Follow Discord
Sweep 02 Oct 2026 · 18:55Z Build v2.1.288 509 read Stable v2.1.285 Latest v2.1.288 Next v2.1.288 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform
One capture · api

One read of Claude Developer Platformapi-20260930T233759Z

343 pages moved out of 740 read.

Pages moved 343 significant first
Pages read 740 in this capture
Captured 23:37 UTC
Corpus hash 1974d9bc7c5a index-hash

What this read moved

326-343 of 343, page 14 of 14

This capture is too large to show at once. Changes 326-343 of 343 are below, significant first; the rest are on the following screens.

api/beta/vaults/list Changed · +2 / -0 lines

from line 129
129129 
130130 - `"mcp-client-2026-09-15"`
131131 
132 - `"ce-plugins-2026-09-01"`
133 
132134- `"anthropic-workspace-id": optional string`
133135 
134136 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).

api/beta/vaults/retrieve Changed · +2 / -0 lines

from line 119
119119 
120120 - `"mcp-client-2026-09-15"`
121121 
122 - `"ce-plugins-2026-09-01"`
123 
122124- `"anthropic-workspace-id": optional string`
123125 
124126 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).

api/beta/vaults/update Changed · +2 / -0 lines

from line 119
119119 
120120 - `"mcp-client-2026-09-15"`
121121 
122 - `"ce-plugins-2026-09-01"`
123 
122124- `"anthropic-workspace-id": optional string`
123125 
124126 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).

api/completions Changed · +2 / -0 lines

from line 127
127127 
128128 - `"mcp-client-2026-09-15"`
129129 
130 - `"ce-plugins-2026-09-01"`
131 
130132### Body parameters
131133 
132134- `max_tokens_to_sample: number`

api/completions/create Changed · +2 / -0 lines

from line 125
125125 
126126 - `"mcp-client-2026-09-15"`
127127 
128 - `"ce-plugins-2026-09-01"`
129 
128130## Body parameters
129131 
130132- `max_tokens_to_sample: number`

api/errors Changed · +1 / -1 lines

from line 490
490490On 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:
491491 
492492```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.
493To turn thinking off on this model, send "thinking": {"type": "between_tools"} instead of {"type": "disabled"}. The model does not think before responding. The short updates it writes between tool calls come back as thinking blocks.
494494```
495495 
496496At `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:

api/models Changed · +4 / -0 lines

from line 143
143143 
144144 - `"mcp-client-2026-09-15"`
145145 
146 - `"ce-plugins-2026-09-01"`
147 
146148### Returns
147149 
148150- `data: array of ModelInfo`
from line 505
503505 - `"inline-tools-2026-09-15"`
504506 
505507 - `"mcp-client-2026-09-15"`
508 
509 - `"ce-plugins-2026-09-01"`
506510 
507511### Returns
508512 

api/models/list Changed · +2 / -0 lines

from line 141
141141 
142142 - `"mcp-client-2026-09-15"`
143143 
144 - `"ce-plugins-2026-09-01"`
145 
144146## Returns
145147 
146148- `data: array of ModelInfo`

api/models/retrieve Changed · +2 / -0 lines

from line 129
129129 
130130 - `"mcp-client-2026-09-15"`
131131 
132 - `"ce-plugins-2026-09-01"`
133 
132134## Returns
133135 
134136- `ModelInfo object`

build-with-claude/refusals-and-fallback Changed · +2 / -2 lines

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, 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.
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, for every fallback model except Claude Opus 5.5 on the Claude API.
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 1135
11351135 <Step title="Re-send on a fallback model">
11361136 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)). It drops Claude Sonnet 5.5 blocks too, because Claude Sonnet 5, its fallback model, can't read them.
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, for every fallback model except Claude Opus 5.5 on the Claude API.
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 · +1 / -1 lines

from line 1070
10701070 
10711071The 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).
10721072 
1073**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.
1073**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. On the Claude API, Claude Opus 5.5 reads Claude Sonnet 5.5's blocks and no other model does: a switch from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API keeps the earlier turns' reasoning, and any other switch away from Claude Sonnet 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.
10741074 
10751075## Preserved thinking
10761076 

manage-claude/access-transparency Changed · +2 / -2 lines

from line 27
2727 
2828## What Access Transparency covers
2929 
30* **Covered content:** Access Transparency covers prompt and response content sent through the Claude Messages API or Claude Code sessions. Anthropic's [general ZDR documentation](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention) and [ZDR for Claude Code documentation](https://code.claude.com/docs/en/zero-data-retention) explain which APIs and features are covered by ZDR. The same APIs and features are covered by Access Transparency.
30* **Covered content:** Access Transparency covers prompt and response content sent through the Claude Messages API or Claude Code sessions. Anthropic's [general ZDR documentation](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention) explains which APIs and features are covered by ZDR. The same APIs and features are covered by Access Transparency.
3131* **Manual views by Anthropic personnel:** Manual views of your covered content by Anthropic reviewers generate events.
3232 
3333## What Access Transparency does not cover
from line 37
3737* **Claude for Enterprise and Claude Apps:** claude.ai Enterprise seats, Claude for Work, Cowork, and Claude in Chrome are not covered.
3838* **Claude consumer products:** Claude Free, Pro, or Max plans.
3939* **Partner-operated platforms:** Amazon Bedrock and Google Cloud; refer to those platforms' transparency controls.
40* **Anything ZDR does not cover:** Products that are not covered by ZDR (for example, the Files API, Anthropic-hosted stateful applications, and the Batch API) are not covered by Access Transparency. See [ZDR documentation](https://code.claude.com/docs/en/zero-data-retention#what-zdr-does-not-cover) for additional details.
40* **Anything ZDR does not cover:** Products that are not covered by ZDR (for example, the Files API, Anthropic-hosted stateful applications, and the Batch API) are not covered by Access Transparency. See [ZDR documentation](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) for additional details.
4141 
4242## Getting started
4343 

managed-agents/define-outcomes Changed · +1 / -0 lines

from line 199
199199 import com.anthropic.models.beta.agents.BetaManagedAgentsAgentToolset20260401Params;
200200 import com.anthropic.models.beta.agents.BetaManagedAgentsModel;
201201 import com.anthropic.models.beta.environments.BetaCloudConfigParams;
202 import com.anthropic.models.beta.environments.BetaLimitedNetworkParams;
202203 import com.anthropic.models.beta.environments.EnvironmentCreateParams;
203204 import com.anthropic.models.beta.files.FileListParams;
204205 import com.anthropic.models.beta.sessions.SessionCreateParams;

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

from line 286
286286* Set `effort` explicitly: the default is `medium`, where Claude Opus 5's is `high`.
287287* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
288288* If you use computer use on the Claude API or Google Cloud, declare `computer_toolset_20260801` (no beta header) instead of `computer_20251124` and update your agent loop for the toolset. On Amazon Bedrock, keep `computer_20251124`; check the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section for other platforms.
289* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5's thinking blocks (Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them). Claude Opus 5.5 itself reads thinking from Claude Opus 5 and earlier Opus, Sonnet, and Haiku models, but not from Claude Fable or Claude Mythos models.
289* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5's thinking blocks (Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them). Claude Opus 5.5 itself reads thinking from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models.
290290* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.
291291* If your interface renders text between tool calls, set `display: "updates"` (beta) or `"summarized"` and render the non-empty `thinking` blocks.
292292* If your code edits earlier turns, the `system` prompt, or `tools` mid-conversation, follow [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
from line 884
884884 
885885#### Thinking blocks are tied to the model and the conversation
886886 
887On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks; no other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In the other direction, Claude 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. Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid; Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. Enforcement matches Claude Fable 5.1 on every platform: for accounts created on or after August 31, 2026, 00:00 UTC, replaying a thinking block after such an edit returns a 400 error by default. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
887On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks; no other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In the other direction, Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models. Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid; Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. Enforcement matches Claude Fable 5.1 on every platform: for accounts created on or after August 31, 2026, 00:00 UTC, replaying a thinking block after such an edit returns a 400 error by default. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
888888 
889889#### The `computer_20251124` computer use tool is not supported on the Claude API and Google Cloud
890890 

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

from line 44
4444 
4545### Thinking blocks are tied to the model and the conversation
4646 
47Every thinking block records which model produced it, and each model reads its own blocks and only some other models'. Claude Opus 5.5 reads thinking blocks from Claude Opus 5 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. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two, or onto it from a Claude Fable or Claude Mythos model, runs the turns after the switch without the previous model's reasoning. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
47Every thinking block records which model produced it, and each model reads its own blocks and only some other models'. Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two, or onto it from a Claude Fable or Claude Mythos model, runs the turns after the switch without the previous model's reasoning. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
4848 
4949The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. As on Claude Fable 5.1, it enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms. On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. Keep the conversation append-only so the question never arises: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide's [note on this change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).
5050 

models/overview Changed · +1 / -1 lines

from line 61
6161 
6262See [Model IDs and versioning](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions) and [Pricing](https://platform.claude.com/docs/en/about-claude/pricing).
6363 
64Legacy models (still available): [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview).
64Legacy models (still available): [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview).
6565 
6666Once you've picked a model, [learn how to make your first API call](https://platform.claude.com/docs/en/get-started). To understand how model IDs, aliases, and snapshots work, see [Model IDs and versioning](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions); for the reliable-knowledge and training-data cutoffs behind each model, see [Anthropic's Transparency Hub](https://www.anthropic.com/transparency).
6767 

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

from line 242
242242To turn off up-front thinking on Claude Sonnet 5.5, send `thinking: {"type": "between_tools"}`. It's the lowest thinking setting. Its progress updates between tool calls still come back as `thinking` blocks with their summary text. Without tools, the response contains only text. Claude Sonnet 5 turns thinking off with `thinking: {"type": "disabled"}` instead, and earlier models run without thinking by default. On Claude Sonnet 5.5, `disabled` returns a 400 `invalid_request_error`:
243243 
244244```text wrap
245"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.
245To turn thinking off on this model, send "thinking": {"type": "between_tools"} instead of {"type": "disabled"}. The model does not think before responding. The short updates it writes between tool calls come back as thinking blocks.
246246```
247247 
248248`between_tools` works on every platform that offers Claude Sonnet 5.5, with no beta header. It's accepted at `low`, `medium`, and `high` effort. At `xhigh` or `max`, it returns a 400 error. To run at those levels, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. With [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), a `between_tools` request that falls back to Claude Sonnet 5 runs there with `thinking: {"type": "disabled"}`.

models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +2 / -2 lines

from line 48
4848 
4949### Thinking blocks are tied to the model and the conversation
5050 
51Every thinking block records which model produced it. Each model reads its own blocks and only some other models' blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. No other model reads Claude Sonnet 5.5 thinking blocks.
51Every thinking block records which model produced it. Each model reads its own blocks and only some other models' blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API, Claude Opus 5.5 reads Claude Sonnet 5.5 thinking blocks; no other model does.
5252 
53So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5 keeps its reasoning, and one that moves from Claude Sonnet 5.5 to any other model runs the turns after the switch without it. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
53So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5, or from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API, keeps its reasoning, and any other move away from Claude Sonnet 5.5 runs the turns after the switch without it. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
5454 
5555The API also checks whether anything before a Claude Sonnet 5.5 thinking block has changed since the block was produced: the `system` prompt, the `tools`, or an earlier message. It enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API, Amazon Bedrock, and Google Cloud. On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, keep the history append-only, or strip the thinking blocks from the edited turn on.
5656 
Feedback