One read of Claude Developer Platformapi-20261022T213726Z
115 pages moved out of 808 read.
Pages moved
115
significant first
Pages read
808
in this capture
Captured
21:37 UTC
Corpus hash
7969d7d723dd
corpus-hash
What this read moved
26-50 of 115, page 2 of 5This capture is too large to show at once. Changes 26-50 of 115 are below, significant first; the rest are on the following screens.
build-with-claude/prompt-caching Changed · +18 / -24 lines
from line 590
590590
591591### Cache limitations
592592
593On 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:
593On the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), the minimum cacheable prompt length is:
594594
595595* 512 tokens for Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), and Claude Haiku 5.5
596596* 2,048 tokens for [Claude Mythos Preview](https://anthropic.com/glasswing) and Claude Opus 4.7
597597* 4,096 tokens for Claude Opus 4.6 and Claude Opus 4.5
598* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), 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))
598* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4.1 ([retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Sonnet 4 ([retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations))
599599* 4,096 tokens for Claude Haiku 4.5
600* 2,048 tokens for Claude Haiku 3.5 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations))
600* 2,048 tokens for Claude Haiku 3.5 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations))
601601
602602These minimums apply on every platform where each model is available.
603603
from line 746
746746### Cache storage and sharing
747747
748748<Warning>
749 Prompt caching uses [workspace](https://platform.claude.com/docs/en/manage-claude/workspaces)-level isolation. Caches are isolated per workspace, ensuring data separation between workspaces within the same organization. This applies to the Claude API, Claude Platform on AWS, and Microsoft Foundry; Bedrock and Google Cloud maintain organization-level cache isolation. If you use multiple workspaces, review your caching strategy to account for this difference.
749 Prompt caching uses [workspace](https://platform.claude.com/docs/en/manage-claude/workspaces)-level isolation. Caches are isolated per workspace, ensuring data separation between workspaces within the same organization. This applies to the Claude API, Claude Platform on AWS, and Microsoft Foundry; Bedrock and Claude Models on Google Cloud (Google managed) maintain organization-level cache isolation. If you use multiple workspaces, review your caching strategy to account for this difference.
750750</Warning>
751751
752* **Organization and workspace isolation:** Caches are isolated between organizations. Different organizations never share caches, even if they use identical prompts. Caches are also isolated per workspace within an organization on the Claude API, Claude Platform on AWS, and Microsoft Foundry; Bedrock and Google Cloud use organization-level isolation only.
752* **Organization and workspace isolation:** Caches are isolated between organizations. Different organizations never share caches, even if they use identical prompts. Caches are also isolated per workspace within an organization on the Claude API, Claude Platform on AWS, and Microsoft Foundry; Bedrock and Claude Models on Google Cloud (Google managed) use organization-level isolation only.
753753
754754* **Exact matching:** Cache hits require 100 percent identical prompt segments, including all text and images up to and including the block marked with cache control.
755755
from line 805
805805If you find that 5 minutes is too short, Anthropic also offers a 1-hour cache duration [at additional cost](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing).
806806
807807<Note>
808 The 1-hour cache duration is available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [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).
808 The 1-hour cache duration is available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry).
809809</Note>
810810
811811To use the extended cache, include `ttl` in the `cache_control` definition like this:
from line 2076
20762076 Messages: []anthropic.MessageParam{
20772077 anthropic.NewUserMessage(anthropic.NewTextBlock("Hello, can you tell me more about the solar system?")),
20782078 anthropic.NewAssistantMessage(anthropic.NewTextBlock("Certainly! The solar system is the collection of celestial bodies that orbit our Sun. It consists of eight planets, numerous moons, asteroids, comets, and other objects. The planets, in order from closest to farthest from the Sun, are: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, and Neptune. Each planet has its own unique characteristics and features. Is there a specific aspect of the solar system you would like to know more about?")),
2079 {OfUser: &anthropic.UserMessageParam{
2080 Content: []anthropic.ContentBlockParamUnion{
2081 anthropic.NewTextBlock("Good to know."),
2082 {OfText: &anthropic.TextBlockParam{
2083 Text: "Tell me more about Mars.",
2084 CacheControl: anthropic.NewCacheControlEphemeralParam(),
2085 }},
2086 },
2087 }},
2079 anthropic.NewUserMessage(
2080 anthropic.NewTextBlock("Good to know."),
2081 anthropic.ContentBlockParamUnion{OfText: &anthropic.TextBlockParam{
2082 Text: "Tell me more about Mars.",
2083 CacheControl: anthropic.NewCacheControlEphemeralParam(),
2084 }},
2085 ),
20882086 },
20892087 })
20902088 if err != nil {
from line 2784
27862784 false,
27872785 )),
27882786 anthropic.NewAssistantMessage(anthropic.NewTextBlock("I found 3 relevant documents about Mars rovers. Let me get more details from the Mars Exploration document.")),
2789 {OfUser: &anthropic.UserMessageParam{
2790 Content: []anthropic.ContentBlockParamUnion{
2791 {OfText: &anthropic.TextBlockParam{
2792 Text: "Yes, please tell me about the Perseverance rover specifically.",
2793 CacheControl: anthropic.NewCacheControlEphemeralParam(),
2794 }},
2795 },
2796 }},
2787 anthropic.NewUserMessage(anthropic.ContentBlockParamUnion{OfText: &anthropic.TextBlockParam{
2788 Text: "Yes, please tell me about the Perseverance rover specifically.",
2789 CacheControl: anthropic.NewCacheControlEphemeralParam(),
2790 }}),
27972791 },
27982792 })
27992793 if err != nil {
from line 3269
32753269
32763270 1. Cache keys are generated using a cryptographic hash of the prompts up to the cache control point. This means only requests with identical prompts can access a specific cache.
32773271
3278 2. On the Claude API, Claude Platform on AWS, and Microsoft Foundry, caches are isolated per workspace within an organization. On Bedrock and Google Cloud, caches are isolated per organization. In every case, caches are never shared across organizations, even for identical prompts. See [Cache storage and sharing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-storage-and-sharing) for details.
3272 2. On the Claude API, Claude Platform on AWS, and Microsoft Foundry, caches are isolated per workspace within an organization. On Bedrock and Claude Models on Google Cloud (Google managed), caches are isolated per organization. In every case, caches are never shared across organizations, even for identical prompts. See [Cache storage and sharing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-storage-and-sharing) for details.
32793273
32803274 3. The caching mechanism is designed to maintain the integrity and privacy of each unique conversation or context.
32813275
build-with-claude/refusals-and-fallback Changed · +10 / -10 lines
from line 15
1515* [SDK middleware](https://platform.claude.com/docs/en/cli-sdks-libraries/middleware): the SDK helper that wraps all of this
1616* [Fallback and billing recipe](https://platform.claude.com/cookbook/fable-5-fallback-billing-guide): a worked end-to-end example
1717
18The simplest setup, in beta on the Claude API: set `fallbacks` to `"default"`, and the API retries a declined request on the fallback model Anthropic recommends for its refusal category. For categories with no recommended fallback, the refusal stands. Claude Haiku 5.5 has no server-side fallback, so for it use [client-side fallback with the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) or [write the retry yourself](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#manual-retry).
18The simplest setup, in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed): set `fallbacks` to `"default"`, and the API retries a declined request on the fallback model Anthropic recommends for its refusal category. For categories with no recommended fallback, the refusal stands. Claude Haiku 5.5 has no server-side fallback, so for it use [client-side fallback with the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) or [write the retry yourself](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#manual-retry).
1919
2020<CodeGroup>
2121 ```bash cURL
from line 205
205205
206206## How refusals are billed
207207
208These billing rules apply on every platform: the Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
208These billing rules apply on every platform.
209209
210210**Refusals before any output:** To disrupt attempts to circumvent Anthropic's safeguards at scale, a refusal that arrives before any output is billed when its `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. These are the categories where Anthropic measures low volumes of false positives, as of September 2026. These refusals are billed like any other request, at the rates of the model that ran it. A refusal before any output in any other category, or with a `null` category, is not billed. Either way, `content` is empty and token counts appear in `usage`. The request still counts against your rate limits.
211211
from line 219
219219
220220There are three ways to retry a refused request on another model. The right one depends on where you are running and how much control you need.
221221
222| Your situation | Use | Why |
223| ------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- |
224| Claude API, simplest setup | [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) | One request, one response. The API handles the retry. |
225| Any platform, using an Anthropic SDK | [The SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) | Configure once on the client. Retries happen automatically. |
226| Raw HTTP or custom retry logic | [A manual retry](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#manual-retry) with [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) | Full control. Fallback credit keeps the cost down. |
222| Your situation | Use | Why |
223| ------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- |
224| Claude API or Claude Models on Google Cloud (Anthropic managed), simplest setup | [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) | One request, one response. The API handles the retry. |
225| Any platform, using an Anthropic SDK | [The SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) | Configure once on the client. Retries happen automatically. |
226| Raw HTTP or custom retry logic | [A manual retry](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#manual-retry) with [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) | Full control. Fallback credit keeps the cost down. |
227227
228228Server-side fallback and the SDK middleware apply fallback credit for you. You only need the [Fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) page when you build the retry yourself. Claude Haiku 5.5 has neither server-side fallback nor fallback credit, so use the SDK middleware or a manual retry.
229229
from line 232
232232Server-side fallback retries a refused request inside a single API call. In the default mode, when the primary model declines and the refusal category has a recommended fallback, the API runs the same request on the model Anthropic recommends for that category. You can instead [name up to three fallback models of your own](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#naming-your-own-fallback-models). Either way, you get back one response that names the model that answered, so your user gets an answer in one round trip.
233233
234234<Note>
235 Server-side fallback is in beta on the Claude API. The `fallbacks` parameter is not supported on the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing) (a batch item that includes it comes back as an errored result) and is not available on Amazon Bedrock, Google Cloud, or Microsoft Foundry. On those platforms, use [client-side fallback with the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead. Claude Haiku 5.5 has no server-side fallback: with `fallbacks: "default"`, a declined request stays declined, and a list of fallback models returns a 400 error.
235 Server-side fallback is in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). On platforms without server-side fallback, use [client-side fallback with the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead. The `fallbacks` parameter is not supported on the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing) (a batch item that includes it comes back as an errored result). Claude Haiku 5.5 has no server-side fallback: with `fallbacks: "default"`, a declined request stays declined, and a list of fallback models returns a 400 error.
236236</Note>
237237
238238### Making the request
from line 1100
11001100
11011101* Retries walk your fallback list in order. A fallback model that itself refuses passes the request to the next entry.
11021102* 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.
1103* Thinking blocks from Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 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 only [Claude Fable 5.1 and Claude Mythos 5.1 read](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 and Google Cloud. Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5 blocks on the Claude API and Google Cloud, and the API drops them for a fallback model that can't read them.
1103* Thinking blocks from Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 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 only [Claude Fable 5.1 and Claude Mythos 5.1 read](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 and Claude Models on Google Cloud (Google managed). Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5 blocks on the Claude API and Claude Models on Google Cloud (Google managed), and the API drops them for a fallback model that can't read them.
11041104* 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.
11051105* The model that accepted is recorded in `BetaFallbackState` (go: `betafallback.BetaFallbackState`), so follow-up requests that share the state stay pinned to it rather than re-asking a model that refused.
11061106
from line 1120
11201120 <Step title="Re-send on a fallback model">
11211121 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):
11221122
1123 * **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: only Claude Fable 5.1 and Claude Mythos 5.1 [read Claude Fable 5.1 blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model), and only those two models, Claude Fable 5, and Claude Mythos 5 read Claude Fable 5 blocks, so for any other fallback model 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 and Google Cloud. A retry after a Claude Haiku 5.5 refusal is always in this case. Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5 blocks on the Claude API and Google Cloud, so leave those blocks in place when you fall back to either model there. For a fallback model that can't read them, the API drops them without billing them.
1123 * **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: only Claude Fable 5.1 and Claude Mythos 5.1 [read Claude Fable 5.1 blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-for-model), and only those two models, Claude Fable 5, and Claude Mythos 5 read Claude Fable 5 blocks, so for any other fallback model 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 and Claude Models on Google Cloud (Google managed). A retry after a Claude Haiku 5.5 refusal is always in this case. Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5 blocks on the Claude API and Claude Models on Google Cloud (Google managed), so leave those blocks in place when you fall back to either model there. For a fallback model that can't read them, the API drops them without billing them.
11241124 * **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)).
11251125 </Step>
11261126
build-with-claude/thinking Changed · +3 / -3 lines
from line 987
987987
988988On 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.
989989
990Use `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` (to send it on Amazon Bedrock, Google Cloud, or Microsoft Foundry, see [Beta features on other platforms](https://platform.claude.com/docs/en/api/beta-headers#beta-features-on-other-platforms)). Without it, the value is rejected with the same 400 `invalid_request_error` as an unknown `display` value.
990Use `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` (to send it on Amazon Bedrock, Claude Models on Google Cloud (Google managed), or Microsoft Foundry, see [Beta features on other platforms](https://platform.claude.com/docs/en/api/beta-headers#beta-features-on-other-platforms)). Without it, the value is rejected with the same 400 `invalid_request_error` as an unknown `display` value.
991991
992992```json
993993{
from line 1065
10651065
10661066The 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).
10671067
1068**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 earlier models' thinking blocks, and only the two of them read each other's, so switching to them keeps the conversation's reasoning and switching from them to any other model 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, and, on the Claude API and Google Cloud, of Claude Haiku 5.5, 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, and, on the Claude API and Google Cloud, from Claude Haiku 5.5, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Google Cloud, 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 and Google Cloud keeps the earlier turns' reasoning, and any other switch away from Claude Sonnet 5.5 drops it. Claude Haiku 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, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Google Cloud, Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5's blocks and no other model does. 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.
1068**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 earlier models' thinking blocks, and only the two of them read each other's, so switching to them keeps the conversation's reasoning and switching from them to any other model 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, and, on the Claude API and Claude Models on Google Cloud (Google managed), of Claude Haiku 5.5, 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, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On those two platforms, 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 there keeps the earlier turns' reasoning, and any other switch away from Claude Sonnet 5.5 drops it. Claude Haiku 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, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5's blocks and no other model does. 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.
10691069
10701070## Preserved thinking
10711071
from line 1160
11601160* When [streaming responses](https://platform.claude.com/docs/en/build-with-claude/thinking#streaming-thinking), the signature arrives as a `signature_delta` inside a `content_block_delta` event just before the `content_block_stop` event.
11611161* `signature` values are significantly longer in Claude 4 and later models than in previous models.
11621162* The `signature` field is opaque: don't interpret or parse it.
1163* `signature` values are compatible across platforms (the Claude API, [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)). Values generated on one platform work on another, except that thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 work only in the account that produced them or in an account linked to it. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
1163* `signature` values are compatible across platforms, including the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). Values generated on one platform work on another, except that thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 work only in the account that produced them or in an account linked to it. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
11641164
11651165## Redacted thinking blocks
11661166
build-with-claude/vision Changed · +5 / -5 lines
from line 23
23233. A `file_id` returned by the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) (upload once, reference many times)
2424
2525<Note>
26 On Amazon Bedrock and Google Cloud, only base64-encoded sources are currently available.
26 On Amazon Bedrock and Claude Models on Google Cloud (Google managed), only base64-encoded sources are currently available.
2727</Note>
2828
2929<Tip>
from line 1226
12261226
12271227The maximum dimensions for each image are 8000x8000 px.
12281228
1229If a single API request contains more than 20 images, a stricter per-image dimension limit applies to every image in that request. All `image` blocks in the request count toward this threshold, including images from earlier conversation turns that you resend and images nested inside `tool_result` content (for example, screenshots returned to the computer use tool). On Amazon Bedrock and Google Cloud, document blocks such as PDFs also count toward this threshold. Images exceeding the stricter limit are rejected with an `invalid_request_error` whose message references "many-image requests" and states the current limit in pixels. To stay under the limit on all platforms, either resize each image so that neither dimension exceeds 2000 px, or keep the request to 20 or fewer image and document blocks.
1229If a single API request contains more than 20 images, a stricter per-image dimension limit applies to every image in that request. All `image` blocks in the request count toward this threshold, including images from earlier conversation turns that you resend and images nested inside `tool_result` content (for example, screenshots returned to the computer use tool). On Amazon Bedrock and Claude Models on Google Cloud (Google managed), document blocks such as PDFs also count toward this threshold. Images exceeding the stricter limit are rejected with an `invalid_request_error` whose message references "many-image requests" and states the current limit in pixels. To stay under the limit on all platforms, either resize each image so that neither dimension exceeds 2000 px, or keep the request to 20 or fewer image and document blocks.
12301230
12311231The maximum size per image is:
12321232
12331233* 10 MB (base64-encoded) when using the Claude API directly.
1234* 5 MB (base64-encoded) on Amazon Bedrock and Google Cloud.
1234* 5 MB (base64-encoded) on Amazon Bedrock and Claude Models on Google Cloud (Google managed).
12351235* 10 MB on [claude.ai](https://claude.ai/).
12361236
12371237<Note>
1238 Although the API supports up to 600 images per request, [request size limits](https://platform.claude.com/docs/en/api/overview#request-size-limits) (32 MB for standard endpoints; lower on some partner-operated platforms, for example, Amazon Bedrock and Google Cloud) can be reached first. For many images, consider uploading with the [Files API](https://platform.claude.com/docs/en/build-with-claude/vision#files-api-image-example) and referencing by `file_id` to keep request payloads small.
1238 Although the API supports up to 600 images per request, [request size limits](https://platform.claude.com/docs/en/api/overview#request-size-limits) can be reached first: 32 MB for standard endpoints, and lower on some partner-operated platforms, such as Amazon Bedrock and Claude Models on Google Cloud (Google managed). For many images, consider uploading with the [Files API](https://platform.claude.com/docs/en/build-with-claude/vision#files-api-image-example) and referencing by `file_id` to keep request payloads small.
12391239
12401240 Even when using the Files API, requests with many large images can fail before reaching the 600-image count. Reduce image dimensions or file sizes (for example, by downsampling) before uploading (see [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size)).
12411241</Note>
from line 1319
13191319 </Accordion>
13201320
13211321 <Accordion title="Is there a limit to the image file size I can upload?">
1322 Yes. See [Request limits](https://platform.claude.com/docs/en/build-with-claude/vision#request-limits) for per-image and overall request size limits across the Claude API, Amazon Bedrock, Google Cloud, and claude.ai.
1322 Yes. See [Request limits](https://platform.claude.com/docs/en/build-with-claude/vision#request-limits) for per-image and overall request size limits across the Claude API, Amazon Bedrock, Claude Models on Google Cloud (Google managed), and claude.ai.
13231323 </Accordion>
13241324
13251325 <Accordion title="How many images can I include in one request?">
cli-sdks-libraries/sdks/csharp Changed · +6 / -2 lines
from line 415
415415 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
416416 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
417417 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
418 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
418 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
419419 * [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry)
420
421 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
420422</Note>
421423
422424The C# SDK supports the following platforms through separate NuGet packages:
423425
424* **Agent Platform:** `Anthropic.Vertex`. See [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) for client setup.
426* **Agent Platform:** `Anthropic.Vertex`. See [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) for client setup.
425427* **Bedrock:** `Anthropic.Bedrock`. Use `AnthropicBedrockMantleClient` for the Messages-API Bedrock endpoint, or `AnthropicBedrockClient` (`bedrock-runtime` path). `AnthropicBedrockMantleClient` takes an optional `MantleAwsClientOptions` config object; `AnthropicBedrockClient` accepts `AnthropicBedrockCredentialsHelper.FromEnv()` or explicit credentials.
426428* **Claude Platform on AWS:** `Anthropic.Aws`. Use `AnthropicAwsClient`; set `WorkspaceId` on the client or the `ANTHROPIC_AWS_WORKSPACE_ID` environment variable (see [Workspaces](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#workspaces)). Available in beta.
427429* **Foundry:** `Anthropic.Foundry`. Use `AnthropicFoundryClient` with `DefaultAnthropicFoundryCredentials.FromEnv()` or explicit credentials.
428430
429431Use `AnthropicBedrockMantleClient` for new projects; `AnthropicBedrockClient` remains for existing applications using the Bedrock `InvokeModel` API.
432
433The C# SDK also supports Claude Models on Google Cloud (Anthropic managed) through `AnthropicGoogleCloudClient`, from the `Anthropic.GoogleCloud` package. This client is in beta. Set `WorkspaceId` on an optional `GoogleCloudClientOptions` value, or set the `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID` environment variable. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution).
430434
431435## Semantic versioning
432436
cli-sdks-libraries/sdks/go Changed · +5 / -1 lines
from line 628
628628 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
629629 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
630630 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
631 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
631 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
632632 * [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry)
633
634 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
633635</Note>
634636
635637The Go SDK supports the following platforms:
from line 642
640642* **Foundry:** `import "github.com/anthropics/anthropic-sdk-go/v2/foundry"`. Use `foundry.NewClient(cfg)` with a `foundry.ClientConfig` value to construct a client; set `APIKey` (or `AzureADTokenProvider` for Microsoft Entra ID) and `Resource` on the config, or the `ANTHROPIC_FOUNDRY_API_KEY` and `ANTHROPIC_FOUNDRY_RESOURCE` environment variables.
641643
642644Use `bedrock.NewMantleClient` for new projects; `bedrock.WithLoadDefaultConfig`/`WithConfig` remain for existing applications using the Bedrock `InvokeModel` API.
645
646The Go SDK also supports Claude Models on Google Cloud (Anthropic managed) through the `github.com/anthropics/anthropic-sdk-go/v2/googlecloud` package. To construct a client, call `googlecloud.NewClient(ctx, cfg)` with a `googlecloud.ClientConfig` value. This client is in beta. Set `WorkspaceID` on the config or set the `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID` environment variable. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution) for how the client resolves the workspace ID.
643647
644648## Advanced usage
645649
cli-sdks-libraries/sdks/java Changed · +5 / -1 lines
from line 1071
10711071 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
10721072 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
10731073 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
1074 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
1074 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
10751075 * [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry)
1076
1077 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
10761078</Note>
10771079
10781080The Java SDK supports the following platforms through separate dependencies that provide platform-specific `Backend` implementations:
from line 1085
10831085* **Foundry:** `com.anthropic:anthropic-java-foundry`: Use `FoundryBackend.fromEnv()` or `FoundryBackend.builder()`.
10841086
10851087Use `BedrockMantleBackend` for new projects; `BedrockBackend` remains for existing applications using the Bedrock `InvokeModel` API.
1088
1089The Java SDK also supports Claude Models on Google Cloud (Anthropic managed) through `GoogleCloudBackend`, from the `com.anthropic:anthropic-java-google-cloud` dependency. This backend is in beta. Create it with `GoogleCloudBackend.builder()` or `GoogleCloudBackend.fromEnv()`. `fromEnv()` reads `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID`, `ANTHROPIC_GOOGLE_CLOUD_PROJECT`, and Google Application Default Credentials. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution).
10861090
10871091The platform artifacts are add-ons to the base `com.anthropic:anthropic-java` dependency, which provides `AnthropicOkHttpClient`, so install both. Each `Backend` implementation is passed to the client with `.backend()` on `AnthropicOkHttpClient.builder()`. Each cloud backend pulls in its respective cloud-platform SDK classes as transitive dependencies.
10881092
cli-sdks-libraries/sdks/php Changed · +5 / -1 lines
from line 218
218218 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
219219 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
220220 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
221 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
221 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
222222 * [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry)
223
224 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
223225</Note>
224226
225227The PHP SDK supports the following platforms:
from line 233
231233* **Foundry:** `Anthropic\Foundry\Client`. Use `::withCredentials()`.
232234
233235Use `MantleClient` for new projects; `Anthropic\Bedrock\Client` remains for existing applications using the Bedrock `InvokeModel` API.
236
237The PHP SDK also supports Claude Models on Google Cloud (Anthropic managed) through `Anthropic\GoogleCloud\Client`. This client is in beta. `Anthropic\GoogleCloud\Client` requires `google/auth` as a soft dependency. Use `new Anthropic\GoogleCloud\Client(workspaceId: ...)` or set the `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID` environment variable. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution).
234238
235239## Semantic versioning
236240
cli-sdks-libraries/sdks/python Changed · +18 / -13 lines
from line 4
44description: Install and configure the Anthropic Python SDK with sync and async client support
55---
66
7The Anthropic Python SDK provides convenient access to the Claude API from Python applications. It supports both synchronous and asynchronous operations, streaming, and integrations with Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
7The Anthropic Python SDK provides convenient access to the Claude API from Python applications. It supports both synchronous and asynchronous operations, streaming, and integrations with Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed), Claude Models on Google Cloud (Google managed), and Microsoft Foundry.
88
99<Info>
1010 For API feature documentation with code examples, see the [API reference](https://platform.claude.com/docs/en/api/overview). This page covers Python-specific SDK features and configuration.
from line 34
3434pip install "anthropic[aiohttp]"
3535```
3636
37To use Claude Models on Google Cloud (Anthropic managed), run `pip install "anthropic[google_cloud]"`.
38
3739## Requirements
3840
3941Python 3.10 or later is required. If you are upgrading from a 0.x release of the SDK, see the [v1 migration guide](https://github.com/anthropics/anthropic-sdk-python/blob/main/MIGRATION.md) for the list of breaking changes.
from line 741
739741 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
740742 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
741743 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
742 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
744 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
743745 * [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry)
746
747 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
744748</Note>
745749
746All five client classes are included in the base `anthropic` package:
750All six client classes are included in the base `anthropic` package:
747751
748| Provider | Client | Extra dependencies |
749| -------------------------------- | ---------------------------------------------- | ---------------------------------- |
750| Agent Platform | `from anthropic import AnthropicVertex` | `pip install "anthropic[vertex]"` |
751| Bedrock | `from anthropic import AnthropicBedrockMantle` | `pip install "anthropic[bedrock]"` |
752| Bedrock (`bedrock-runtime` path) | `from anthropic import AnthropicBedrock` | `pip install "anthropic[bedrock]"` |
753| Claude Platform on AWS | `from anthropic import AnthropicAWS` | `pip install "anthropic[aws]"` |
754| Foundry | `from anthropic import AnthropicFoundry` | None |
752| Provider | Client | Extra dependencies |
753| ------------------------------------------------- | ---------------------------------------------- | --------------------------------------- |
754| Agent Platform | `from anthropic import AnthropicVertex` | `pip install "anthropic[vertex]"` |
755| Bedrock | `from anthropic import AnthropicBedrockMantle` | `pip install "anthropic[bedrock]"` |
756| Bedrock (`bedrock-runtime` path) | `from anthropic import AnthropicBedrock` | `pip install "anthropic[bedrock]"` |
757| Claude Platform on AWS | `from anthropic import AnthropicAWS` | `pip install "anthropic[aws]"` |
758| Claude Models on Google Cloud (Anthropic managed) | `from anthropic import AnthropicGoogleCloud` | `pip install "anthropic[google_cloud]"` |
759| Foundry | `from anthropic import AnthropicFoundry` | None |
755760
756The `AnthropicAWS` client is in beta. Pass `workspace_id` to the constructor or set the `ANTHROPIC_AWS_WORKSPACE_ID` environment variable.
761The `AnthropicAWS` client is in beta. Pass `workspace_id` to the constructor or set the `ANTHROPIC_AWS_WORKSPACE_ID` environment variable. The `AnthropicGoogleCloud` client is also in beta. Pass `workspace_id` to the constructor or set the `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID` environment variable. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution) for how the client resolves the workspace ID.
757762
758763Use `AnthropicBedrockMantle` for new projects; `AnthropicBedrock` remains for existing applications using the Bedrock `InvokeModel` API.
759764
cli-sdks-libraries/sdks/ruby Changed · +5 / -1 lines
from line 395
395395 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
396396 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
397397 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
398 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
398 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
399
400 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
399401</Note>
400402
401403The Ruby SDK supports the following platforms:
from line 408
406408* **Foundry:** Not currently supported in the Ruby SDK. See [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for supported SDKs.
407409
408410Use `Anthropic::BedrockMantleClient` for new projects; `Anthropic::BedrockClient` remains for existing applications using the Bedrock `InvokeModel` API.
411
412The Ruby SDK also supports Claude Models on Google Cloud (Anthropic managed) through `Anthropic::GoogleCloudClient`. This client is in beta. It ships in the main `anthropic` gem and needs the `googleauth` gem. Pass `workspace_id:` to the constructor or set the `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID` environment variable. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution) for how the client resolves the workspace ID.
409413
410414## Semantic versioning
411415
cli-sdks-libraries/sdks/typescript Changed · +5 / -1 lines
from line 767
767767 * [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock)
768768 * [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy)
769769 * [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws)
770 * [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai)
770 * [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed)
771771 * [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry)
772
773 See also [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed).
772774</Note>
773775
774776The TypeScript SDK supports the following platforms:
from line 781
779781* **Foundry:** `npm install @anthropic-ai/foundry-sdk`: Provides `AnthropicFoundry` client
780782
781783Use `AnthropicBedrockMantle` for new projects; `AnthropicBedrock` remains for existing applications using the Bedrock `InvokeModel` API.
784
785The TypeScript SDK also supports Claude Models on Google Cloud (Anthropic managed) through the `AnthropicGoogleCloud` client. This client is in beta. To install it, run `npm install @anthropic-ai/google-cloud-sdk`. Pass `workspaceId` to the constructor or set the `ANTHROPIC_GOOGLE_CLOUD_WORKSPACE_ID` environment variable. See [Project, location, and workspace resolution](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#project-location-and-workspace-resolution) for how the client resolves the workspace ID.
782786
783787## Semantic versioning
784788
manage-claude/access-transparency Changed · +13 / -13 lines
from line 36
3636* **Your own organization's activity:** Your API calls, admin actions, and Compliance API reads are covered by standard [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) event types.
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.
39* **Partner-operated platforms:** Amazon Bedrock and Google Cloud; refer to those platforms' transparency controls.
39* **Partner-operated platforms:** Amazon Bedrock and Claude Models on Google Cloud (Google managed); refer to those platforms' transparency controls.
4040* **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
from line 165
165165
166166The following table lists which surfaces are covered by Access Transparency. Coverage means human access to content from that surface generates `anthropic_access` events.
167167
168| Surface | Covered | Details |
169| ----------------------------------------------- | ------- | ---------------------------------------------------------------------------------------------------------- |
170| Claude API (`api.anthropic.com`) | Yes | Prompts, completions, and data directly embedded in the API inputs |
171| Claude Code (using an API key) | Yes | API traffic from Claude Code is covered as Claude API traffic |
172| Claude Platform on AWS | Yes | Claude Platform on AWS generates Access Transparency events within the Compliance API (not AWS CloudTrail) |
173| Claude API (`api.anthropic.com`) (Batch, Files) | No | The Claude API Batch and Files APIs are not covered, just like they are not covered by ZDR |
174| Claude for Enterprise (claude.ai seats) | No | Not covered |
175| Claude for Work | No | Not covered |
176| Claude Free, Pro, Max | No | Consumer plans are not eligible |
177| Playground (Claude Console) | No | Not covered |
178| Microsoft Foundry | No | Not available |
179| Amazon Bedrock, Google Cloud | No | Partner-operated platforms; refer to those platforms' transparency controls |
168| Surface | Covered | Details |
169| -------------------------------------------------------------- | ------- | ---------------------------------------------------------------------------------------------------------- |
170| Claude API (`api.anthropic.com`) | Yes | Prompts, completions, and data directly embedded in the API inputs |
171| Claude Code (using an API key) | Yes | API traffic from Claude Code is covered as Claude API traffic |
172| Claude Platform on AWS | Yes | Claude Platform on AWS generates Access Transparency events within the Compliance API (not AWS CloudTrail) |
173| Claude API (`api.anthropic.com`) (Batch, Files) | No | The Claude API Batch and Files APIs are not covered, just like they are not covered by ZDR |
174| Claude for Enterprise (claude.ai seats) | No | Not covered |
175| Claude for Work | No | Not covered |
176| Claude Free, Pro, Max | No | Consumer plans are not eligible |
177| Playground (Claude Console) | No | Not covered |
178| Microsoft Foundry | No | Not available |
179| Amazon Bedrock, Claude Models on Google Cloud (Google managed) | No | Partner-operated platforms; refer to those platforms' transparency controls |
180180
181181## Limitations and exclusions
182182
manage-claude/api-and-data-retention Changed · +4 / -2 lines
from line 4
44description: Learn about how Anthropic's APIs and associated features retain data, including information about zero data retention (ZDR) and HIPAA-ready API access.
55---
66
7This page covers the Claude API (`api.anthropic.com`), Claude Platform on AWS, and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), where Anthropic is the data processor. On Amazon Bedrock and Google Cloud's Agent Platform, the cloud provider is the data processor; refer to those platforms' data retention and compliance documentation for their equivalent controls.
7This page covers the Claude API (`api.anthropic.com`), Claude Platform on AWS, [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), where Anthropic is the data processor. On Amazon Bedrock and Claude Models on Google Cloud (Google managed), the cloud provider is the data processor; refer to those platforms' data retention and compliance documentation for their equivalent controls.
88
99Anthropic offers two data handling arrangements for the Claude API: [zero data retention (ZDR)](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) and [HIPAA readiness](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness). The [feature eligibility table](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility) lists which API features each arrangement covers. For Anthropic's standard retention policies outside these arrangements, see the [commercial data retention policy](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data) and the [consumer data retention policy](https://privacy.claude.com/en/articles/10023548-how-long-do-you-store-my-data).
1010
from line 28
2828* **Claude Code with API keys:** ZDR applies when Claude Code is used with API keys from a Commercial organization (an organization under Anthropic's Commercial Terms of Service, as distinct from a consumer Claude account). If metrics logging is enabled in Claude Code, productivity data such as usage statistics is exempted from ZDR and may be retained. Claude Code on Claude Enterprise is not covered by this arrangement and has a separate ZDR offering; see [What ZDR does not cover](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#what-zdr-does-not-cover).
2929* **Claude Platform on AWS:** [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) follows the same data retention policy as the first-party Claude API. ZDR is available on request; contact your Anthropic account representative to enable it.
3030
31- **Claude Models on Google Cloud (Anthropic managed):** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) follows the same data retention policy as the first-party Claude API. ZDR is available on request; contact your Anthropic account representative to enable it.
32
3133### What ZDR does not cover
3234
3335* **Claude Console:** Any usage in the Claude Console, including playground.
from line 251
249251 </Accordion>
250252
251253 <Accordion title="Does this apply to Amazon Bedrock or Google Cloud?">
252 No. The ZDR and HIPAA arrangements described on this page apply to the Claude API, where Anthropic is the data processor. On Bedrock and Google Cloud, the cloud provider is the data processor; refer to those platforms' data retention and compliance policies for their equivalent controls.
254 [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) follows the same data retention policy as the first-party Claude API, and Anthropic is the data processor. ZDR is available there on request. On Amazon Bedrock and Claude Models on Google Cloud (Google managed), the cloud provider is the data processor; refer to those platforms' data retention and compliance policies for their equivalent controls.
253255 </Accordion>
254256
255257 <Accordion title="Is Claude Platform on AWS eligible for ZDR or HIPAA readiness?">
manage-claude/data-residency Changed · +10 / -2 lines
from line 223
223223The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5 (deprecated), Claude Haiku 4.5, or earlier models return a 400 error.
224224
225225<Note>
226 The `inference_geo` parameter is available on the Claude API (first-party) and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws). On Amazon Bedrock and Google Cloud, the inference region is determined by the endpoint URL or inference profile, so `inference_geo` is not applicable. On [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), `inference_geo` is likewise not applicable: deployments hosted on Azure can instead use the US Data Zone Standard deployment type, which keeps inference within the United States. The `inference_geo` parameter is also not available through the [OpenAI SDK compatibility endpoint](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk).
226 The `inference_geo` parameter is available on the Claude API (first-party), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). On Amazon Bedrock and Claude Models on Google Cloud (Google managed), the inference region is determined by the endpoint URL or inference profile, so `inference_geo` is not applicable. On [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), `inference_geo` is likewise not applicable: deployments hosted on Azure can instead use the US Data Zone Standard deployment type, which keeps inference within the United States. The `inference_geo` parameter is also not available through the [OpenAI SDK compatibility endpoint](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk).
227227</Note>
228228
229229### Workspace-level restrictions
from line 235
235235
236236These settings can be configured through the Console or the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api) under the `data_residency` field.
237237
238<Note>
239 **Claude Models on Google Cloud (Anthropic managed):** Every workspace allows all inference geos and uses `"global"` as its default inference geo. The Claude Console shows both settings as read-only. For US-only inference, set `inference_geo: "us"` on each request.
240</Note>
241
238242## Workspace geo
239243
240244Workspace geo is set when you create a workspace and can't be changed afterward. Currently, `"us"` is the only available workspace geo.
from line 253
249253 **Claude Platform on AWS:** Workspace geo is not configurable. Claude Managed Agents sessions on this platform run with an effective Workspace geo of `"us"`, which is currently the only available workspace geo. See [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) for data residency considerations specific to that platform.
250254</Note>
251255
256<Note>
257 **Claude Models on Google Cloud (Anthropic managed):** Workspace geo is not configurable. Every workspace uses `"us"` as its workspace geo, and the **Workspace geo** field doesn't appear in the Claude Console.
258</Note>
259
252260## Pricing
253261
254262Data residency pricing varies by model generation:
from line 265
257265* **Global routing (`inference_geo: "global"`):** Standard pricing applies.
258266* **Older models:** Don't support `inference_geo` (see [Model availability](https://platform.claude.com/docs/en/manage-claude/data-residency#model-availability)). Standard pricing applies. Requests that include the parameter return a 400 error.
259267
260This pricing applies to the Claude API (first-party) and Claude Platform on AWS. On Claude in Microsoft Foundry, the same 1.1x multiplier applies to deployments hosted on Azure that use the US Data Zone Standard deployment type. Partner-operated platforms (Bedrock and Google Cloud) have their own regional pricing. See [Data residency pricing](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing) for details.
268This pricing applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). On Claude in Microsoft Foundry, the same 1.1x multiplier applies to deployments hosted on Azure that use the US Data Zone Standard deployment type. Partner-operated platforms, Bedrock and Claude Models on Google Cloud (Google managed), have their own regional pricing. See [Data residency pricing](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing) for details.
261269
262270The same multiplier applies to [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview): when an agent's [model configuration](https://platform.claude.com/docs/en/managed-agents/agent-setup) pins `inference_geo` to `"us"`, model requests in sessions running that agent are priced at 1.1x the standard rate.
263271
manage-claude/user-profiles Changed · +15 / -15 lines
### Attribute requests on Amazon Bedrock and Claude Models on Google Cloud (Google managed) ### Attribute requests on Amazon Bedrock and Google Cloud
from line 37
3737* An organization on [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws). The calling principal needs the [user profile IAM actions](https://platform.claude.com/docs/en/api/claude-platform-on-aws-iam-actions#user-profiles).
3838* A [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) deployment [hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options), not one hosted on Azure. You don't need an organization on the Claude API or Claude Platform on AWS. Use your Foundry endpoint, with the same base URL and authentication that you use for inference.
3939
40Amazon Bedrock and Google Cloud don't have the `/v1/user_profiles` endpoints. If your inference runs there, create your profiles in an organization on the Claude API or Claude Platform on AWS. On Amazon Bedrock, profiles work only with [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock). See [Attribute requests on Amazon Bedrock and Google Cloud](https://platform.claude.com/docs/en/manage-claude/user-profiles#attribute-requests-on-amazon-bedrock-and-google-cloud).
40Amazon Bedrock and Claude Models on Google Cloud (Google managed) don't have the `/v1/user_profiles` endpoints. If your inference runs there, create your profiles in an organization on the Claude API or Claude Platform on AWS. On Amazon Bedrock, profiles work only with [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock). See [Attribute requests on Amazon Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/manage-claude/user-profiles#attribute-requests-on-amazon-bedrock-and-google-cloud).
4141
4242Keep the traffic you send for your end customers in one organization and your own internal usage in another. Profiles belong to an organization, not a workspace, so separate workspaces in one organization aren't enough. Only the organization for end-customer traffic needs user profiles. To create another organization on the Claude API, see the "How to create a new organization" section of [Creating and managing Workspaces in the Claude Console](https://support.claude.com/en/articles/9796807) in the Claude Help Center.
4343
from line 362
362362
363363Message Batches is the exception: creating a batch checks only the ID's format. If a well-formed ID doesn't belong to the organization that sends the batch, the batch is still created, and each request in it then fails with an `errored` result that contains the same `invalid_request_error`.
364364
365### Attribute requests on Amazon Bedrock and Google Cloud
365### Attribute requests on Amazon Bedrock and Claude Models on Google Cloud (Google managed)
366366
367A profile ID of either access type also works on [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and on Google Cloud. It doesn't work with the [earlier Amazon Bedrock integration](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) that you call with `InvokeModel` or `Converse`. You use your Anthropic organization's credentials only to create and manage profiles. Inference stays on your existing AWS or Google Cloud credentials.
367A profile ID of either access type also works on [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and on Claude Models on Google Cloud (Google managed). It doesn't work with the [earlier Amazon Bedrock integration](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) that you call with `InvokeModel` or `Converse`. You use your Anthropic organization's credentials only to create and manage profiles. Inference stays on your existing AWS or Google Cloud credentials.
368368
369| Platform | Create profiles | Send the profile ID in |
370| --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ | ------------------------------------------- |
371| Claude API | Yes | `anthropic-user-profile-id` header |
372| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | Yes | `anthropic-user-profile-id` header |
373| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), deployments hosted on Anthropic | Yes | `anthropic-user-profile-id` header |
374| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | No. Create them on the Claude API or Claude Platform on AWS. | `anthropic-user-profile-id` header |
375| [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | No. Create them on the Claude API or Claude Platform on AWS. | `user_profile_id` field in the request body |
369| Platform | Create profiles | Send the profile ID in |
370| ---------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ | ------------------------------------------- |
371| Claude API | Yes | `anthropic-user-profile-id` header |
372| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | Yes | `anthropic-user-profile-id` header |
373| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), deployments hosted on Anthropic | Yes | `anthropic-user-profile-id` header |
374| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | No. Create them on the Claude API or Claude Platform on AWS. | `anthropic-user-profile-id` header |
375| [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | No. Create them on the Claude API or Claude Platform on AWS. | `user_profile_id` field in the request body |
376376
377377On Claude in Amazon Bedrock, put the ID at the top level of the request body:
378378
from line 385
385385}
386386```
387387
388Link each AWS account that sends requests to Claude in Amazon Bedrock, and each Google Cloud project that sends requests on Google Cloud, to the Anthropic organization that creates your profiles:
388Link each AWS account that sends requests to Claude in Amazon Bedrock, and each Google Cloud project that sends requests to Claude Models on Google Cloud (Google managed), to the Anthropic organization that creates your profiles:
389389
3903901. An admin or owner of that organization starts the link in the Verification Portal at `portal.anthropic.com`, under **Linked accounts**.
3913912. Someone who can manage IAM in the AWS account or Google Cloud project runs a command that the portal provides.
from line 393
393393
394394Programs that apply to a profile apply to an account's requests only after the account is linked and the portal shows it as **Linked**. Those programs include the ones an end customer's organization is approved for after the end customer [links the profile to that organization](https://platform.claude.com/docs/en/manage-claude/user-profiles-verification-portal) and, for Cyber Verification Program access levels, turns them on for the profile in the portal.
395395
396Claude in Amazon Bedrock and Google Cloud check the format of the ID but don't look the profile up. They reject a malformed ID with a `400`. They accept any well-formed ID, so a successful response doesn't confirm that the ID matches a profile. A request with no ID goes through unattributed, and if it triggers an enforcement action, the action applies to your whole organization.
396Claude in Amazon Bedrock and Claude Models on Google Cloud (Google managed) check the format of the ID but don't look the profile up. They reject a malformed ID with a `400`. They accept any well-formed ID, so a successful response doesn't confirm that the ID matches a profile. A request with no ID goes through unattributed, and if it triggers an enforcement action, the action applies to your whole organization.
397397
398398### Identify individual users within a company
399399
from line 671
671671
672672The response repeats the ID with `"type": "user_profile_deleted"`. If a delete returns a server error, retry it. A `404` on the retry means the first delete went through.
673673
674After a delete, the profile endpoints return a `404` for that ID. For up to about 10 minutes, inference requests that carry the deleted ID can still succeed. After that, the platforms that check the ID on every request reject the request with a `400`. Claude in Amazon Bedrock and Google Cloud don't look profiles up, so they still accept it.
674After a delete, the profile endpoints return a `404` for that ID. For up to about 10 minutes, inference requests that carry the deleted ID can still succeed. After that, the platforms that check the ID on every request reject the request with a `400`. Claude in Amazon Bedrock and Claude Models on Google Cloud (Google managed) don't look profiles up, so they still accept it.
675675
676676## Next steps
677677
managed-agents/choosing-an-environment Changed · +7 / -1 lines
## Differences on Claude Models on Google Cloud (Anthropic managed)
from line 63
6363
6464If you use Claude Managed Agents through Claude Platform on AWS, Anthropic still operates the service. There, a self-hosted sandbox can't use memory stores, workers don't use an environment key, and MCP tunnels aren't available. See [Claude Managed Agents on Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#claude-managed-agents) and [Features not supported](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported).
6565
66## Differences on Claude Models on Google Cloud (Anthropic managed)
67
68If you use Claude Managed Agents through Claude Models on Google Cloud (Anthropic managed), Anthropic still operates the service. There, memory stores aren't supported in a self-hosted sandbox, and MCP tunnels aren't available. Workers authenticate with Google Cloud credentials, not an environment key, and you write your own, because the pre-built workers in the `ant` CLI and the Python, TypeScript, and Go SDKs don't work there. See [Feature support](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#feature-support) in the Claude Models on Google Cloud (Anthropic managed) guide.
69
6670## Switch from a cloud environment to a self-hosted sandbox
6771
6872To switch to a self-hosted sandbox, you keep the agent, create a `self_hosted` environment, and reference its ID in new sessions and deployments.
6973
70* **What carries over:** The agent definition, the API key or AWS credentials your application uses, your skills, your MCP servers, and your [memory stores](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-memory).
74* **What carries over:** The agent definition, the API key, Google Cloud credentials, or AWS credentials your application uses, your skills, your MCP servers, and your [memory stores](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-memory).
7175* **What is new:** A `self_hosted` environment, an environment key that you generate in the Claude Console, and a worker that you run. The [self-hosted sandboxes quickstart](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#quickstart) covers all three.
7276* **What stops working:** The features listed in [What you take on and give up with a self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/choosing-an-environment#what-you-take-on-and-give-up-with-a-self-hosted-sandbox).
7377
7478On Claude Platform on AWS, memory stores don't carry over to a self-hosted sandbox, and the worker doesn't use an environment key. See [Differences on Claude Platform on AWS](https://platform.claude.com/docs/en/managed-agents/choosing-an-environment#differences-on-claude-platform-on-aws).
79
80On Claude Models on Google Cloud (Anthropic managed), memory stores aren't supported in a self-hosted sandbox, and you write your own worker, which doesn't use an environment key. See [Differences on Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/managed-agents/choosing-an-environment#differences-on-claude-models-on-google-cloud-anthropic-managed).
7581
models/fable-5-1/migration-guide Changed · +4 / -4 lines
from line 20
2020 The skill applies the model ID swap and, as needed, breaking parameter changes, prefill replacement, and effort calibration for your target model across your code base, then produces a checklist of items to verify manually. It asks you to confirm the migration scope (entire working directory, a subdirectory, or a specific file list) before editing any files. The skill also detects Amazon Bedrock and Claude Platform on AWS clients and adjusts model ID formats and feature changes for those platforms.
2121</Tip>
2222
23[Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) succeeds Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost. It's available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [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). [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) shares the same capabilities and is available only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). For behavioral differences and prompting patterns, see [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1).
23[Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) succeeds Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost. It's available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) shares the same capabilities and is available only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). For behavioral differences and prompting patterns, see [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1).
2424
2525The baseline settings shared by `claude-fable-5-1` and `claude-mythos-5-1`:
2626
from line 1491
14911491
14921492 Placed between an `assistant` turn and the next `user` turn, as here, the message takes effect from that `user` turn. Placed directly after a `user` turn with new input, it sets the level for Claude's reply to that turn. A `user` turn that holds only tool results doesn't count as new input: the change waits for the next `user` turn with new input. The level then holds until another `role: "system"` message changes it. Only the named levels are accepted (`low`, `medium`, `high`, `xhigh`, `max`), and the `mid-conversation-output-config-2026-07-01` beta header is required. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).
14931493
14942. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), with `tool_addition` and `tool_removal` blocks for tool changes (beta header `inline-tools-2026-09-15` on the Claude API). A `tool_addition` block can name a tool declared in `tools` at session start or [carry the tool's full definition](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), so a tool that is unknown at session start doesn't need to be in `tools`. This preserves prompt cache hits on earlier turns and keeps the conversation history append-only. The older `mid-conversation-tool-changes-2026-07-01` header still works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, and Google Cloud. The same message replaces forced `tool_choice` when a specific tool must run on the current turn (see [Breaking changes](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-breaking-changes)). For a reminder that applies to one turn only, send it as a separate text-only `role: "system"` message with `clear_at: "next_user_message"` ([turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages), beta header `mid-conversation-system-clear-at-2026-08-21`) and leave it in the history: it stops rendering after the next user message and costs no tokens once cleared. A message that carries `tool_addition` or `tool_removal` blocks can't be turn-scoped.
14942. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), with `tool_addition` and `tool_removal` blocks for tool changes (beta header `inline-tools-2026-09-15` on the Claude API). A `tool_addition` block can name a tool declared in `tools` at session start or [carry the tool's full definition](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), so a tool that is unknown at session start doesn't need to be in `tools`. This preserves prompt cache hits on earlier turns and keeps the conversation history append-only. The older `mid-conversation-tool-changes-2026-07-01` header still works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). The same message replaces forced `tool_choice` when a specific tool must run on the current turn (see [Breaking changes](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-breaking-changes)). For a reminder that applies to one turn only, send it as a separate text-only `role: "system"` message with `clear_at: "next_user_message"` ([turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages), beta header `mid-conversation-system-clear-at-2026-08-21`) and leave it in the history: it stops rendering after the next user message and costs no tokens once cleared. A message that carries `tool_addition` or `tool_removal` blocks can't be turn-scoped.
14951495
14963. **Use `fallbacks: "default"` for refusals:** Keep handling `stop_reason: "refusal"` and reading `stop_details.category` before response content. To re-run refused requests on another model automatically, set `fallbacks: "default"` (beta, `server-side-fallback-2026-07-01` header). `"default"` retries a declined request on the model Anthropic recommends for that category. The permitted fallback targets for Claude Fable 5.1 are Claude Opus 4.8 (`claude-opus-4-8`) and Claude Opus 5 (`claude-opus-5`). An explicit `fallbacks` list may name either. The fallback model doesn't receive Claude Fable 5.1's thinking blocks. The `fallbacks` parameter isn't available on Amazon Bedrock, Google Cloud, or Microsoft Foundry. On those platforms, use [client-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead. If you build the retry yourself, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) applies on the same terms as Claude Fable 5. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
14963. **Use `fallbacks: "default"` for refusals:** Keep handling `stop_reason: "refusal"` and reading `stop_details.category` before response content. To re-run refused requests on another model automatically, set `fallbacks: "default"` (beta, `server-side-fallback-2026-07-01` header). `"default"` retries a declined request on the model Anthropic recommends for that category. The permitted fallback targets for Claude Fable 5.1 are Claude Opus 4.8 (`claude-opus-4-8`) and Claude Opus 5 (`claude-opus-5`). An explicit `fallbacks` list may name either. The fallback model doesn't receive Claude Fable 5.1's thinking blocks. The `fallbacks` parameter isn't available on Amazon Bedrock, Claude Models on Google Cloud (Google managed), or Microsoft Foundry. On those platforms, use [client-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead. If you build the retry yourself, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) applies on the same terms as Claude Fable 5. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
14971497
149814984. **Start at `high` effort and sweep:** The [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) default is `high`, and all five levels are supported. Keep the Claude Fable 5 guidance: `high` for most work, and `medium` as a cost control worth testing. Claude Fable 5.1's gains over Claude Fable 5 are largest at `xhigh` and `max`, but those levels also add thinking time and time-to-first-response, so step up to them for the most capability-sensitive tasks and where your evals show the gain. Run a fresh sweep on your own evals rather than carrying over a setting tuned for Claude Fable 5. See [Recommended effort levels for Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-1).
14991499
models/fable-5-1/overview Changed · +14 / -13 lines
from line 47
4747
4848### Model IDs
4949
50| Platform | Model ID |
51| :----------------------------------------------------------------------------------------------------- | :--------------------------- |
52| Claude API | `claude-fable-5-1` |
53| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-1` |
54| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | `claude-fable-5-1` |
55| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-1` |
56| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5-1` |
50| Platform | Model ID |
51| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------- |
52| Claude API | `claude-fable-5-1` |
53| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-1` |
54| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-fable-5-1` |
55| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-1` |
56| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5-1` |
57| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-fable-5-1` |
5758
5859### Pricing
5960
from line 84
8384
8485### Availability
8586
86| Feature | Value |
87| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
88| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (latest) |
89| Released | September 1, 2026 |
90| Retirement | Not sooner than September 1, 2027 |
91| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
87| Feature | Value |
88| :---------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
89| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (latest) |
90| Released | September 1, 2026 |
91| Retirement | Not sooner than September 1, 2027 |
92| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
9293
9394## Resources
9495
models/fable-5/overview Changed · +14 / -13 lines
from line 39
3939
4040### Model IDs
4141
42| Platform | Model ID |
43| :----------------------------------------------------------------------------------------------------- | :------------------------- |
44| Claude API | `claude-fable-5` |
45| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5` |
46| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | `claude-fable-5` |
47| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5` |
48| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5` |
42| Platform | Model ID |
43| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------- |
44| Claude API | `claude-fable-5` |
45| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5` |
46| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-fable-5` |
47| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5` |
48| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-fable-5` |
49| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-fable-5` |
4950
5051### Pricing
5152
from line 75
7475
7576### Availability
7677
77| Feature | Value |
78| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
79| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (legacy) |
80| Released | June 9, 2026 |
81| Retirement | Not sooner than June 9, 2027 |
82| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
78| Feature | Value |
79| :---------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
80| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (legacy) |
81| Released | June 9, 2026 |
82| Retirement | Not sooner than June 9, 2027 |
83| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
8384
8485## Resources
8586
models/haiku-4-5/overview Changed · +16 / -15 lines
from line 35
3535
3636### Model IDs
3737
38| Platform | Model ID |
39| :-------------------------------------------------------------------------------------------------------------------- | :----------------------------------------- |
40| Claude API | `claude-haiku-4-5-20251001` |
41| Claude API alias | `claude-haiku-4-5` |
42| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-4-5` |
43| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-haiku-4-5-20251001-v1:0` |
44| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | `claude-haiku-4-5@20251001` |
45| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-4-5` |
46| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-haiku-4-5` |
38| Platform | Model ID |
39| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------- |
40| Claude API | `claude-haiku-4-5-20251001` |
41| Claude API alias | `claude-haiku-4-5` |
42| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-4-5` |
43| [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | `anthropic.claude-haiku-4-5-20251001-v1:0` |
44| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-haiku-4-5@20251001` |
45| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-4-5` |
46| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-haiku-4-5` |
47| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-haiku-4-5-20251001` |
4748
4849### Pricing
4950
from line 73
7273
7374### Availability
7475
75| Feature | Value |
76| :---------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
77| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (legacy) |
78| Released | October 15, 2025 |
79| Retirement | Not sooner than October 15, 2026 |
80| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
76| Feature | Value |
77| :---------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
78| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (legacy) |
79| Released | October 15, 2025 |
80| Retirement | Not sooner than October 15, 2026 |
81| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
8182
8283## Good to know
8384
models/haiku-5-5/migration-guide Changed · +13 / -13 lines
from line 34
34344. If your code reads the first content block as the answer, select blocks by `type` instead. See [Configure thinking](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking).
35355. Remove `temperature`, `top_p`, and `top_k` from your requests. See [Remove sampling parameters](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters).
36366. If your requests end `messages` with an assistant turn for the model to continue, end them with a user turn instead. See [Replace assistant prefill](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill).
377. If you use computer use, replace `computer_20250124`: on the Claude API and Google Cloud, with the `computer_toolset_20260801` toolset; on Amazon Bedrock, with `computer_20251124` and the `computer-use-2025-11-24` beta header. See [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset).
377. If you use computer use, replace `computer_20250124`: on the Claude API and Claude Models on Google Cloud (Google managed), with the `computer_toolset_20260801` toolset; on Amazon Bedrock, with `computer_20251124` and the `computer-use-2025-11-24` beta header. See [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset).
38388. If you replay stored conversations through a different account, replay each one through the account that produced it. See [Replay thinking blocks through the account that produced them](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replay-thinking-blocks-through-the-producing-account).
39399. If your code changes `system`, `tools`, or earlier `messages` between requests in a conversation and sends thinking blocks back, keep the conversation append-only. See [Keep earlier turns unchanged](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#keep-earlier-turns-unchanged).
404010. Handle `stop_reason: "refusal"`. Claude Haiku 5.5 runs safety classifiers that can decline a request, and it has no server-side fallback. See [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#safeguard-refusals).
from line 54
5454
5555Replace the Claude Haiku 4.5 model ID with the Claude Haiku 5.5 ID for your platform.
5656
57| Platform | Claude Haiku 4.5 | Claude Haiku 5.5 |
58| ---------------------- | ------------------------------------------------- | ---------------------------- |
59| Claude API | `claude-haiku-4-5-20251001` or `claude-haiku-4-5` | `claude-haiku-5-5` |
60| Amazon Bedrock | `anthropic.claude-haiku-4-5` | `anthropic.claude-haiku-5-5` |
61| Claude Platform on AWS | `claude-haiku-4-5` | `claude-haiku-5-5` |
62| Google Cloud | `claude-haiku-4-5@20251001` | `claude-haiku-5-5` |
63| Microsoft Foundry | `claude-haiku-4-5` | `claude-haiku-5-5` |
57| Platform | Claude Haiku 4.5 | Claude Haiku 5.5 |
58| ---------------------------------------------- | ------------------------------------------------- | ---------------------------- |
59| Claude API | `claude-haiku-4-5-20251001` or `claude-haiku-4-5` | `claude-haiku-5-5` |
60| Amazon Bedrock | `anthropic.claude-haiku-4-5` | `anthropic.claude-haiku-5-5` |
61| Claude Platform on AWS | `claude-haiku-4-5` | `claude-haiku-5-5` |
62| Claude Models on Google Cloud (Google managed) | `claude-haiku-4-5@20251001` | `claude-haiku-5-5` |
63| Microsoft Foundry | `claude-haiku-4-5` | `claude-haiku-5-5` |
6464
6565`claude-haiku-5-5` is a fixed model ID with no date suffix and no separate alias.
6666
from line 114
114114
115115Claude Haiku 5.5 accepts a forced `tool_choice` (`any` or a named tool), but the response starts with the tool call and has no `thinking` block. To let the model think before it calls a tool, use `tool_choice: {"type": "auto"}` and say in the prompt when to use the tool.
116116
117Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, so a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn't read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Google Cloud, Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5's blocks. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
117Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, so a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn't read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5's blocks. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
118118
119119## Remove sampling parameters
120120
from line 131
131131
132132## Move computer use to the toolset
133133
134Claude Haiku 4.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_20250124` tool, with the `computer-use-2025-01-24` beta header. On the Claude API and Google Cloud, Claude Haiku 5.5 supports computer use only through the `computer_toolset_20260801` toolset, and a request that declares `computer_20250124` returns a 400 error. On Amazon Bedrock, Claude Haiku 5.5 doesn't accept `computer_20250124` either; use the `computer_20251124` tool version with the `computer-use-2025-11-24` beta header.
134Claude Haiku 4.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_20250124` tool, with the `computer-use-2025-01-24` beta header. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 supports computer use only through the `computer_toolset_20260801` toolset, and a request that declares `computer_20250124` returns a 400 error. On Amazon Bedrock, Claude Haiku 5.5 doesn't accept `computer_20250124` either; use the `computer_20251124` tool version with the `computer-use-2025-11-24` beta header.
135135
136136To move an integration to the toolset, drop the `computer-use-2025-01-24` beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then make the other request and agent-loop changes in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): dispatch on each member `tool_use` block's `name` and `toolset_name` rather than on `input.action`, handle every such block in a turn, and echo `toolset_name` on results. Zoom is on by default in the toolset; if your environment doesn't implement it, add `"configs": {"zoom": {"enabled": false}}`. If you send the `fine-grained-tool-streaming-2025-05-14` beta header, remove it. Alongside a toolset entry, it returns a 400 error. For other platforms, see the computer use tool's [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section.
137137
138On the Claude API and Google Cloud, Claude Haiku 5.5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. Claude Haiku 4.5 doesn't support it.
138On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. Claude Haiku 4.5 doesn't support it.
139139
140140## Replay thinking blocks through the account that produced them
141141
from line 147
147147
148148## Migrating to Claude Haiku 5.5 from Claude Haiku 3.5 and earlier Haiku models
149149
150Claude Haiku 3.5 is retired on the Claude API and Amazon Bedrock, and Claude Haiku 3 is retired on the Claude API and Google Cloud. Requests to a retired model fail. Google Cloud lists Claude Haiku 3.5 as deprecated and available only to existing customers. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
150Claude Haiku 3.5 is retired on the Claude API and Amazon Bedrock, and Claude Haiku 3 is retired on the Claude API and Claude Models on Google Cloud (Google managed). Requests to a retired model fail. Claude Models on Google Cloud (Google managed) lists Claude Haiku 3.5 as deprecated and available only to existing customers. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
151151
152152From either model, first apply every preceding section, then these changes:
153153
154* **Model ID:** Replace `claude-3-5-haiku-20241022`, its alias `claude-3-5-haiku-latest`, or `claude-3-haiku-20240307` with `claude-haiku-5-5`. On Google Cloud, replace `claude-3-5-haiku@20241022` with `claude-haiku-5-5`. On Amazon Bedrock, use the Claude Haiku 5.5 ID from [Use the Claude Haiku 5.5 model ID](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#use-the-claude-haiku-5-5-model-id).
154* **Model ID:** Replace `claude-3-5-haiku-20241022`, its alias `claude-3-5-haiku-latest`, or `claude-3-haiku-20240307` with `claude-haiku-5-5`. On Claude Models on Google Cloud (Google managed), replace `claude-3-5-haiku@20241022` with `claude-haiku-5-5`. On Amazon Bedrock, use the Claude Haiku 5.5 ID from [Use the Claude Haiku 5.5 model ID](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#use-the-claude-haiku-5-5-model-id).
155155* **Code execution:** Claude Haiku 5.5 accepts `code_execution_20250825` and later versions. If you use the legacy Python-only `code_execution_20250522`, move to one of them. See [Upgrade to latest tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version).
156156* **Text editor:** If you use the text editor tool, move to `text_editor_20250728` (tool name `str_replace_based_edit_tool`), which has no `undo_edit` command. See [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool).
157157* **Stop reasons:** Handle `refusal` and `model_context_window_exceeded`. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
models/haiku-5-5/overview Changed · +14 / -13 lines
from line 43
4343
4444### Model IDs
4545
46| Platform | Model ID |
47| :----------------------------------------------------------------------------------------------------- | :--------------------------- |
48| Claude API | `claude-haiku-5-5` |
49| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-5-5` |
50| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | `claude-haiku-5-5` |
51| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-5-5` |
52| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-haiku-5-5` |
46| Platform | Model ID |
47| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------- |
48| Claude API | `claude-haiku-5-5` |
49| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-5-5` |
50| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-haiku-5-5` |
51| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-5-5` |
52| [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) | `claude-haiku-5-5` |
53| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-haiku-5-5` |
5354
5455### Pricing
5556
from line 81
8081
8182### Availability
8283
83| Feature | Value |
84| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
85| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (latest) |
86| Released | October 7, 2026 |
87| Retirement | Not sooner than October 7, 2027 |
88| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
84| Feature | Value |
85| :---------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
86| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (latest) |
87| Released | October 7, 2026 |
88| Retirement | Not sooner than October 7, 2027 |
89| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
8990
9091## Good to know
9192
models/haiku-5-5/whats-new-haiku-5-5 Changed · +18 / -18 lines
from line 12
1212
1313Each row names one change, whether it is new, changed, or breaking, and what your code has to do.
1414
15| Change | Type | Action needed |
16| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
17| [Adaptive thinking and effort](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#adaptive-thinking-and-effort) | New | Optional: set `effort` to trade response quality against speed and cost. |
18| [Larger context window and output](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#larger-context-window-and-output) | New | None. Existing `max_tokens` values stay valid, but thinking tokens count toward them. Long prompts are billed at higher prices; see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing). |
19| [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | New | None. Available on the Claude API and Google Cloud. |
20| [Safety classifiers can decline a request](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn't available. |
21| [Manual extended thinking returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Breaking | Replace `budget_tokens` with adaptive thinking. |
22| [Sampling parameters can return an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters) | Breaking | Omit `temperature`, `top_p`, and `top_k`. |
23| [Assistant message prefill returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill) | Breaking | End `messages` with a user turn. |
24| [`computer_20250124` returns an error on the Claude API, Google Cloud, and Amazon Bedrock](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) | Breaking | Replace it with `computer_toolset_20260801` on the Claude API and Google Cloud, or with `computer_20251124` on Amazon Bedrock. |
25| [Changing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#keep-earlier-turns-unchanged) | Breaking | Keep conversations append-only if you send thinking blocks back. |
26| [Responses can start with thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#responses-can-begin-with-thinking-blocks) | Changed | Select content blocks by `type`, not by position. |
27| [Thinking text is omitted by default](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Changed | To receive summarized thinking, set `thinking.display` to `"summarized"`. |
28| [Same text counts as more tokens](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#same-text-counts-as-more-tokens) | Changed | Recount prompts and revisit `max_tokens` and cost estimates. |
29| [Replaying thinking blocks across accounts](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#replaying-thinking-blocks-across-accounts) | Changed | If you replay stored conversations through a different account, replay each through the account that produced it. |
30| [Earlier thinking blocks stay in context](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#earlier-thinking-blocks-stay-in-context) | Changed | Expect more input tokens in multi-turn conversations. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). |
31| [Shorter prompts can be cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations) | Changed | None. The minimum cacheable prompt length is 512 tokens, down from 4,096 on Claude Haiku 4.5, so a prompt in between that sets `cache_control` is cached on Claude Haiku 5.5. |
32| [Context awareness tags aren't injected](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness) | Changed | To give the model an explicit budget for an agentic loop, use [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta). |
15| Change | Type | Action needed |
16| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
17| [Adaptive thinking and effort](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#adaptive-thinking-and-effort) | New | Optional: set `effort` to trade response quality against speed and cost. |
18| [Larger context window and output](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#larger-context-window-and-output) | New | None. Existing `max_tokens` values stay valid, but thinking tokens count toward them. Long prompts are billed at higher prices; see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing). |
19| [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | New | None. Available on the Claude API and Claude Models on Google Cloud (Google managed). |
20| [Safety classifiers can decline a request](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn't available. |
21| [Manual extended thinking returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Breaking | Replace `budget_tokens` with adaptive thinking. |
22| [Sampling parameters can return an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters) | Breaking | Omit `temperature`, `top_p`, and `top_k`. |
23| [Assistant message prefill returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill) | Breaking | End `messages` with a user turn. |
24| [`computer_20250124` returns an error on the Claude API, Claude Models on Google Cloud (Google managed), and Amazon Bedrock](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) | Breaking | Replace it with `computer_toolset_20260801` on the Claude API and Claude Models on Google Cloud (Google managed), or with `computer_20251124` on Amazon Bedrock. |
25| [Changing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#keep-earlier-turns-unchanged) | Breaking | Keep conversations append-only if you send thinking blocks back. |
26| [Responses can start with thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#responses-can-begin-with-thinking-blocks) | Changed | Select content blocks by `type`, not by position. |
27| [Thinking text is omitted by default](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Changed | To receive summarized thinking, set `thinking.display` to `"summarized"`. |
28| [Same text counts as more tokens](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#same-text-counts-as-more-tokens) | Changed | Recount prompts and revisit `max_tokens` and cost estimates. |
29| [Replaying thinking blocks across accounts](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#replaying-thinking-blocks-across-accounts) | Changed | If you replay stored conversations through a different account, replay each through the account that produced it. |
30| [Earlier thinking blocks stay in context](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#earlier-thinking-blocks-stay-in-context) | Changed | Expect more input tokens in multi-turn conversations. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). |
31| [Shorter prompts can be cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations) | Changed | None. The minimum cacheable prompt length is 512 tokens, down from 4,096 on Claude Haiku 4.5, so a prompt in between that sets `cache_control` is cached on Claude Haiku 5.5. |
32| [Context awareness tags aren't injected](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness) | Changed | To give the model an explicit budget for an agentic loop, use [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta). |
3333
3434## New capabilities
3535
models/mythos-5-1/overview Changed · +12 / -12 lines
from line 38
3838
3939### Model IDs
4040
41| Platform | Model ID |
42| :----------------------------------------------------------------------------------------------------- | :---------------------------- |
43| Claude API | `claude-mythos-5-1` |
44| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-mythos-5-1` |
45| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | `claude-mythos-5-1` |
46| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-mythos-5-1` |
41| Platform | Model ID |
42| :--------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------- |
43| Claude API | `claude-mythos-5-1` |
44| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-mythos-5-1` |
45| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-mythos-5-1` |
46| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-mythos-5-1` |
4747
4848### Pricing
4949
from line 73
7373
7474### Availability
7575
76| Feature | Value |
77| :---------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
78| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (verification required) |
79| Released | September 1, 2026 |
80| Retirement | Not sooner than September 1, 2027 |
81| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
76| Feature | Value |
77| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
78| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (verification required) |
79| Released | September 1, 2026 |
80| Retirement | Not sooner than September 1, 2027 |
81| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
8282
8383## Reference
8484
models/mythos-5/overview Changed · +12 / -12 lines
from line 37
3737
3838### Model IDs
3939
40| Platform | Model ID |
41| :----------------------------------------------------------------------------------------------------- | :-------------------------- |
42| Claude API | `claude-mythos-5` |
43| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-mythos-5` |
44| [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) | `claude-mythos-5` |
45| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-mythos-5` |
40| Platform | Model ID |
41| :--------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------- |
42| Claude API | `claude-mythos-5` |
43| [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-mythos-5` |
44| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-mythos-5` |
45| [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | `claude-mythos-5` |
4646
4747### Pricing
4848
from line 71
7171
7272### Availability
7373
74| Feature | Value |
75| :---------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
76| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (verification required) |
77| Released | June 9, 2026 |
78| Retirement | Not sooner than June 9, 2027 |
79| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
74| Feature | Value |
75| :---------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
76| [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations) | Active (verification required) |
77| Released | June 9, 2026 |
78| Retirement | Not sooner than June 9, 2027 |
79| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
8080
8181## Resources
8282