174 pages for extract.

Skills Claude Developer Platform · in the page api/skills …cription: string` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: string` The Skill's immutable kebab-case slug, set at creat… Versions Claude Developer Platform · in the page api/skills/versions …cription: string` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: string` The Skill's immutable kebab-case slug, set at creat… Create Skill Version Claude Developer Platform · in the page api/skills/versions/create …cription: string` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: string` The Skill's immutable kebab-case slug, set at creat… List Skill Versions Claude Developer Platform · in the page api/skills/versions/list …cription: string` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: string` The Skill's immutable kebab-case slug, set at creat… Get Skill Version Claude Developer Platform · in the page api/skills/versions/retrieve …cription: string` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: string` The Skill's immutable kebab-case slug, set at creat… Message Batches API Claude Developer Platform · in the page build-with-claude/batch-processing …length drafts and technical documentation, exhaustive structured data extraction, large code-generation scaffolds, and long reasoning chains. A single 300k-token generation can take over an hour to c… citations Claude Developer Platform · in the page build-with-claude/citations …ons into the response formats described in the following sections and extracts `cited_text` directly, citations are guaranteed to contain valid pointers to the provided documents. * **Improved citat… claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …requires citations to be enabled * Without citations, only basic text extraction is available * For full control without forced citations, use the InvokeModel API ### Mid-conversation system messages… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …ed in `<summary></summary>` tags. 3. **Context replacement:** The SDK extracts the summary and replaces the entire message history with it. 4. **Continuation:** The conversation resumes from the summa… files Claude Developer Platform · in the page build-with-claude/files …docs/en/build-with-claude/pdf-support"> Process PDFs with Claude. Extract text, analyze charts, and understand visual content from your documents. </Card> <Card title="Code execution tool" ic… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …Francisco?"}], ) if response.stop_reason == "tool_use": # Extract and execute the tool for block in response.content: if block.type == "tool_use": result = ex… pdf-support Claude Developer Platform · in the page build-with-claude/pdf-support …build-with-claude/pdf-support description: "Process PDFs with Claude: extract text, analyze charts, and understand visual content from your documents." featureMetadata: status: ga zdr: eligibi… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …llowing, long-run progress claims, memory systems, and the `reasoning_extraction` refusal category.… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …e sciences content (such as lab methods or molecular mechanisms), and extraction of the model's summarized thinking. Benign cybersecurity work and beneficial life sciences tasks might also trigger the… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …write its thinking or reasoning might be declined with the `reasoning_extraction` category. Ask for a short explanation or a summary of the actions taken instead, or read the reasoning from [summarize… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …rms better for API use cases with carefully tuned prompts, structured extraction, and pipelines where you want predictable behavior. If you need Claude to apply an instruction broadly, state the scope… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …verbatim or in a fixed format, might be declined with the `reasoning_extraction` [refusal category](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). Ask… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …reasoning in the response text might be declined with the `reasoning_extraction` [refusal category](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). * **… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …rms better for API use cases with carefully tuned prompts, structured extraction, and pipelines where you want predictable behavior. If you need Claude to apply an instruction broadly, state the scope… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …could help with the development of competing AI models. * `reasoning_extraction`: the request asks the model to reproduce its internal reasoning in the response text. * `general_harms`: the request f… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …| Yes | | `"reasoning_extraction"` | The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structur… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …de_execution_20250825", "name": "code_execution"}], ) # Step 2: Extract file IDs from the response def extract_file_ids(response): file_ids = [] for item in response.content:… structured-outputs Claude Developer Platform · in the page build-with-claude/structured-outputs …at`): Get Claude's response in a specific JSON format, for example to extract data from images or text, generate structured reports, or format API responses. This page covers JSON outputs. * **Strict… thinking Claude Developer Platform · in the page build-with-claude/thinking …response text may be refused with `stop_details.category: "reasoning_extraction"`. See [Refusal categories](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-respons… thinking-tool-workflows Claude Developer Platform · in the page build-with-claude/thinking-tool-workflows …"user", "content": "What's the weather in Paris?"}], ) # Extract the tool use block to get its ID for the tool result tool_use_block = next(block for block in response.content if bl… vision Claude Developer Platform · in the page build-with-claude/vision …nd best-practice techniques for tasks such as interpreting charts and extracting content from forms. </Card> <Card title="API reference" icon="code" href="https://platform.claude.com/docs/en/api/… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …p with your original image. You'll need this for OCR pipelines, form extraction, chart parsing, UI element location, and any task where you act on a specific region of an image. For sending images, s… API usage primer for Claude Claude Developer Platform · in the page claude_api_primer …"role": "user", "content": "What's the weather in Paris?"}], ) # Extract thinking block and tool use block thinking_block = next( (block for block in response.content if block.type == "th… quickstart Claude Developer Platform · in the page cli-sdks-libraries/cli/quickstart …nlines file contents into string fields with an `@path` reference. It extracts response fields with a built-in `--transform` query, so you don't need a separate tool such as `jq`, and it paginates lis… scripting Claude Developer Platform · in the page cli-sdks-libraries/cli/scripting …apply to errors, so use `--format-error yaml` for an unquoted scalar. Extract only the error message: ```bash ant beta:agents retrieve --agent-id bogus \ --transform-error error.message --format-er… using Claude Developer Platform · in the page cli-sdks-libraries/cli/using …..", "name": "Coding Assistant", "model": "claude-opus-5-5"} ``` ### Extract a scalar To capture a single field as an unquoted string (for example, the ID of a newly created resource), pair `--trans… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …apiKey("YOUR_API_KEY")) ``` <Warning> A key bundled into an app is extractable from the shipping binary, and anyone who extracts it can make requests billed to your account. Use `.apiKey` for devel… typescript Claude Developer Platform · in the page cli-sdks-libraries/sdks/typescript …onments. Any user with access to the browser can potentially inspect, extract, and misuse these credentials. This could lead to unauthorized access using your credentials and potentially compromise se… home Claude Developer Platform · in the page home …w — *For high-volume, latency-sensitive tasks such as classification, extraction, and routing* — Fastest · Lowest cost · High volume </HomeSection> <HomeSection last> <HomeSectionHeader label… intro Claude Developer Platform · in the page intro …w — *For high-volume, latency-sensitive tasks such as classification, extraction, and routing* — Fastest · Lowest cost · High volume [Compare models](https://platform.claude.com/docs/en/models/overvi… WARNING: This operation PERMANENTLY deletes the chat, all of its messages, Claude Developer Platform · in the page manage-claude/compliance-content-data …es, PowerPoint files, and some PDFs) are stored as the text claude.ai extracted from them. For these documents, the endpoint returns the extracted text under the original file name, and the original d… before_id is the first_id from a previous response Claude Developer Platform · in the page manage-claude/compliance-integration-patterns …). * The original file for a chat attachment that claude.ai stored as extracted text, such as some Word, PowerPoint, and PDF uploads (the file content endpoint returns the extracted text; see [Retriev… inference-hooks Claude Developer Platform · in the page manage-claude/inference-hooks …he user sees: transcript text, tool calls and their results, and text extracted from attachments. It never receives raw file or image bytes, system prompts, or Anthropic-internal context. The Inferen… inference-hooks-endpoint Claude Developer Platform · in the page manage-claude/inference-hooks-endpoint …e. `text`: the text content of the attachment when available, such as extracted document text, an audio transcript, or link metadata. Raw attachment bytes are never sent.… Replace NODE_UID with the node's UID: Claude Developer Platform · in the page manage-claude/wif-providers/spiffe …response as a two-element JSON array, so `jq -r '.[0].svids[0].svid'` extracts the bare token. On older SPIRE versions without `-output`, the command prints a labeled block instead. In that case, pipe… files Claude Developer Platform · in the page managed-agents/files …uments (`.txt`, `.md`) * Archives (`.zip`, `.tar.gz`) - the agent can extract these using bash * Binary files - the agent can process these with appropriate tools ## File paths <Note> Files mounte… spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …ater; the Python and Go SDKs use their standard libraries for archive extraction and have no additional binary requirements. * **The `ant` CLI or an Anthropic SDK** (Python, TypeScript, or Go) on the… self-hosted-sandboxes-reference Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-reference …itional binaries. These SDKs use their standard libraries for archive extraction. | [Memory stores](https://platform.claude.com/docs/en/managed-agents/self-hosted-san… tools Claude Developer Platform · in the page managed-agents/tools …tep. Bloated responses waste context and make it harder for Claude to extract what matters. ## Next steps <CardGroup cols={2}> <Card title="Restrict web search and web fetch domains" icon="shield"… overview Claude Developer Platform · in the page models/haiku-5-5/overview …26. For high-volume, latency-sensitive tasks such as classification, extraction, and routing Model ID: `claude-haiku-5-5` Context window: 1M tokens · Max output: 128K tokens · Input pricing: From $… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It supports adaptive thinking with the effort parameter, a 1M token context window, and up to 128k… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …gory` values such as `"bio"` in addition to `"cyber"` and `"reasoning_extraction"`; see the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal… whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …reasoning in the response text might be declined with the `reasoning_extraction` category. See [Refusals and fallback in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new… Models overview Claude Developer Platform · in the page models/overview …| For high-volume, latency-sensitive tasks such as classification, extraction, and routing | | Model page… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …uld help with the development of competing AI models. * **`"reasoning_extraction"`:** The request asks the model to reproduce its internal reasoning in the response text. * **`"general_harms"`:** The…