One read of Claude Developer Platformapi-20261007T190728Z
91 pages moved out of 754 read.
Pages moved
91
significant first
Pages read
754
in this capture
Captured
19:07 UTC
Corpus hash
4b90aa04d919
corpus-hash
What this read moved
76-91 of 91, page 4 of 4This capture is too large to show at once. Changes 76-91 of 91 are below, significant first; the rest are on the following screens.
cli-sdks-libraries/sdks/typescript Changed · +1 / -1 lines
from line 140
140140
141141This SDK provides helpers for making it easy to create and run tools in the Messages API. You can use Zod schemas or JSON Schemas to describe the input to a tool. You can then run those tools using the `client.beta.messages.toolRunner()` method. This method handles passing the inputs generated by the chosen model into the right tool and passing the result back to the model.
142142
143For more details on tool use, see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
143For more details on tool use, see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). To run the browser use tool or the computer use tool with this SDK, see [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk).
144144
145145```typescript
146146import { betaZodTool } from "@anthropic-ai/sdk/helpers/beta/zod";
get-started Changed · +2 / -2 lines
from line 436
436436 }
437437
438438 dependencies {
439 implementation("com.anthropic:anthropic-java:2.68.0")
439 implementation("com.anthropic:anthropic-java:2.69.0")
440440 }
441441
442442 application {
from line 462
462462 <dependency>
463463 <groupId>com.anthropic</groupId>
464464 <artifactId>anthropic-java</artifactId>
465 <version>2.68.0</version>
465 <version>2.69.0</version>
466466 </dependency>
467467 </dependencies>
468468 </project>
home Changed · +1 / -1 lines
from line 412
412412 * [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) (`claude-fable-5-1`) — New — *For demanding reasoning and long-horizon agentic work* — Most capable · Research · Multi-day tasks
413413 * [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) (`claude-opus-5-5`) — New — *For long-running agentic coding and knowledge work* — Complex projects · Agents · Coding
414414 * [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) (`claude-sonnet-5-5`) — New — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient
415 * [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (`claude-haiku-4-5`) — *The fastest model with near-frontier intelligence* — Fastest · Lowest cost · High volume
415 * [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) (`claude-haiku-5-5`) — New — *For high-volume, latency-sensitive tasks such as classification, extraction, and routing* — Fastest · Lowest cost · High volume
416416 </HomeSection>
417417
418418 <HomeSection last>
intro Changed · +1 / -1 lines
from line 24
2424* [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) (`claude-fable-5-1`) — New — *For demanding reasoning and long-horizon agentic work* — Most capable · Research · Multi-day tasks
2525* [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) (`claude-opus-5-5`) — New — *For long-running agentic coding and knowledge work* — Complex projects · Agents · Coding
2626* [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) (`claude-sonnet-5-5`) — New — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient
27* [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (`claude-haiku-4-5`) — *The fastest model with near-frontier intelligence* — Fastest · Lowest cost · High volume
27* [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) (`claude-haiku-5-5`) — New — *For high-volume, latency-sensitive tasks such as classification, extraction, and routing* — Fastest · Lowest cost · High volume
2828
2929[Compare models](https://platform.claude.com/docs/en/models/overview)
3030
manage-claude/compliance-content-data Changed · +4 / -0 lines
from line 24
2424
2525Use [List chats](https://platform.claude.com/docs/en/api/compliance/apps/chats/list) to page through chat metadata, then [Get chat messages](https://platform.claude.com/docs/en/api/compliance/apps/chats/messages/list) to fetch the full message content of one chat.
2626
27Chats in the unified Claude experience are returned by these endpoints like any other chat: a chat that continues in a session in the cloud comes back as one chat. The work Claude does there appears in each message's `content` as `tool_use` blocks (the tool's `name` and `input`) and `tool_result` blocks (its output, matched by `tool_use_id`). Coverage of these chats is in beta.
28
2729The chat list endpoint defaults to organization-wide scope: leave off `user_ids[]` to include every chat under your parent organization. Add `order_by=updated_at` to sort by last update time. This combination is the recommended way to export chats and keep an export current, because one paginated loop picks up new chats, chats with new messages, and chats deleted in claude.ai for every user without enumerating users first. The following request lists chats updated since a given date.
2830
2931```bash cURL
from line 273
271273* [Delete file](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/delete): handles both chat files and project files.
272274* [Delete project document](https://platform.claude.com/docs/en/api/compliance/apps/projects/documents/delete): removes a single project document by ID.
273275* [Delete project](https://platform.claude.com/docs/en/api/compliance/apps/projects/delete): see [Detach chats before deleting a project](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#detach-chats-before-deleting-a-project).
276
277For a chat in the unified Claude experience, [Delete chat](https://platform.claude.com/docs/en/api/compliance/apps/chats/delete) also deletes the sessions in the cloud that were started for the chat. It does not delete sessions that those sessions started.
274278
275279All four endpoints require the `delete:compliance_user_data` scope, which is granted separately from the read scope when the Compliance Access Key is created.
276280
manage-claude/compliance-sessions Changed · +2 / -0 lines
from line 349
349349
350350`product_surface` (string or `null`) identifies the product that created the session. The endpoint currently returns only sessions with `product_surface` of `cowork_remote`: Cowork sessions started on claude.ai web or mobile.
351351
352To retrieve a chat in the unified Claude experience, including the part that ran in the cloud, use the chat endpoints ([Get chat messages](https://platform.claude.com/docs/en/api/compliance/apps/chats/messages/list)), not the remote session endpoints.
353
352354<Note>
353355 **Build forward-compatible handlers.** Pass through unrecognized `status` and `product_surface` values, and ignore fields your handler does not expect, so your integration keeps working as new statuses and product surfaces ship.
354356</Note>
manage-claude/inference-hooks Changed · +3 / -1 lines
from line 25
2525
2626The following diagram traces one example (a Cowork request where Claude also calls an O365 tool) to illustrate which parts of the flow are hooked. The hooked points are the diagram's steps 1, 2, and 3, where the prompt arrives, Claude calls the tool, and the tool result returns. At each one, your AI security server returns a verdict before the flow continues. Step 2 is hooked only with **Validate tool calls** on, and its one verdict covers all the tool calls in a response.
2727
28
28<Frame>
29 
30</Frame>
2931
3032A verdict is a small JSON object: `{"action": "allow"}` lets the request proceed, and a deny carries the user-facing reason. For the full verdict schema, see [Return a verdict](https://platform.claude.com/docs/en/manage-claude/inference-hooks-endpoint#return-a-verdict).
3133
manage-claude/inference-hooks-configuration Changed · +1 / -1 lines
from line 155
155155
156156## Audit trail
157157
158Inference hooks activity is recorded in your organization's [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed): configuration changes, denials, circuit breaker trips, and requests that proceeded without inspection because no verdict could be obtained. That last kind is recorded only while **Enforce verdicts** is on and **Mode** is **Allow the request**. Its reason is `endpoint_timeout`, `endpoint_error` for any other problem calling your AI security server, or `internal_error` for a failure on Anthropic's side. Under **Block the request** or **Shadow mode**, failed requests aren't recorded individually, and the circuit breaker's automatic recovery isn't recorded. While the circuit breaker is tripped, no per-request Inference hooks activities are recorded; the trip activity is the feed's record of that window. Denial records carry identifiers that let you join each denial to the matching record in your own system.
158Inference hooks activity is recorded in your organization's [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed): configuration changes, denials, circuit breaker trips, and requests that proceeded without inspection because no verdict could be obtained. That last kind is recorded only while **Enforce verdicts** is on and **Mode** is **Allow the request**. Its reason is `endpoint_timeout`, `endpoint_error` for any other problem calling your AI security server, or `internal_error` for a failure on Anthropic's side. Under **Block the request** or **Shadow mode**, failed requests aren't recorded individually. The circuit breaker's automatic recovery isn't recorded in any mode. While the circuit breaker is tripped, no per-request Inference hooks activities are recorded; the trip activity is the feed's record of that window. Denial records carry identifiers that let you join each denial to the matching record in your own system.
159159
160160## Turn Inference hooks off
161161
managed-agents/events-and-streaming Changed · +1 / -1 lines
from line 2640
26402640### Sending system messages
26412641
26422642<Note>
2643 `system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Sonnet 5.5. If the agent's primary model does not support mid-conversation system injection, the event is rejected with a `model_does_not_support_mid_conversation_system` validation error. Subagent models are not checked, because `system.message` lands on the primary thread only.
2643 `system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Sonnet 5.5, and Claude Haiku 5.5. If the agent's primary model does not support mid-conversation system injection, the event is rejected with a `model_does_not_support_mid_conversation_system` validation error. Subagent models are not checked, because `system.message` lands on the primary thread only.
26442644</Note>
26452645
26462646Send a `system.message` event to give the agent privileged system-level context that applies to the accompanying turn and all subsequent turns. Unlike the `system` field on the agent definition (which sets the top-level system prompt), `system.message` content is appended to the session's system context as a `role: "system"` turn rather than replacing that prompt. Use it when the agent needs updated system-level guidance mid-session: a different persona, revised constraints, or context fetched at runtime that should shape the model's behavior going forward.
managed-agents/quickstart Changed · +2 / -2 lines
from line 43
4343 For Linux environments, download the release binary directly.
4444
4545 ```bash
46 VERSION=1.38.0
46 VERSION=1.39.0
4747 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
4848 case $(uname -m) in
4949 x86_64) ARCH=amd64 ;;
from line 94
9494
9595 <Tab title="Java">
9696 ```groovy Gradle
97 implementation("com.anthropic:anthropic-java:2.68.0")
97 implementation("com.anthropic:anthropic-java:2.69.0")
9898 ```
9999 </Tab>
100100
managed-agents/self-hosted-sandboxes-workers Changed · +1 / -1 lines
from line 447
447447
448448 ```dockerfile
449449 FROM your-base-image
450 ARG ANT_VERSION=1.38.0
450 ARG ANT_VERSION=1.39.0
451451 ARG TARGETARCH
452452 RUN ARCH=$([ "$TARGETARCH" = "arm64" ] && echo arm64 || echo amd64) && \
453453 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${ANT_VERSION}/ant_${ANT_VERSION}_linux_${ARCH}.tar.gz" \
models/sonnet-5-5/migration-guide Changed · +1 / -1 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
23Claude Sonnet 5.5 has the same prices as Claude Sonnet 5. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview). For features and prompting, see [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
23Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview). For features and prompting, see [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
2424
2525## Send a request to Claude Sonnet 5.5
2626
models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +1 / -1 lines
from line 102
102102
103103## Pricing
104104
105Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, including prompt caching and batch processing rates. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for the full list, data residency, and tool pricing.
105Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for the full list, data residency, and tool pricing.
106106
107107## Availability
108108
release-notes/system-prompts/overview Changed · +2 / -0 lines
from line 7
77Claude's web interface ([claude.ai](https://claude.ai)) and mobile apps use a system prompt to provide up-to-date information, such as the current date, to Claude at the start of every conversation. The system prompt also encourages certain behaviors, such as always providing code snippets in Markdown. This prompt is periodically updated to improve Claude's responses. These system prompt updates do not apply to the Claude API. Some models have multiple dated entries on their pages. Starting with the Claude 4.6 generation, each model ID is a [single fixed snapshot](https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions), so those models have one entry.
88
99<CardGroup cols={3}>
10 <Card id="claude-haiku-5-5" title="Claude Haiku 5.5" icon="file" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-haiku-5-5" />
11
1012 <Card id="claude-sonnet-5-5" title="Claude Sonnet 5.5" icon="file" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-sonnet-5-5" />
1113
1214 <Card id="claude-opus-5-5" title="Claude Opus 5.5" icon="file" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-opus-5-5" />
resources/overview Changed · +4 / -0 lines
from line 5
55---
66
77<CardGroup cols={3}>
8 <Card title="Claude Haiku 5.5 System Card" icon="file" href="https://www.anthropic.com/document/claude-haiku-5-5-system-card">
9 Detailed documentation of Claude Haiku 5.5.
10 </Card>
11
812 <Card title="Claude Opus 5.5 System Card" icon="file" href="https://www.anthropic.com/claude-opus-5-5-system-card">
913 Detailed documentation of Claude Opus 5.5.
1014 </Card>
test-and-evaluate/develop-tests Changed · +3 / -1 lines
from line 6
66
77Building a successful LLM-based application starts with clearly defining your success criteria and then designing evaluations to measure performance against them. This cycle is central to prompt engineering.
88
9
9<Frame>
10 
11</Frame>
1012
1113## Define your success criteria
1214