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
101-115 of 115, page 5 of 5This capture is too large to show at once. Changes 101-115 of 115 are below, significant first; the rest are on the following screens.
build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 Changed · +2 / -2 lines
from line 21
2121<Note>
2222 For the breaking API changes when migrating from Claude Haiku 4.5, see the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide).
2323
24 Several sections on this page suggest text to add to your system prompt. Add it to new conversations only. A request that sends thinking blocks back after `system` changed can return a 400 error, so a stored conversation resumed with the new system prompt can fail. To change instructions partway through a conversation, [put them in the newest turn](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#changing-context). On the Claude API, Amazon Bedrock, and Google Cloud, you can instead [append a system message to the conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions).
24 Several sections on this page suggest text to add to your system prompt. Add it to new conversations only. A request that sends thinking blocks back after `system` changed can return a 400 error, so a stored conversation resumed with the new system prompt can fail. To change instructions partway through a conversation, [put them in the newest turn](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#changing-context). On the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed), you can instead [append a system message to the conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions).
2525</Note>
2626
2727## Use effort to control thinking
from line 38
3838* Thinking is on by default and counts toward `max_tokens`, which can go up to 128,000. A `max_tokens` value sized for Claude Haiku 4.5 requests that ran without thinking can cut the reply off, so leave room for thinking.
3939* To get less thinking, lower the effort level. In Anthropic's testing, telling the model in the prompt to answer directly didn't stop it from thinking. You can also turn thinking off with `thinking: {"type": "disabled"}`. This works at `low`, `medium`, and `high` only. At `xhigh` and `max`, the request returns a 400 error.
4040* At `xhigh` effort in multi-turn chats, the model sometimes writes its whole answer in its thinking and ends the turn with no visible text. If you see this behavior, check each response for an empty reply.
41* Changing the top-level `effort` value between requests invalidates the prompt cache for the conversation's messages. On the Claude API and Google Cloud, you can change the level partway through a conversation with a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), which keeps the cache. A change holds for every later turn until another one replaces it. It needs the `mid-conversation-output-config-2026-07-01` beta header and adaptive thinking, which is the default. With thinking off, a per-message effort change returns a 400 error.
41* Changing the top-level `effort` value between requests invalidates the prompt cache for the conversation's messages. On the Claude API and Claude Models on Google Cloud (Google managed), you can change the level partway through a conversation with a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), which keeps the cache. A change holds for every later turn until another one replaces it. It needs the `mid-conversation-output-config-2026-07-01` beta header and adaptive thinking, which is the default. With thinking off, a per-message effort change returns a 400 error.
4242
4343## Accurate search results
4444
build-with-claude/prompt-engineering/prompting-claude-opus-4-8 Changed · +1 / -1 lines
from line 157
157157
158158## Computer use
159159
160Claude Opus 4.8 supports the `computer_toolset_20260801` toolset (on the Claude API and Google Cloud) and the earlier `computer_20251124` tool version. On the Claude API and Google Cloud, Claude Opus 4.8 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. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
160Claude Opus 4.8 supports the earlier `computer_20251124` tool version and, on the Claude API and Claude Models on Google Cloud (Google managed), the `computer_toolset_20260801` toolset. On those two platforms, Claude Opus 4.8 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. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
161161
162162For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model's behavior.
163163
build-with-claude/prompt-engineering/prompting-claude-sonnet-5 Changed · +1 / -1 lines
from line 149
149149
150150## Computer use
151151
152Claude Sonnet 5 supports the `computer_toolset_20260801` toolset (on the Claude API and Google Cloud) and the earlier `computer_20251124` tool version. On the Claude API and Google Cloud, Claude Sonnet 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. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
152Claude Sonnet 5 supports the earlier `computer_20251124` tool version and, on the Claude API and Claude Models on Google Cloud (Google managed), the `computer_toolset_20260801` toolset. On those two platforms, Claude Sonnet 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. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
153153
154154For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model's behavior.
155155
build-with-claude/search-results Changed · +1 / -1 lines
from line 2116
21162116
21172117## Limitations
21182118
2119* Search result content blocks are available on Claude API, Amazon Bedrock, and Google Cloud.
2119* Search result content blocks are available on Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed).
21202120* Only text content is supported within search results (no images or other media).
21212121* `search_result` blocks can only appear in user messages (including inside tool results). Assistant messages with search results are rejected.
21222122* When the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) is enabled in the same request, citations must be enabled on all `search_result` blocks.
build-with-claude/thinking-steering-and-cost Changed · +1 / -1 lines
from line 96
9696
9797Per-message steering is useful when only some requests in a conversation warrant extended reasoning. An agent harness, for example, can append the encouraging phrase on planning steps and the discouraging phrase on routine confirmations, without touching the system prompt or changing any request parameters between turns.
9898
99On Claude Haiku 5.5, the discouraging phrase doesn't reliably reduce thinking. On the Claude API and Google Cloud, run routine turns on that model with less thinking by using a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which also keeps the prompt cache.
99On Claude Haiku 5.5, the discouraging phrase doesn't reliably reduce thinking. On the Claude API and Claude Models on Google Cloud (Google managed), run routine turns on that model with less thinking by using a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which also keeps the prompt cache.
100100
101101### Verify steering on your workload
102102
cli-sdks-libraries/cli/authentication Changed · +1 / -1 lines
from line 85
8585
8686## Check authentication status
8787
88`ant auth status` prints the credential source the CLI selected (API key environment variable, OAuth login, federation, or profile), the active profile, the workspace the active token is bound to, and the configuration directory paths. Use it to diagnose why a workload picked the wrong credential or workspace.
88`ant auth status` prints the credential source the CLI selected (API key environment variable, OAuth login, federation, Google Cloud, or profile), the active profile, the workspace the active token is bound to, and the configuration directory paths. Use it to diagnose why a workload picked the wrong credential or workspace.
8989
9090```bash CLI
9191ant auth status
home Changed · +1 / -1 lines
from line 229
229229 Amazon Bedrock
230230 </HomeCloudPartnerLink>
231231
232 <HomeCloudPartnerLink icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai">
232 <HomeCloudPartnerLink icon="cloud" href="https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/overview">
233233 Google Cloud
234234 </HomeCloudPartnerLink>
235235
manage-claude/claude-code-analytics-api Changed · +1 / -1 lines
from line 262
262262
263263### Which Claude Code deployments are supported?
264264
265This API only tracks Claude Code usage on the Claude API. Usage through [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), or [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) is not included.
265This API only tracks Claude Code usage on the Claude API. Usage through [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), [Claude Models on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/overview), or [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) is not included.
266266
267267### What does it cost to use this API?
268268
manage-claude/usage-cost-api Changed · +4 / -0 lines
from line 28
2828 **Claude Platform on AWS:** The programmatic Usage and Cost API endpoints are not currently available. View usage and cost data on the **Usage** and **Cost** pages in the Claude Console instead.
2929</Note>
3030
31<Note>
32 **Claude Models on Google Cloud (Anthropic managed):** Of the Usage and Cost API endpoints, only the [usage endpoint](https://platform.claude.com/docs/en/manage-claude/usage-cost-api#usage-api) is available. Call it through the [organization-level base URL](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#making-requests) with Google Cloud credentials instead of an Admin API key. The only predefined [IAM role](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#iam-roles) that allows this call is `roles/claude.admin`. View cost data on the **Cost** page in the [Claude Console](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#using-the-claude-console).
33</Note>
34
3135## Which API do you need?
3236
3337Anthropic provides cost and usage reporting through two APIs, depending on which Claude product your organization manages:
manage-claude/user-profiles-verification-portal Changed · +1 / -1 lines
from line 192
192192
193193The end customer can see the linked profile under **Linked accounts** in the portal.
194194
195If your inference runs on Claude in Amazon Bedrock or Google Cloud, you have to link your own accounts too. Programs apply to requests from an AWS account or Google Cloud project only after you link it to the Anthropic organization that creates your profiles. 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).
195If your inference runs on Claude in Amazon Bedrock or Claude Models on Google Cloud (Google managed), you have to link your own accounts too. Programs apply to requests from an AWS account or Google Cloud project only after you link it to the Anthropic organization that creates your profiles. 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).
196196
197197## Next steps
198198
manage-claude/wif-reference Changed · +2 / -0 lines
from line 62
6262| 4 | Federation environment variables | `ANTHROPIC_FEDERATION_RULE_ID` + `ANTHROPIC_ORGANIZATION_ID` + `ANTHROPIC_SERVICE_ACCOUNT_ID` + `ANTHROPIC_IDENTITY_TOKEN[_FILE]`. |
6363| 5 | Active profile | Resolved from `<config_dir>/active_config`, falling back to a profile named `default`. |
6464
65In the `ant` CLI, the settings for [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#authentication) rank after the federation environment variables and before the active profile. The settings are the project, the workspace ID, and the location. You set them with the `--google-cloud-*` flags or the `ANTHROPIC_GOOGLE_CLOUD_*` variables. The CLI uses these settings when any one of them is set. With these settings, the CLI gets its credential from Google Application Default Credentials.
66
6567When a profile is loaded, environment variables fill any fields the profile omits but never override fields the profile sets explicitly. For example, `ANTHROPIC_WORKSPACE_ID` fills `workspace_id` only when the active profile does not set it.
6668
6769## Profile configuration file
manage-claude/workspaces Changed · +1 / -1 lines
from line 842
842842To look up your organization's workspace IDs, call the [List Workspaces](https://platform.claude.com/docs/en/api/organization/workspaces/list) endpoint (pass `include_default=true` to include the Default Workspace) or find them on the [Workspaces](https://platform.claude.com/settings/workspaces) page in the Claude Console.
843843
844844<Note>
845 [Prompt caches](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) are also isolated per workspace on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). On Amazon Bedrock and Google Cloud, prompt caches are isolated per organization.
845 [Prompt caches](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) are also isolated per workspace on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). On Amazon Bedrock and Claude Models on Google Cloud (Google managed), prompt caches are isolated per organization.
846846</Note>
847847
848848## Identify the workspace behind an API response
managed-agents/overview Changed · +1 / -1 lines
from line 20
2020Claude Managed Agents provides the harness and infrastructure for running Claude as an autonomous agent. Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and run code securely. The harness supports built-in prompt caching, compaction, and other performance optimizations for high-quality, efficient agent outputs. To build your own agent loop with direct model access instead, see [Using the Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages).
2121
2222<Note>
23 Claude Managed Agents is also available on Claude Platform on AWS, with some differences in feature availability and session behavior. See [Claude Managed Agents](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#claude-managed-agents) in the Claude Platform on AWS guide.
23 Claude Managed Agents is also available on Claude Platform on AWS and Claude Models on Google Cloud (Anthropic managed), with some differences in feature availability and session behavior. See [Claude Managed Agents](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#claude-managed-agents) in the Claude Platform on AWS guide or the [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#claude-managed-agents) guide.
2424</Note>
2525
2626<CardGroup cols={3}>
managed-agents/self-hosted-sandboxes-memory Changed · +2 / -0 lines
from line 23
2323
2424<Note>
2525 Memory stores cannot be attached to sessions on self-hosted environments on [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws).
26
27 On [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), memory stores aren't supported for sessions on self-hosted environments.
2628</Note>
2729
2830## Prepare the host
models/fable-5-1/whats-new-fable-5-1 Changed · +2 / -2 lines
from line 69
6969
7070### Change effort mid-conversation (beta)
7171
72On Claude Fable 5.1 you can change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level mid-conversation without invalidating the prompt cache. Raise it for a hard step and lower it for routine ones. Per-message effort is in beta: include the `mid-conversation-output-config-2026-07-01` beta header. Claude Fable 5.1 and Claude Mythos 5.1 support it on the Claude API, Google Cloud, and Amazon Bedrock. To use it with Claude Fable 5.1 through the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), send that value in the `anthropic_beta` array of the request body instead. For the other models that support it and the platforms for each, see [Change effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation).
72On Claude Fable 5.1 you can change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level mid-conversation without invalidating the prompt cache. Raise it for a hard step and lower it for routine ones. Per-message effort is in beta: include the `mid-conversation-output-config-2026-07-01` beta header. Claude Fable 5.1 and Claude Mythos 5.1 support it on the Claude API, Claude Models on Google Cloud (Google managed), and Amazon Bedrock. To use it with Claude Fable 5.1 through the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), send that value in the `anthropic_beta` array of the request body instead. For the other models that support it and the platforms for each, see [Change effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation).
7373
7474<CodeGroup>
7575 ```bash cURL
from line 426
426426
427427* **Claude API:** all customers, as `claude-fable-5-1`.
428428* **AWS:** [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-fable-5-1`, and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), as `claude-fable-5-1`.
429* **Google Cloud:** [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), as `claude-fable-5-1`.
429* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `claude-fable-5-1`, and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), as `claude-fable-5-1`.
430430* **Microsoft Foundry:** [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), on Anthropic infrastructure.
431431
432432Claude Mythos 5.1 is available only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). To request access, apply to the program that covers your use case, or contact your Anthropic, AWS, or Google Cloud account team.