, each with `reason: "prefix_binding_mismatch"`. With `"error"`, the request returns the 400 described in [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior), and its last sentence names the `system` prompt. In the cURL and CLI tabs, remove the `jq` filter to see the error body. If the count is still 0, there was nothing to check: confirm that the model is claude-fable-5-1, that the request sets `block_binding`, that the history you sent contains `thinking` blocks, and that the first two requests had no `system` prompt.
784797
from line 1721
17081721 </Accordion>
17091722
17101723 <Accordion title="A saved session now fails on every request. How do I get it working again?">
1711 The stored history has an edit in it, so replaying it can't succeed. Send that session with `prefix_mismatch_behavior: "drop_block"` from now on, or remove its `thinking` and `redacted_thinking` blocks once and continue. Thinking the model produces from that point on stays valid as long as nothing before it changes again. Then find the edit so that new sessions don't hit it. See [Handle the error in code](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#handle-the-error-in-code).
1724 The stored history has an edit in it, so replaying it can't succeed. Send that session with `prefix_mismatch_behavior: "drop_block"` from now on, or remove its `thinking` and `redacted_thinking` blocks once and continue. On Claude Sonnet 5.5, `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. Thinking the model produces from that point on stays valid as long as nothing before it changes again. Then find the edit so that new sessions don't hit it. See [Handle the error in code](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#handle-the-error-in-code).
17121725 </Accordion>
17131726
17141727 <Accordion title="My harness can route a turn to a non-Claude model. Do those turns invalidate Claude's earlier thinking?">
from line 1729
17161729 </Accordion>
17171730
17181731 <Accordion title="Can I carry a conversation's reasoning into a new conversation?">
1719 Not into a different conversation. A thinking block is usable only when it follows the exact `system`, `tools`, and `messages` it was produced from. A branch that replays that history unchanged up to the fork point keeps its thinking. A conversation that starts from anything else can't use it, so start that conversation from a summary of the task state, as in [simple compaction](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#custom-compaction-on-the-client): the goal, decisions made, files and results so far, and the next step.
1732 Not into a different conversation. A thinking block is usable only when it follows the exact `system`, `tools`, and `messages` it was produced from. A branch that replays that history unchanged up to the fork point keeps its thinking. A conversation that starts from anything else can't use it, so start that conversation from a summary of the task state, as in [simple compaction](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#custom-compaction-on-the-client): the goal, decisions made, files and results so far, and the next step. Claude Sonnet 5.5's thinking blocks also can't be reused from another account (see [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking)).
17201733 </Accordion>
17211734</AccordionGroup>
17221735
build-with-claude/prompt-caching Changed · +4 / -3 lines
from line 245
245245| Claude Opus 4.5 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |
246246| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok |
247247| Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok |
248| Claude Sonnet 5.5 | $2 / MTok | $2.50 / MTok | $4 / MTok | $0.20 / MTok | $10 / MTok |
248249| Claude Sonnet 5 | $2 / MTok | $2.50 / MTok | $4 / MTok | $0.20 / MTok | $10 / MTok |
249250| Claude Sonnet 4.6 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |
250251| Claude Sonnet 4.5 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |
from line 603
602603
603604On the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), the minimum cacheable prompt length is:
604605
605* 512 tokens for Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Fable 5, and [Claude Mythos 5](https://anthropic.com/glasswing)
606* 512 tokens for Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Fable 5, and [Claude Mythos 5](https://anthropic.com/glasswing)
606607* 2,048 tokens for [Claude Mythos Preview](https://anthropic.com/glasswing) and Claude Opus 4.7
607608* 4,096 tokens for Claude Opus 4.6 and Claude Opus 4.5
608609* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations))
from line 667
666667| **Thinking parameters** | Model-specific | Model-specific | ✘ | The thinking configuration (mode, and `budget_tokens` in extended mode) is rendered into the prompt, so changing it always invalidates message blocks; tool and system caches are also invalidated on models that render the configuration ahead of them. See [Thinking and prompt caching](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-prompt-caching). |
667668| **Effort setting** | Model-specific | Model-specific | ✘ | Changing the [`output_config.effort`](https://platform.claude.com/docs/en/build-with-claude/effort) value always invalidates message blocks, with the same model-specific effect on tool and system caches as thinking parameters. Setting effort explicitly to the model's default is equivalent to omitting it and does not invalidate. On models that support [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta), an effort change carried in a `role: "system"` message inside `messages` leaves the cached prefix intact. |
668669| **Non-tool results passed to extended thinking requests** | ✓ | ✓ | Model-specific | On Opus 4.5+ and Sonnet 4.6+, thinking blocks are preserved by default, so the cache remains valid (✓). On earlier Opus/Sonnet models and all Haiku models, all previously-cached thinking blocks are stripped from context, and any messages that follow those thinking blocks are removed from the cache (✘). For more details, see [Caching with thinking blocks](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#caching-with-thinking-blocks). |
669| **Dropped thinking blocks** | ✓ | ✓ | ✘ | When the API drops a Claude Fable 5.1, Claude Mythos 5.1, or Claude Opus 5.5 thinking block that isn't [preserved](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking) on that request (for example, one you replay to a model that can't read it), the cached prefix changes from that block's position onward on that request. Blocks the receiving model can read, passed back unchanged, keep the cache intact. |
670| **Dropped thinking blocks** | ✓ | ✓ | ✘ | When the API drops a Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, or Claude Sonnet 5.5 thinking block that isn't [preserved](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking) on that request (for example, one you replay to a model that can't read it), the cached prefix changes from that block's position onward on that request. Blocks the receiving model can read, passed back unchanged, keep the cache intact. |
670671
671672On models that support [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), the `inline-tools-2026-09-15` beta header lets you add a tool, or change a tool's definition, partway through a conversation without editing `tools`. Send the definition in a `tool_addition` block in a mid-conversation system message and leave `tools` exactly as you first sent it. The cached prefix still matches, so only the appended message is processed as new input. The one exception is a `tools` array with no non-deferred tool, where the first tool defined this way costs one full cache miss on that request. See [Define tools in a message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta).
672673
673674<Note>
674 On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, and Claude Opus 5, you can add a new system instruction partway through a conversation without invalidating the system or message caches. Append a `{"role": "system"}` message to `messages` instead of editing the top-level `system` field, so the cached prefix stays unchanged. This feature is not available on Claude Sonnet 5. Use the top-level `system` field instead. See [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
675 On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, Claude Opus 5, and Claude Sonnet 5.5, you can add a new system instruction partway through a conversation without invalidating the system or message caches. Append a `{"role": "system"}` message to `messages` instead of editing the top-level `system` field, so the cached prefix stays unchanged. This feature is not available on Claude Sonnet 5. Use the top-level `system` field instead. See [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
675676</Note>
676677
677678### Tracking cache performance
build-with-claude/prompt-engineering/claude-prompting-best-practices Changed · +20 / -15 lines
### Migrating to Claude Sonnet 5.5 ### Migrating to Claude Sonnet 5 from Claude Sonnet 4.5 or earlier
from line 4
44description: Comprehensive guide to prompt engineering techniques for Claude's latest models, covering clarity, examples, XML structuring, thinking, and agentic systems.
55---
66
7This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 4.5. The page is organized in three parts:
7This is the reference for prompt engineering with current Claude models, including Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 4.5. The page is organized in three parts:
88
99* **[Model-specific guidance](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#model-specific-guidance)** first: where a single model behaves differently and what to change in your prompt.
1010* **Techniques for all current models** after that: general principles, output and formatting, tool use, thinking, and agentic systems.
from line 11
1111* **Migration considerations** last, for prompts moving from earlier generations.
1212
1313<Tip>
14 For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, 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 Claude Fable 5 capabilities and API changes, see [Introducing Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5). For details on what's new in Claude Sonnet 5, see [What's new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5). For migration guidance, see the [Migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide). For Claude Opus 5.5, see [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5).
14 For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, 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 Claude Fable 5 capabilities and API changes, see [Introducing Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5). For details on what's new in Claude Sonnet 5, see [What's new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5). For migration guidance, see the [Migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide). For Claude Opus 5.5, 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 Claude Sonnet 5.5, see [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5).
1515</Tip>
1616
1717## Model-specific guidance
from line 18
1818
1919Each of these models has its own prompting page. Read the one for your model first, then the techniques that follow.
2020
21| Model | Guide | What's different |
22| -------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
23| Claude Fable 5.1 and Claude Mythos 5.1 | [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1) | Differences from Claude Fable 5: effort levels, finishing long tasks, user-facing progress updates, passing thinking blocks back unchanged, tool-call batching in agent loops, search triggering at low effort, formatting, and writing density. |
24| Claude Fable 5 and Claude Mythos 5 | [Prompting Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5) | Differences from Claude Opus 4.8: effort levels, instruction following, long-run progress claims, memory systems, and the `reasoning_extraction` refusal category. |
25| Claude Sonnet 5 | [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5) | Differences from Claude Sonnet 4.6: response length, effort and thinking-depth calibration, tool use triggering, literal instruction following, and design and frontend defaults. |
26| Claude Opus 5.5 | [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5) | Differences from Claude Opus 5: effort calibration, prompts written for thinking disabled, user-facing progress updates, safeguard false positives, and tools for complex visual inputs. |
27| Claude Opus 5 | [Prompting Claude Opus 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5) | Differences from prior Opus models: response length and verbosity, user-facing progress updates, written deliverable length, task scope and over-verification, subagent control, and self-correction. |
28| Claude Opus 4.8 | [Prompting Claude Opus 4.8](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-4-8) | Response length, effort and thinking-depth calibration, tool use triggering, literal instruction following, subagent control, and design and frontend defaults. |
21| Model | Guide | What's different |
22| -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
23| Claude Fable 5.1 and Claude Mythos 5.1 | [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1) | Differences from Claude Fable 5: effort levels, finishing long tasks, user-facing progress updates, passing thinking blocks back unchanged, tool-call batching in agent loops, search triggering at low effort, formatting, and writing density. |
24| Claude Fable 5 and Claude Mythos 5 | [Prompting Claude Fable 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5) | Differences from Claude Opus 4.8: effort levels, instruction following, long-run progress claims, memory systems, and the `reasoning_extraction` refusal category. |
25| Claude Sonnet 5.5 | [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5) | Differences from Claude Sonnet 5: effort calibration, initiative and scope, running without up-front thinking, JSON output on reasoning tasks, user-facing progress updates, tool use in chat, mid-turn user messages, verification on coding tasks, tool-call handling, complex visual inputs, and safeguard refusals. |
26| Claude Sonnet 5 | [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5) | Differences from Claude Sonnet 4.6: response length, effort and thinking-depth calibration, tool use triggering, literal instruction following, and design and frontend defaults. |
27| Claude Opus 5.5 | [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5) | Differences from Claude Opus 5: effort calibration, prompts written for thinking disabled, user-facing progress updates, safeguard false positives, and tools for complex visual inputs. |
28| Claude Opus 5 | [Prompting Claude Opus 5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5) | Differences from prior Opus models: response length and verbosity, user-facing progress updates, written deliverable length, task scope and over-verification, subagent control, and self-correction. |
29| Claude Opus 4.8 | [Prompting Claude Opus 4.8](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-4-8) | Response length, effort and thinking-depth calibration, tool use triggering, literal instruction following, subagent control, and design and frontend defaults. |
2930
3031## General principles
3132
from line 773
772773 ```
773774</CodeGroup>
774775
775If you are not using extended thinking, no changes are required. On Claude Opus 4.6 through Claude Opus 4.8 and Claude Sonnet 4.6, thinking is off when you omit the `thinking` parameter. On Claude Opus 5 and Claude Sonnet 5, thinking is on by default when you omit the `thinking` parameter. On Claude Opus 5, you can disable it only at effort `high` or lower. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on, regardless of whether you set the `thinking` parameter.
776If you are not using extended thinking, no changes are required. On Claude Opus 4.6 through Claude Opus 4.8 and Claude Sonnet 4.6, thinking is off when you omit the `thinking` parameter. On Claude Opus 5, Claude Sonnet 5.5, and Claude Sonnet 5, thinking is on by default when you omit the `thinking` parameter. On Claude Opus 5, you can disable it only at effort `high` or lower. On Claude Sonnet 5.5, the lowest thinking setting is `between_tools`, accepted at effort `high` or lower. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on, regardless of whether you set the `thinking` parameter.
776777
777778* **Prefer general instructions over prescriptive steps.** A prompt like "think thoroughly" often produces better reasoning than a hand-written step-by-step plan. Claude's reasoning frequently exceeds what a human would prescribe.
778779* **Multishot examples work with thinking.** Use `<thinking>` tags inside your few-shot examples to show Claude the reasoning pattern. It will generalize that style to its own extended thinking blocks.
from line 1082
10811082
108210836. **Tune anti-laziness prompting:** If your prompts previously encouraged the model to be more thorough or use tools more aggressively, dial back that guidance. Claude 4.6 models are more proactive and may overtrigger on instructions that were needed for previous models.
10831084
10847. **Pass thinking blocks back unchanged and keep history append-only:** Append each assistant turn exactly as the API returned it, thinking blocks included. On Claude Fable 5.1 and Claude Opus 5.5, [modifying the conversation before a thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) results in an error, or in the block being dropped if you opt into that: editing earlier messages, rebuilding `system` or `tools`, or summarizing older turns in place between requests invalidates every later thinking block, so move those changes to mid-conversation system messages and server-side context management. See [Keep the conversation history append-only](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#keep-the-conversation-history-append-only).
10857. **Pass thinking blocks back unchanged and keep history append-only:** Append each assistant turn exactly as the API returned it, thinking blocks included. On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, [modifying the conversation before a thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) results in an error, or in the block being dropped if you opt into that: editing earlier messages, rebuilding `system` or `tools`, or summarizing older turns in place between requests invalidates every later thinking block, so move those changes to mid-conversation system messages and server-side context management. See [Keep the conversation history append-only](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#keep-the-conversation-history-append-only).
10851086
10861087For detailed migration steps, see the [Migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide).
10871088
1088### Migrating to Claude Sonnet 5 from Claude Sonnet 4.5 or earlier
1089### Migrating to Claude Sonnet 5.5
10891090
1090See [Migrating to Claude Sonnet 5 from Claude Sonnet 4.5 or earlier](https://platform.claude.com/docs/en/models/sonnet-5/migration-guide#migrating-from-sonnet-45) in the migration guide, which covers the effort default change and the removal of manual extended thinking (`budget_tokens`).
1091See the [Claude Sonnet 5.5 migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide). It covers the breaking changes for code written for Claude Sonnet 5 and the steps from Claude Sonnet 4.6 and earlier, including the removal of manual extended thinking (`budget_tokens`).
10911092
10921093## Next steps
10931094
from line 1099
10981099
10991100 <Card title="Prompting Claude Fable 5" icon="terminal" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5">
11001101 Behavioral differences and prompting patterns for Claude Fable 5 and Claude Mythos 5, covering effort, instruction following, long runs, memory, and scaffolding changes.
1102 </Card>
1103
1104 <Card title="Prompting Claude Sonnet 5.5" icon="terminal" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5">
1105 Behavioral differences and prompting patterns for Claude Sonnet 5.5, covering effort calibration, initiative and scope, running without up-front thinking, JSON output on reasoning tasks, progress updates, tool use, mid-turn user messages, coding verification, tool-call handling, visual inputs, and safeguard refusals.
11011106 </Card>
11021107
11031108 <Card title="Prompting Claude Sonnet 5" icon="terminal" href="https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5">
build-with-claude/refusals-and-fallback Changed · +7 / -7 lines
from line 1
11---
22title: Refusals and fallback
33url: https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback
4description: How Claude Fable and Claude Opus models return classifier refusals and how to retry refused requests on a fallback model.
4description: How Claude Fable models, Claude Opus models, and Claude Sonnet 5.5 return classifier refusals and how to retry refused requests on a fallback model.
55---
66
7Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, and Claude Opus 5 include safety classifiers that can decline a request. When that happens, you receive a normal response, not an error, with `stop_reason: "refusal"`. Its `stop_details.category` names the policy area (see [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response)). You can usually still get an answer by sending the same request to another Claude model. This page shows you how to recognize a refusal and how to set up that retry.
7Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5 include safety classifiers that can decline a request. When that happens, you receive a normal response, not an error, with `stop_reason: "refusal"`. Its `stop_details.category` names the policy area (see [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response)). You can usually still get an answer by sending the same request to another Claude model. This page shows you how to recognize a refusal and how to set up that retry.
88
99Read this page when you build on any of these models and want declined requests to fall through to another model automatically. It also applies when you have seen `"refusal"` in a response and want to know what to do next.
1010
from line 637
637637* Entries are tried in order. Each must be distinct from the other entries and from the requested model.
638638* Each entry must be one of the requested model's permitted targets. With the beta header set, that list is published as `allowed_fallback_models` on the model's entry in the [Models API](https://platform.claude.com/docs/en/api/models/list).
639639* Each entry names a `model` and can override `max_tokens`, `thinking`, `output_config`, and `speed` for that attempt only.
640* The request must be valid as a direct request to every model named. If a fallback model does not support a feature the request uses, the API rejects the request up front.
640* The request must be valid as a direct request to every model named. If a fallback model does not support a feature the request uses, the API rejects the request up front. Under the `2026-07-01` header, `thinking: {"type": "between_tools"}` is the exception: when a Claude Sonnet 5.5 request falls back to Claude Sonnet 5, the fallback attempt runs with `thinking: {"type": "disabled"}` and `display: "omitted"`. Under `2026-06-01`, set `thinking` on the Claude Sonnet 5 entry, or the request is rejected up front.
641641* As with the default mode, only a safety classifier decline triggers the fallback. A rate limit, overload, or server error on the requested model is returned to you as-is.
642642* If a fallback model is rate limited or overloaded, the fallback attempt is not made and the preceding refusal is returned instead. The refusal's `stop_details.recommended_model` then names a model to retry directly. Size the fallback model's rate limits for the refusal volume you expect, or fallbacks degrade to refusals under load.
643643
from line 1115
11151115
11161116* Retries walk your fallback list in order. A fallback model that itself refuses passes the request to the next entry.
11171117* When every model in the list has declined, the middleware returns the final refusal (the last model's refusal response) rather than raising an error.
1118* Thinking blocks from Claude Fable 5.1, Claude Opus 5.5, or Claude Fable 5 pass through unchanged. Each retry re-sends your original request body, and the only blocks the middleware removes from conversation history on later requests are the `fallback` boundary blocks it added itself. The fallback model can't read Claude Fable 5.1 blocks, which are [preserved only for that model or a newer one](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model), so the API drops them. The API also drops Claude Opus 5.5 blocks for every fallback model except Claude Fable 5.1 and Claude Mythos 5.1 (see [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)).
1118* Thinking blocks from Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, or Claude Fable 5 pass through unchanged. Each retry re-sends your original request body, and the only blocks the middleware removes from conversation history on later requests are the `fallback` boundary blocks it added itself. The fallback model can't read Claude Fable 5.1 blocks, which are [preserved only for that model or a newer one](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model), so the API drops them. The API also drops Claude Opus 5.5 blocks for every fallback model except Claude Fable 5.1 and Claude Mythos 5.1 (see [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). It drops Claude Sonnet 5.5 blocks too, because Claude Sonnet 5, its fallback model, can't read them.
11191119* Responses served through the middleware include a `fallback` content block at each model boundary, the same as server-side fallback responses. The middleware manages those blocks for you on later requests.
11201120* The model that accepted is recorded in `BetaFallbackState`, so follow-up requests that share the state stay pinned to it rather than re-asking a model that refused.
11211121
from line 1133
11331133 </Step>
11341134
11351135 <Step title="Re-send on a fallback model">
1136 Send the same request with `model` set to a fallback model, such as Claude Opus 4.8. Another model can normally serve a request that Claude Fable 5.1 or Claude Fable 5 declines. How you handle the conversation history depends on whether you redeem a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit):
1136 Send the same request with `model` set to a fallback model, such as Claude Opus 4.8. If the refused request sent `thinking: {"type": "between_tools"}`, change `thinking` first: only Claude Sonnet 5.5 accepts that value, so omit `thinking` or set a value the fallback model accepts. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) under the `2026-07-01` header makes this change for you when it falls back to Claude Sonnet 5. Another model can normally serve a request that Claude Fable 5.1 or Claude Fable 5 declines. How you handle the conversation history depends on whether you redeem a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit):
11371137
1138 * **Not redeeming a credit:** you can leave the earlier `thinking` and `redacted_thinking` blocks in place or strip them to save input tokens. The fallback model normally can't use them either way: it ignores Claude Fable 5 blocks, and Claude Fable 5.1 blocks are [preserved only for that model or a newer one](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model), so the API drops them. The API also drops Claude Opus 5.5 blocks for every fallback model except Claude Fable 5.1 and Claude Mythos 5.1 (see [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)).
1138 * **Not redeeming a credit:** you can leave the earlier `thinking` and `redacted_thinking` blocks in place or strip them to save input tokens. The fallback model normally can't use them either way: it ignores Claude Fable 5 blocks, and Claude Fable 5.1 blocks are [preserved only for that model or a newer one](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model), so the API drops them. The API also drops Claude Opus 5.5 blocks for every fallback model except Claude Fable 5.1 and Claude Mythos 5.1 (see [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). It drops Claude Sonnet 5.5 blocks too, because Claude Sonnet 5, its fallback model, can't read them.
11391139 * **Redeeming a credit:** send the body unchanged, because redemption requires an exact match. The server handles the earlier model's thinking blocks on a redemption, so do not strip them (see [Fields that must match the refused request](https://platform.claude.com/docs/en/build-with-claude/fallback-credit#reference)).
11401140 </Step>
11411141
build-with-claude/thinking Changed · +37 / -29 lines
from line 46
4646
4747On most models, thinking is on by default or one parameter away. The following table shows what each model does with each `thinking` value a request can send. A 400 error means the API rejects the request, and [Troubleshooting thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting) has each error and its fix.
4848
49| Model | No `thinking` field | `"adaptive"` | `"enabled"` with `budget_tokens` | `"disabled"` |
50| --------------------- | ------------------- | ----------------- | -------------------------------- | -------------------------------------- |
51| Claude Opus 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error |
52| Claude Fable 5.1 | Adaptive thinking | Adaptive thinking | 400 error | 400 error |
53| Claude Mythos 5.1 | Adaptive thinking | Adaptive thinking | 400 error | 400 error |
54| Claude Fable 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error |
55| Claude Mythos 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error |
56| Claude Opus 5 | Adaptive thinking | Adaptive thinking | 400 error | Thinking off at `high` effort or below |
57| Claude Sonnet 5 | Adaptive thinking | Adaptive thinking | 400 error | Thinking off |
58| Claude Opus 4.8 | Thinking off | Adaptive thinking | 400 error | Thinking off |
59| Claude Opus 4.7 | Thinking off | Adaptive thinking | 400 error | Thinking off |
60| Claude Mythos Preview | Adaptive thinking | Adaptive thinking | Extended thinking | 400 error |
61| Claude Opus 4.6 | Thinking off | Adaptive thinking | Extended thinking (deprecated) | Thinking off |
62| Claude Sonnet 4.6 | Thinking off | Adaptive thinking | Extended thinking (deprecated) | Thinking off |
63| Claude Opus 4.5 | Thinking off | 400 error | Extended thinking | Thinking off |
64| Claude Sonnet 4.5 | Thinking off | 400 error | Extended thinking | Thinking off |
65| Claude Haiku 4.5 | Thinking off | 400 error | Extended thinking | Thinking off |
49| Model | No `thinking` field | `"adaptive"` | `"enabled"` with `budget_tokens` | `"between_tools"` | `"disabled"` |
50| --------------------- | ------------------- | ----------------- | -------------------------------- | ----------------------------------------------- | -------------------------------------- |
51| Claude Opus 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
52| Claude Sonnet 5.5 | Adaptive thinking | Adaptive thinking | 400 error | Up-front thinking off at `high` effort or below | 400 error |
53| Claude Fable 5.1 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
54| Claude Mythos 5.1 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
55| Claude Fable 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
56| Claude Mythos 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
57| Claude Opus 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | Thinking off at `high` effort or below |
58| Claude Sonnet 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | Thinking off |
59| Claude Opus 4.8 | Thinking off | Adaptive thinking | 400 error | 400 error | Thinking off |
60| Claude Opus 4.7 | Thinking off | Adaptive thinking | 400 error | 400 error | Thinking off |
61| Claude Mythos Preview | Adaptive thinking | Adaptive thinking | Extended thinking | 400 error | 400 error |
62| Claude Opus 4.6 | Thinking off | Adaptive thinking | Extended thinking (deprecated) | 400 error | Thinking off |
63| Claude Sonnet 4.6 | Thinking off | Adaptive thinking | Extended thinking (deprecated) | 400 error | Thinking off |
64| Claude Opus 4.5 | Thinking off | 400 error | Extended thinking | 400 error | Thinking off |
65| Claude Sonnet 4.5 | Thinking off | 400 error | Extended thinking | 400 error | Thinking off |
66| Claude Haiku 4.5 | Thinking off | 400 error | Extended thinking | 400 error | Thinking off |
6667
6768In the table, "at `high` effort or below" means the request works at `low`, `medium`, and `high` effort and returns a 400 error at `xhigh` or `max`.
6869
69On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview, thinking is already on and needs no configuration. `display` defaults to `"omitted"` on these models, so the thinking text is hidden until you opt in. Opt in with `thinking: {"type": "adaptive", "display": "summarized"}`, which is exactly the following request with the [model string](https://platform.claude.com/docs/en/models/overview) swapped.
70On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview, thinking is already on and needs no configuration. `display` defaults to `"omitted"` on these models, so the thinking text is hidden until you opt in. Opt in with `thinking: {"type": "adaptive", "display": "summarized"}`, which is exactly the following request with the [model string](https://platform.claude.com/docs/en/models/overview) swapped.
7071
7172On Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6, thinking is off until you set `thinking: {type: "adaptive"}`, which lets Claude decide when and how deeply to think based on the request. The following examples do that, set `display: "summarized"` so the thinking text is visible, and use a roomy `max_tokens`:
7273
from line 461
460461
461462Claude Opus 5 also has thinking on by default and accepts `thinking: {type: "disabled"}` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. At `xhigh` or `max` effort, thinking cannot be turned off: requests that combine `thinking: {type: "disabled"}` with those effort levels return a 400 error. This restriction is enforced on each request. With thinking disabled, Claude Opus 5 can occasionally emit tool calls as plain text or include internal XML tags in its visible output. See [Running with thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5#running-with-thinking-disabled) for prompting mitigations.
462463
464Claude Sonnet 5.5 also has thinking on by default, and it rejects `thinking: {type: "disabled"}` with a 400 error. To turn off up-front thinking, send `thinking: {type: "between_tools"}` instead. It's the lowest thinking setting on Claude Sonnet 5.5, and it's accepted at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. The model still returns its [progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates). Without tools, the response contains only text, as with `disabled` on Claude Sonnet 5. 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) for prompting guidance.
465
463466Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, and Claude Mythos Preview reject `thinking: {type: "disabled"}`. Thinking can't be turned off on these models.
464467
465468If your model supports only extended thinking (see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#supported-models)), configure it with `type: "enabled"` and a `budget_tokens` value instead. The [Extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) page covers that configuration. And if any thinking configuration comes back with a 400 error, [Troubleshooting thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting) matches each error message to its fix.
from line 474
471474The `display` field on the thinking configuration controls how thinking content is returned in API responses. `display` works in both modes: set it alongside `type: "adaptive"` or `type: "enabled"`. It accepts these values:
472475
473476* `"summarized"`: thinking blocks contain [summarized thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#summarized-thinking) text, a readable summary of Claude's reasoning. This is the default on Claude Opus 4.6, Claude Sonnet 4.6, and earlier models.
474* `"omitted"`: thinking blocks are returned with an empty `thinking` field. The `signature` field still carries the encrypted full thinking for multi-turn continuity (see [Thinking encryption](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-encryption)). This is the default on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, and [Claude Mythos Preview](https://anthropic.com/glasswing).
477* `"omitted"`: thinking blocks are returned with an empty `thinking` field. The `signature` field still carries the encrypted full thinking for multi-turn continuity (see [Thinking encryption](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-encryption)). This is the default on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, and [Claude Mythos Preview](https://anthropic.com/glasswing).
475478* `"updates"` (beta): reasoning blocks are returned with an empty `thinking` field, as with `"omitted"`, and the short [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) some models write between tool calls come back as readable text. Requires the beta header `thinking-display-updates-2026-08-18`.
476479
477480Set `display: "omitted"` when your application doesn't surface thinking content to users. The primary benefit is faster time-to-first-text-token when streaming: the server skips streaming thinking tokens entirely and delivers only the signature, so the final text response begins streaming sooner.
from line 527
524527 In rare cases where you need access to full thinking output, [contact Anthropic sales](mailto:[email protected]).
525528</Note>
526529
527To see the model's reasoning, read the `thinking` blocks rather than prompting for reasoning in the response text. On Claude Fable 5.1, Claude Opus 5.5, and Claude Fable 5, a request that attempts to elicit the model's internal reasoning as part of the response text can be refused with `stop_details.category: "reasoning_extraction"`. See [Refusal categories](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the field reference and handling guidance.
530To see the model's reasoning, read the `thinking` blocks rather than prompting for reasoning in the response text. On Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Fable 5, a request that attempts to elicit the model's internal reasoning as part of the response text can be refused with `stop_details.category: "reasoning_extraction"`. See [Refusal categories](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the field reference and handling guidance.
528531
529532### Streaming thinking
530533
from line 893
890893
891894* **Lower cost or latency on a thinking-enabled workload:** lower `effort` first. It scales the whole response down, thinking included.
892895* **Claude is thinking too rarely or too shallowly:** raise `effort`, or see [Steering how often Claude thinks](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#tuning-thinking-behavior) on the steering page.
893* **You need thinking fully off:** use `thinking: {type: "disabled"}` on models that allow it (see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#supported-models)).
896* **You need thinking fully off:** use `thinking: {type: "disabled"}` on models that allow it (see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#supported-models)). Claude Sonnet 5.5 rejects `"disabled"`. Its lowest setting is `thinking: {type: "between_tools"}`, which turns off up-front thinking.
894897* **You need a hard ceiling on spend:** use `max_tokens`. Effort is soft guidance. `max_tokens` is a strict limit.
895898
896899## Thinking with tool use
from line 900
897900
898901Thinking works alongside [tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), letting Claude reason through tool selection and process tool results. Two constraints apply:
899902
9001. **Tool choice limitation (manual mode):** tool use with manual extended thinking (`thinking: {type: "enabled"}`) only supports `tool_choice: {"type": "auto"}` (the default) or `tool_choice: {"type": "none"}`. Using `tool_choice: {"type": "any"}` or `tool_choice: {"type": "tool", "name": "..."}` results in an error because these options force tool use, which is incompatible with manual extended thinking. Adaptive thinking, including on models where thinking is on by default, supports forced tool use, except on Claude Opus 5.5, Claude Fable 5.1, and Claude Mythos 5.1 (see [Response prefill and forced tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#limits-and-feature-compatibility)).
9031. **Tool choice limitation (manual mode):** tool use with manual extended thinking (`thinking: {type: "enabled"}`) only supports `tool_choice: {"type": "auto"}` (the default) or `tool_choice: {"type": "none"}`. Using `tool_choice: {"type": "any"}` or `tool_choice: {"type": "tool", "name": "..."}` results in an error because these options force tool use, which is incompatible with manual extended thinking. Adaptive thinking, including on models where thinking is on by default, supports forced tool use, except on Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 (see [Response prefill and forced tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#limits-and-feature-compatibility)).
9019042. **Preserving thinking blocks:** when you return tool results, you must pass the thinking blocks from the assistant message back to the API, complete and unmodified. See [Preserving thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks).
902905
903906**A tool-use loop is one assistant turn.** From the model's perspective, an assistant turn doesn't complete until Claude finishes its full response, which may include multiple tool calls and results. This whole sequence is a single assistant turn:
from line 964
961964 Consecutive tool calls do not require interleaved thinking. Claude can chain tool calls with or without interleaved thinking. Interleaving changes where thinking blocks appear between tool calls, not whether tool calls can chain.
962965</Note>
963966
964With adaptive thinking, interleaved thinking is automatic on every model that supports adaptive thinking. No beta header is needed. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7, reasoning between tool calls always appears in thinking blocks. Claude Haiku 4.5 does not support interleaved thinking. On models using manual extended thinking, interleaving requires a beta header and changes how the thinking budget is counted. [Interleaved thinking in manual mode](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#interleaved-thinking) covers the per-model rules and platform-specific header behavior.
967With adaptive thinking, interleaved thinking is automatic on every model that supports adaptive thinking. No beta header is needed. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Opus 4.8, and Claude Opus 4.7, reasoning between tool calls always appears in thinking blocks. Claude Haiku 4.5 does not support interleaved thinking. On models using manual extended thinking, interleaving requires a beta header and changes how the thinking budget is counted. [Interleaved thinking in manual mode](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#interleaved-thinking) covers the per-model rules and platform-specific header behavior.
965968
966969With interleaved thinking, the thinking allocation can span the entire assistant turn rather than a single response. Interleaved thinking is only supported for [tools used through the Messages API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
967970
from line 972
969972
970973### Progress updates between tool calls
971974
972On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, and Claude Fable 5, the model can write a progress update between tool calls. A progress update is a sentence or two on what the model just found and what it's about to do next, written for the person watching the agent rather than as reasoning. Each one comes back as its own `thinking` block with its own `signature`, separate from any reasoning block at the same point. It sits immediately before the `tool_use` or `server_tool_use` block it introduces. At most one progress update precedes each tool call, and the model can skip any of them. Progress updates aren't [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking): they appear whether or not reasoning blocks appear between tool calls, and a response can contain both.
975On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Fable 5, the model can write a progress update between tool calls. A progress update is a note on what the model just found and what it's about to do next, written for the person watching the agent rather than as reasoning. Each one comes back as its own `thinking` block with its own `signature`, separate from any reasoning block at the same point. It sits immediately before the `tool_use` or `server_tool_use` block it introduces. At most one progress update precedes each tool call, and the model can skip any of them. Progress updates aren't [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking): they appear whether or not reasoning blocks appear between tool calls, and a response can contain both.
973976
974977What a progress-update block contains depends on [`display`](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display):
975978
from line 982
979982| `"updates"` (beta) | Empty `thinking` field | Summary text |
980983| `"summarized"` | Summary text | Summary text, not distinguishable from a reasoning block |
981984
985On Claude Sonnet 5.5, the lowest thinking setting is `thinking: {type: "between_tools"}`. It turns off up-front thinking, and each progress update comes back with its summary text, as it would under `display: "updates"`. `between_tools` is accepted only at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. At `xhigh` or `max`, a request with it returns a 400 error. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. The setting needs no beta header and works on every platform that offers Claude Sonnet 5.5. Pass the blocks back unchanged: a progress-update block you send back gives the model the full note it wrote, not the summary.
986
982987Use `display: "updates"` for an agent interface that keeps reasoning hidden and shows the user a status line at each step. Under it, any `thinking` block with non-empty text is a progress update, so render those and nothing else. It's in beta and requires the beta header `thinking-display-updates-2026-08-18` (on Amazon Bedrock, Google Cloud, and Microsoft Foundry, pass the beta value as described in [Beta headers](https://platform.claude.com/docs/en/api/beta-headers)). Without it, the value is rejected with the same 400 `invalid_request_error` as an unknown `display` value.
983988
984989```json
from line 1046
10411046* A progress-update block can come back with an empty `thinking` field under any `display` value. Render nothing for an empty block. Under `"updates"` it looks the same as an empty reasoning block and needs no separate handling.
10421047* When a response stops on `max_tokens`, `model_context_window_exceeded`, or `stop_sequence` soon after a tool call or tool result, its last block can be a progress-update block standing in for the work the model hadn't finished. Under `"updates"` and `"summarized"` its text is exactly `This part of the response was interrupted before it finished.` and you can show it like any other update. Under `"omitted"` it's empty. To continue, pass the assistant turn back unchanged and append a new `user` message (with a `tool_result` for each `tool_use` block in that turn).
10431048* When [streaming](https://platform.claude.com/docs/en/build-with-claude/thinking#streaming-thinking), expect a pause of several seconds before a progress-update block opens. See the `"updates"` trace in [Streaming thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#streaming-thinking).
1044* These models write fewer progress updates at higher [effort](https://platform.claude.com/docs/en/build-with-claude/effort) and in long tool chains. If your interface depends on them, 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) or, for Claude Opus 5.5, [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates).
1049* These models write fewer progress updates at higher [effort](https://platform.claude.com/docs/en/build-with-claude/effort) and in long tool chains. If your interface depends on them, 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) or, for Claude Opus 5.5, [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates). For Claude Sonnet 5.5, see [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#user-facing-progress-updates).
10451050
10461051### Thinking block preservation by model
10471052
from line 1062
10571062
10581063The tradeoff is context usage: long conversations consume more context space on keep-all models, because retained thinking blocks count as input like any other conversation history (see [Thinking and the context window](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-the-context-window)). The behavior is automatic in both regimes. No code changes or beta headers are required, and you should keep passing complete, unmodified thinking blocks back as described in [Preserving thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks). To override the default in either direction, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing).
10591064
1060**Switching models mid-conversation.** Keep passing thinking blocks back unchanged when you switch models, for example after a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback). A thinking block is readable only by the model that produced it and certain other models, and the API ignores or drops the blocks the target model can't read. On Claude Fable 5.1 and Claude Mythos 5.1 the direction matters: they read every earlier model's thinking blocks and no earlier model reads theirs, so switching up to them keeps the conversation's reasoning and switching down drops it (see [how dropped blocks are billed and reported](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). Claude Opus 5.5 reads Claude Opus 5's thinking blocks and those of earlier Opus, Sonnet, and Haiku models, but not those of the Claude Fable and Claude Mythos models; on the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5's blocks. A switch from Claude Opus 5.5 up to Claude Fable 5.1 on the Claude API keeps the earlier turns' reasoning; a switch from Claude Fable 5.1 to Claude Opus 5.5 drops it. Strip prior `thinking` and `redacted_thinking` blocks yourself only to save input tokens on models that ignore rather than drop them, and never when redeeming a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit), which requires the body unchanged.
1065**Switching models mid-conversation.** Keep passing thinking blocks back unchanged when you switch models, for example after a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback). A thinking block is readable only by the model that produced it and certain other models, and the API ignores or drops the blocks the target model can't read. On Claude Fable 5.1 and Claude Mythos 5.1 the direction matters: they read every earlier model's thinking blocks and no earlier model reads theirs, so switching up to them keeps the conversation's reasoning and switching down drops it (see [how dropped blocks are billed and reported](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). Claude Opus 5.5 reads Claude Opus 5's thinking blocks and those of earlier Opus, Sonnet, and Haiku models, but not those of the Claude Fable and Claude Mythos models; on the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5's blocks. A switch from Claude Opus 5.5 up to Claude Fable 5.1 on the Claude API keeps the earlier turns' reasoning; a switch from Claude Fable 5.1 to Claude Opus 5.5 drops it. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. No other model reads its blocks, so a switch from Claude Sonnet 5.5 to any other model drops its reasoning. Strip prior `thinking` and `redacted_thinking` blocks yourself only to save input tokens on models that ignore rather than drop them, and never when redeeming a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit), which requires the body unchanged.
10611066
10621067## Preserved thinking
10631068
from line 1071
10661071* **The model that produced it.** Each model reads its own thinking blocks and those of a fixed set of other models. Claude Fable 5.1 reads blocks from Claude Opus 5 and, on the Claude API, from Claude Opus 5.5; neither Claude Opus 5 nor Claude Opus 5.5 reads blocks from Claude Fable 5.1. The API drops a block the current model can't read, without an error and without billing it. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
10671072* **Everything sent before it.** A block stays valid only while the top-level `system` prompt, the `tools`, and the messages before it are unchanged. If any of them changes, that block and every later thinking block are invalid, and the API rejects the request with a 400 error or drops the invalid blocks, whichever you choose. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
10681073
1074Claude Sonnet 5.5's thinking blocks are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) for where the API enforces this.
1075
10691076The model check applies to every account. The API enforces the prefix check by default for accounts created on or after August 31, 2026, 00:00 UTC. On older accounts it enforces the check only on requests that set `thinking.block_binding.prefix_mismatch_behavior`. Make your integration append-only regardless of your account's age, so the same code works on every account, including newer accounts enforced by default.
10701077
10711078To keep thinking valid, send every assistant turn back exactly as you received it and add new messages only at the end of `messages`. If your code builds the `messages` array itself, the Preserved thinking page covers:
from line 1086
10791086
10801087[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) interacts with thinking in a few specific ways. The following rules apply in both thinking modes.
10811088
1082**Configuration changes invalidate caching.** The thinking configuration and the resolved [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort) level are rendered into the prompt itself, so changing any of them starts a new cache prefix. Switching between `adaptive`, `enabled`, and `disabled`, changing `budget_tokens`, and changing the effort value all invalidate cache breakpoints: message-level breakpoints always miss, and tool and system-prompt breakpoints can miss too, depending on where the model renders the configuration. Treat any thinking or top-level effort change as starting the cache over. On models that support [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta), an effort change carried in a `role: "system"` message inside `messages` leaves the cached prefix intact. Consecutive requests that keep the same configuration preserve the cache, and setting a parameter explicitly to its default value is equivalent to omitting it. A thinking block the API drops under either [preserved-thinking condition](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking) changes the cached prefix from that block's position onward. Blocks passed back unchanged keep the cache intact. A worked demonstration with usage output is on the [Steering thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#prompt-caching) page.
1089**Configuration changes invalidate caching.** The thinking configuration and the resolved [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort) level are rendered into the prompt itself, so changing any of them starts a new cache prefix. Switching between `adaptive`, `enabled`, and `disabled`, changing `budget_tokens`, and changing the effort value all invalidate cache breakpoints: message-level breakpoints always miss, and tool and system-prompt breakpoints can miss too, depending on where the model renders the configuration. Treat any thinking or top-level effort change as starting the cache over. On models that support [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta), an effort change carried in a `role: "system"` message inside `messages` leaves the cached prefix intact. Consecutive requests that keep the same configuration preserve the cache, and setting a parameter explicitly to its default value is equivalent to omitting it. A thinking block the API drops under any [preserved-thinking condition](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking) changes the cached prefix from that block's position onward. Blocks passed back unchanged keep the cache intact. A worked demonstration with usage output is on the [Steering thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#prompt-caching) page.
10831090
10841091**Thinking blocks are cached with tool results.** During a tool-use loop, caching occurs when you make a follow-up request that includes tool results. At that point the previous conversation history, including its thinking blocks, can be cached, and those cached thinking blocks count as input tokens in your usage metrics when read from the cache. This occurs automatically, even without explicit `cache_control` markers, and behaves the same for regular and interleaved thinking. The tradeoff: thinking blocks you never see again in responses still contribute to input token usage when read from cache.
10851092
from line 1180
11731180
11741181### Sampling parameters
11751182
1176On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5, non-default `temperature`, `top_p`, or `top_k` values return a 400 error on every request, regardless of whether thinking is used. On older models, the restriction applies only while thinking is on: `temperature` and `top_k` are incompatible with thinking, and `top_p` is allowed at values between 0.95 and 1.
1183On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5.5, and Claude Sonnet 5, non-default `temperature`, `top_p`, or `top_k` values return a 400 error on every request, regardless of whether thinking is used. On older models, the restriction applies only while thinking is on: `temperature` and `top_k` are incompatible with thinking, and `top_p` is allowed at values between 0.95 and 1.
11771184
11781185### Response prefill and forced tool use
11791186
1180You can't prefill the assistant response while thinking is on. Forced tool use (`tool_choice: {"type": "any"}` or `{"type": "tool", ...}`) is incompatible with manual extended thinking but works with adaptive thinking. The exceptions are Claude Opus 5.5, Claude Fable 5.1, and Claude Mythos 5.1, which reject forced tool use on every request with a 400 error. On those models, use `tool_choice: {"type": "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) instead. See [Thinking with tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use).
1187You can't prefill the assistant response while thinking is on. Forced tool use (`tool_choice: {"type": "any"}` or `{"type": "tool", ...}`) is incompatible with manual extended thinking but works with adaptive thinking. The exceptions are Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1, which reject forced tool use on every request with a 400 error. On those models, use `tool_choice: {"type": "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) instead. See [Thinking with tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use).
11811188
11821189### Output limits
11831190
from line 1203
11961203| Claude Opus 4.7 | 128K | 300K |
11971204| Claude Opus 4.6 | 128K | 300K |
11981205| Claude Opus 4.5 | 64K | Not available |
1206| Claude Sonnet 5.5 | 128K | 300K |
11991207| Claude Sonnet 5 | 128K | 300K |
12001208| Claude Sonnet 4.6 | 128K | 300K |
12011209| Claude Sonnet 4.5 | 64K | Not available |
build-with-claude/thinking-troubleshooting Changed · +54 / -8 lines
## A 400 error says `"thinking.type.between_tools"` is not supported ## A 400 error says an effort level is not supported when thinking is disabled ## A 400 error says effort cannot change when thinking is disabled
from line 16
1616
1717Extended thinking (`thinking.type: "enabled"` with `budget_tokens`) is deprecated on the Claude 4.6 models (requests using it still succeed). Claude 4.7 and later models do not support it and reject requests that use it, returning a 400 error. On Claude 4.5 and earlier models that support thinking, extended thinking is the only available thinking mode. Claude Mythos Preview supports both modes. Where both modes are available, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) instead.
1818
19The table lists what each model supports, what it defaults to, and which `thinking.type` values it rejects with a 400 error; any value not listed as rejected is accepted.
19The table lists what each model supports, what it defaults to, and which `thinking.type` values it rejects with a 400 error; any value not listed as rejected is accepted. Only Claude Sonnet 5.5 accepts `"between_tools"`, and it takes that value in place of `"disabled"`.
2020
2121| Model | Thinking types | Default | Rejected with 400 |
2222| --------------------- | -------------------------------- | --------- | -------------------------- |
from line 29
2929| Claude Opus 5 | Adaptive only | On | `"enabled"`, `"disabled"`2 |
3030| Claude Opus 4.8 | Adaptive only | Off | `"enabled"` |
3131| Claude Opus 4.7 | Adaptive only | Off | `"enabled"` |
32| Claude Sonnet 5.5 | Adaptive, `between_tools`3 | On | `"enabled"`, `"disabled"` |
3233| Claude Sonnet 5 | Adaptive only | On | `"enabled"` |
3334| Claude Opus 4.6 | Adaptive, extended (deprecated)1 | Off | None |
3435| Claude Sonnet 4.6 | Adaptive, extended (deprecated)1 | Off | None |
from line 38
3738| Claude Sonnet 4.5 | Extended only | Off | `"adaptive"` |
3839
3940*1 `enabled` and `budget_tokens` still work on these models but are deprecated; use adaptive thinking instead.*\
40*2 Claude Opus 5 accepts `"disabled"` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below; combining it with effort `xhigh` or `max` returns a 400 error. This restriction is enforced on each request.*
41*2 Claude Opus 5 accepts `"disabled"` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below; combining it with effort `xhigh` or `max` returns a 400 error. This restriction is enforced on each request.*\
42*3 Claude Sonnet 5.5 accepts `"between_tools"` at effort `high` or below. Combining it with effort `xhigh` or `max` returns a 400 error, and so does a per-message effort that differs from the level in effect.*
4143
42Models marked `Always on` cannot turn thinking off. Models marked `On` default to thinking but accept `thinking: {type: "disabled"}`.
44Models marked `Always on` cannot turn thinking off. Models marked `On` default to thinking. Claude Opus 5 and Claude Sonnet 5 accept `thinking: {type: "disabled"}`. On Claude Sonnet 5.5, send `thinking: {type: "between_tools"}` to turn off up-front thinking.
4345
4446Earlier Claude 4 models (Claude Opus 4.1, Claude Sonnet 4, and Claude Opus 4) support extended thinking only. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) for their availability. Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5 are not available under [zero data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements) unless expressly authorized by Anthropic.
4547
from line 77
7577
7678A 400 error on `"disabled"` can also occur on Claude Opus 5, which accepts `thinking: {type: "disabled"}` only at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below: combining it with effort `xhigh` or `max` is rejected. Lower the effort level, or leave thinking on.
7779
80On Claude Sonnet 5.5, `thinking: {type: "disabled"}` returns a 400 error at every effort level. The message reads:
81
82```text wrap
83"thinking.type.disabled" is not supported for this model. Use "thinking.type.between_tools" for the lowest thinking setting, or "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.
84```
85
86To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {type: "between_tools"}` instead, at effort `high` or below.
87
88## A 400 error says `"thinking.type.between_tools"` is not supported
89
90The request fails with a 400 error whose message reads:
91
92```text wrap
93"thinking.type.between_tools" is not supported for this model.
94```
95
96This happens because only Claude Sonnet 5.5 accepts `thinking: {type: "between_tools"}` (see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#rejected-configurations)).
97
98Send `between_tools` only to Claude Sonnet 5.5. On other models, omit `thinking` or use a `thinking.type` value the table doesn't list as rejected.
99
100## A 400 error says an effort level is not supported when thinking is disabled
101
102On Claude Sonnet 5.5, a request with `thinking: {type: "between_tools"}` at effort `xhigh` or `max` fails with a 400 error whose message reads:
103
104```text wrap
105output_config.effort 'xhigh' is not supported when thinking is disabled on this model. Use effort 'high' or below, or enable thinking.
106```
107
108This happens because Claude Sonnet 5.5 accepts `between_tools` only at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. The message says thinking is disabled because `between_tools` has no up-front thinking, even though the request didn't send `"disabled"`. The message names the level the request sent.
109
110Lower the effort to `high` or below. To run at `xhigh` or `max`, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. That's what the message means by "enable thinking". Claude Sonnet 5.5 rejects `"enabled"` with a 400 error.
111
112## A 400 error says effort cannot change when thinking is disabled
113
114On Claude Sonnet 5.5, a request with `thinking: {type: "between_tools"}` whose [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) changes the level fails with a 400 error whose message reads:
115
116```text wrap
117messages.N: output_config.effort 'low' differs from the 'high' in effect before it; effort cannot change when thinking is disabled on this model. Use effort 'high', or enable thinking.
118```
119
120The message says thinking is disabled because `between_tools` has no up-front thinking. With `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. `messages.N` is the position of the message that set the new level.
121
122Remove that per-message effort, or set it to the level in effect. To vary effort per turn, use adaptive thinking, which is what the message means by "enable thinking".
123
78124## A 400 error says adaptive thinking is not supported
79125
80126The request fails with a 400 error whose message reads:
from line 147
101147
102148## A 400 error says a thinking block signature is invalid
103149
104A request to Claude Fable 5.1 or Claude Opus 5.5 that replays earlier thinking blocks fails with a 400 `invalid_request_error` whose message reads:
150A request to Claude Fable 5.1, Claude Opus 5.5, or Claude Sonnet 5.5 that replays earlier thinking blocks fails with a 400 `invalid_request_error` whose message reads:
105151
106152```text wrap
107153messages.{i}.content.{j}: Invalid `signature` in `thinking` block. The block is bound to a different conversation. Remove the block, or set `thinking.block_binding.prefix_mismatch_behavior` to "drop_block".
from line 159
113159
114160If the message stops after ``Invalid `signature` in `thinking` block``, the signature itself didn't verify: it was truncated, altered, or sent back empty, and `prefix_mismatch_behavior` doesn't apply. Edited thinking text returns a different error. See [A 400 error says thinking blocks cannot be modified](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-blocks-modified).
115161
116On Claude Fable 5.1 and Claude Opus 5.5, the API accepts a replayed thinking block only while the `system` prompt, `tools`, and messages that preceded it are unchanged. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check). The error means something earlier in the conversation changed between requests: an edited, reordered, or removed turn, a per-turn reminder that was injected and later removed, a rebuilt `system` prompt or `tools` array, or client-side compaction that kept recent turns and their thinking verbatim. The check is enforced for new accounts created on or after August 31, 2026, and for any request that sets `thinking.block_binding.prefix_mismatch_behavior`. Server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) and [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) never trigger it.
162On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, the API accepts a replayed thinking block only while the `system` prompt, `tools`, and messages that preceded it are unchanged. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check). The error means something earlier in the conversation changed between requests: an edited, reordered, or removed turn, a per-turn reminder that was injected and later removed, a rebuilt `system` prompt or `tools` array, or client-side compaction that kept recent turns and their thinking verbatim. The check is enforced for new accounts created on or after August 31, 2026, and for any request that sets `thinking.block_binding.prefix_mismatch_behavior`. Server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) and [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) never trigger it.
117163
118To fix it, keep the history append-only: pass earlier turns back exactly as sent and received, add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) instead of editing `system` or `tools`, and let 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) do any trimming. Retrying the same request body doesn't clear the error. To continue this request without the invalidated reasoning, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. Alternatively, strip every `thinking` and `redacted_thinking` block from the history (at minimum the named block and every one after it, in that turn and all later turns), leave each turn's other blocks in place, and retry once.
164To fix it, keep the history append-only: pass earlier turns back exactly as sent and received, add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) instead of editing `system` or `tools`, and let 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) do any trimming. Retrying the same request body doesn't clear the error. To continue this request without the invalidated reasoning, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. Alternatively, strip every `thinking` and `redacted_thinking` block from the history (at minimum the named block and every one after it, in that turn and all later turns), leave each turn's other blocks in place, and retry once. On Claude Sonnet 5.5, `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.
119165
120166A block from a model the target model can't read never produces this error: the API drops it and, under the beta header, reports it in `input_transformations`.
121167
claude_api_primer Changed · +4 / -2 lines
from line 14
1414Recommended default for most work, including complex agentic coding: Claude Opus 5.5: claude-opus-5-5
1515Step up for the hardest long-running agentic and research tasks, at 2.5x Claude Opus 5.5 pricing: Claude Fable 5.1: claude-fable-5-1
1616Previous Opus model: Claude Opus 5: claude-opus-5
17Smart model: Claude Sonnet 5: claude-sonnet-5
17Smart model: Claude Sonnet 5.5: claude-sonnet-5-5
18Previous Sonnet model: Claude Sonnet 5: claude-sonnet-5
1819For fast, cost-effective tasks: Claude Haiku 4.5: claude-haiku-4-5-20251001
1920```
2021
from line 245
244245Thinking is supported in the following models:
245246
246247* Claude Opus 5.5 (`claude-opus-5-5`, adaptive thinking only, always on)
248* Claude Sonnet 5.5 (`claude-sonnet-5-5`, adaptive thinking only, on by default)
247249* Claude Opus 5 (claude-opus-5, adaptive thinking only, on by default)
248250* Claude Sonnet 5 (`claude-sonnet-5`, adaptive thinking only, on by default)
249251* Claude Opus 4.8 (claude-opus-4-8, adaptive thinking only)
from line 627
625627* `tool` forces Claude to always use a particular tool.
626628* `none` prevents Claude from using any tools.
627629
628On Claude Opus 5.5, Claude Fable 5.1, and Claude Mythos 5.1, `any` and `tool` return a 400 error. Leave `tool_choice` at `auto` and set `"strict": true` on the tool definition to guarantee that any call Claude makes matches the tool's `input_schema`. See [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use).
630On Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1, `any` and `tool` return a 400 error. Leave `tool_choice` at `auto` and set `"strict": true` on the tool definition to guarantee that any call Claude makes matches the tool's `input_schema`. See [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use).
629631
630632### JSON output
631633
managed-agents/reference Changed · +3 / -3 lines
from line 76
7676 </Tab>
7777
7878 <Tab title="System events">
79 | Type | Description |
80 | ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
81 | `system.message` | Append privileged system-level context that applies to the accompanying turn and all subsequent turns. Supported on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8. On an unsupported primary model the event is rejected with `model_does_not_support_mid_conversation_system`. |
79 | Type | Description |
80 | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
81 | `system.message` | Append privileged system-level context that applies to the accompanying turn and all subsequent turns. Supported on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Sonnet 5.5. On an unsupported primary model the event is rejected with `model_does_not_support_mid_conversation_system`. |
8282 </Tab>
8383
8484 <Tab title="Event deltas">
models/fable-5-1/overview Changed · +7 / -7 lines
from line 28
2828
2929## How it compares
3030
31| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
32| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |
33| **Claude Fable 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
34| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
35| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |
36| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |
31| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
32| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |
33| **Claude Fable 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
34| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
35| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
36| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |
3737
3838* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
39* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
39* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
4040* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5). See Pricing for the full list.
4141* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
4242* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
models/fable-5/overview Changed · +8 / -8 lines
from line 20
2020
2121## How it compares to the current lineup
2222
23| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
24| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |
25| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
26| **Claude Fable 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026 |
27| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
28| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jan 2026 |
29| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |
23| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
24| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |
25| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
26| **Claude Fable 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026 |
27| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
28| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
29| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |
3030
3131* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
32* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
32* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
3333* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5). See Pricing for the full list.
3434* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3535* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/haiku-4-5/overview Changed · +7 / -7 lines
from line 16
1616
1717## How it compares
1818
19| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
20| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
22| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
23| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |
24| **Claude Haiku 4.5** (this model) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |
19| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
20| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
22| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
23| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
24| **Claude Haiku 4.5** (this model) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |
2525
2626* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
27* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
27* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
2828* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5). See Pricing for the full list.
2929* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
models/mythos-5-1/overview Changed · +8 / -8 lines
from line 18
1818
1919## How it compares
2020
21| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
22| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |
23| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
24| **Claude Mythos 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
25| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
26| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jan 2026 |
27| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |
21| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
22| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------- | :------------------- | :------------- | :--------------- |
23| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
24| **Claude Mythos 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
25| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
26| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
27| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Fastest | Extended | — | Feb 2025 |
2828
2929* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
30* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
30* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
3131* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5). See Pricing for the full list.
3232* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3333* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
models/mythos-5/overview Changed · +8 / -8 lines
from line 18
1818
1919## How it compares
2020
21| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
22| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |
23| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
24| **Claude Mythos 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026 |
25| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
26| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jan 2026 |
27| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |
21| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
22| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |
23| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
24| **Claude Mythos 5** (this model) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jan 2026 |
25| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
26| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
27| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |
2828
2929* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
30* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
30* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
3131* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5). See Pricing for the full list.
3232* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3333* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/opus-4-5/overview Changed · +8 / -8 lines
from line 16
1616
1717## How it compares to the current lineup
1818
19| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
20| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
22| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
23| **Claude Opus 4.5** (this model) | 200K | 64K | $5 / $25 | Extended | `high` | May 2025 |
24| [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jan 2026 |
25| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |
19| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
20| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
22| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
23| **Claude Opus 4.5** (this model) | 200K | 64K | $5 / $25 | Extended | `high` | May 2025 |
24| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
25| [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) | 200K | 64K | $1 / $5 | Extended | — | Feb 2025 |
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
28* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
28* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
2929* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.