> ## Documentation Index > Fetch the complete documentation index at: https://docs.helve.dev/llms.txt > Use this file to discover all available pages before exploring further. # Extract page content > URLs in, clean content out. Returns the full page as markdown or text, and optionally focused excerpts and a summary when you pass a `query`. URLs the provider cannot fetch are listed in `failed` rather than failing the whole request. ## OpenAPI ````yaml openapi.json POST /v1/extract openapi: 3.1.0 info: title: Helve API version: 1.0.0 description: >- One key, one request shape, one bill for the tools your software calls: web search across eleven engines, page extraction across nine, and transcription across three. Every response says which provider served it, how the request was adjusted for that provider, and what it cost. servers: - url: https://helve.dev description: Production security: - bearerAuth: [] tags: - name: Search description: >- Web search with one schema across Exa, Parallel, Tavily, Brave, Serper, Firecrawl, Linkup, Valyu, Jina, Octen, Perplexity, and the `fusion` panel. - name: Extract description: Fetch and clean pages by URL. - name: Transcription description: >- Durable speech-to-text jobs across AssemblyAI, Deepgram, and ElevenLabs. Submit a recording, poll the job. paths: /v1/extract: post: tags: - Extract summary: Extract page content description: >- URLs in, clean content out. Returns the full page as markdown or text, and optionally focused excerpts and a summary when you pass a `query`. URLs the provider cannot fetch are listed in `failed` rather than failing the whole request. operationId: extract requestBody: required: true content: application/json: example: urls: - https://arxiv.org/abs/2211.17192 query: how does speculative decoding work content: excerpts: max_per_url: 3 schema: type: object properties: urls: type: array items: type: string format: uri minItems: 1 maxItems: 20 description: >- The pages to extract, 1–20 absolute URLs. Providers that take one URL per call are fanned out by Helve. provider: type: string enum: - exa - tavily - parallel - serper - firecrawl - linkup - valyu - jina - octen - auto description: >- Which provider fetches and cleans the pages. `auto` (default) picks the first configured provider in Helve's priority order. Brave and Perplexity have no extraction product. query: type: string minLength: 1 description: >- What you are extracting for. Drives focused excerpts and summaries on providers that support them (Exa, Tavily, Parallel, Firecrawl, Valyu). content: type: object properties: full_text: type: boolean description: Return the whole page in `content`. Default true. max_chars: type: integer minimum: 100 maximum: 100000 description: >- Cap on `content` length per URL. Native on Exa; Helve truncates for other providers. excerpts: type: object properties: max_per_url: type: integer minimum: 1 maximum: 20 description: Cap on the number of excerpts per URL. max_chars_per_excerpt: type: integer minimum: 1 description: Cap on the length of each excerpt, in characters. additionalProperties: false description: >- Return focused excerpts in `excerpts`, instead of or alongside the full text. Most useful with `query`. summary: type: boolean description: >- Return a per-URL summary in `summary`. Native on Exa and Valyu. format: type: string enum: - markdown - text description: >- Output format for `content`. Native on Tavily and Serper; most providers return markdown regardless. additionalProperties: false description: What to return for each URL. include_links: type: boolean description: Return the page's outbound links in `links`. Native on Exa. include_images: type: boolean description: >- Return the page's image URLs in `images`. Native on Exa and Tavily. max_age_hours: type: integer minimum: 0 maximum: 720 description: >- Accept a cached copy up to this many hours old; 0 forces a live fetch. Native on Exa. timeout_ms: type: integer minimum: 1000 maximum: 90000 description: >- Per-page fetch timeout in milliseconds, 1000–90000. Native on Exa and Tavily. strict: type: boolean description: >- When true, any parameter the serving provider cannot honour is a 400 instead of a warning. Default false. provider_options: type: object properties: exa: type: object additionalProperties: nullable: true description: >- Passed verbatim to Exa when it serves the request; ignored by every other provider. parallel: type: object additionalProperties: nullable: true description: >- Passed verbatim to Parallel when it serves the request; ignored by every other provider. tavily: type: object additionalProperties: nullable: true description: >- Passed verbatim to Tavily when it serves the request; ignored by every other provider. brave: type: object additionalProperties: nullable: true description: >- Passed verbatim to Brave when it serves the request; ignored by every other provider. serper: type: object additionalProperties: nullable: true description: >- Passed verbatim to Serper when it serves the request; ignored by every other provider. firecrawl: type: object additionalProperties: nullable: true description: >- Passed verbatim to Firecrawl when it serves the request; ignored by every other provider. linkup: type: object additionalProperties: nullable: true description: >- Passed verbatim to Linkup when it serves the request; ignored by every other provider. octen: type: object additionalProperties: nullable: true description: >- Passed verbatim to Octen when it serves the request; ignored by every other provider. valyu: type: object additionalProperties: nullable: true description: >- Passed verbatim to Valyu when it serves the request; ignored by every other provider. jina: type: object additionalProperties: nullable: true description: >- Passed verbatim to Jina when it serves the request; ignored by every other provider. additionalProperties: false description: >- Escape hatch for provider-native parameters, keyed by provider id and merged into that provider's request unchanged. required: - urls additionalProperties: false responses: '200': description: Extracted content content: application/json: schema: type: object properties: id: type: string description: Helve's id for this extraction, `ext_…`. provider: type: string enum: - exa - tavily - parallel - serper - firecrawl - linkup - valyu - jina - octen description: >- The provider that served the request, resolved from `auto`. results: type: array items: type: object properties: url: type: string description: The URL as requested. final_url: type: string description: >- The URL after redirects, when the provider reports it. title: type: string content: type: string description: >- The full extracted page, in markdown or text per `content.format`. excerpts: type: array items: type: string description: Focused excerpts, when requested. summary: type: string description: Per-URL summary, when requested and supported. published_date: type: string description: ISO 8601 date when known. author: type: string links: type: array items: type: string images: type: array items: type: string raw: nullable: true description: >- The provider's original result object, verbatim. Always present. required: - url additionalProperties: false description: One entry per successfully extracted URL. failed: type: array items: type: object properties: url: type: string error: type: string required: - url - error additionalProperties: false description: >- URLs the provider could not fetch, with its reason. Partial success is a 200. warnings: type: array items: type: object properties: code: type: string enum: - param_ignored - param_approximated - results_post_filtered param: type: string description: The request field the warning concerns. message: type: string required: - code - message additionalProperties: false description: >- How the request was adjusted for the serving provider. Empty when it was honoured exactly. usage: type: object properties: cost_usd: type: number description: >- What this request debited from your balance: the provider's raw price. credits: type: number required: - cost_usd - credits additionalProperties: false latency_ms: type: number description: Wall-clock time Helve spent on the request. required: - id - provider - results - failed - warnings - usage - latency_ms additionalProperties: false '400': description: Invalid request content: application/json: schema: type: object properties: error: type: object properties: type: type: string enum: - unauthorized - invalid_request - provider_not_available - provider_not_configured - provider_error - not_found - insufficient_credits description: >- Stable machine-readable category. `invalid_request` carries validation issues in `detail`; `provider_error` carries the provider's own error body. message: type: string description: Human-readable explanation. detail: nullable: true description: >- Validation issues for `invalid_request`; the provider's error body for `provider_error`. required: - type - message additionalProperties: false required: - error additionalProperties: false '401': description: Missing or invalid API key content: application/json: schema: type: object properties: error: type: object properties: type: type: string enum: - unauthorized - invalid_request - provider_not_available - provider_not_configured - provider_error - not_found - insufficient_credits description: >- Stable machine-readable category. `invalid_request` carries validation issues in `detail`; `provider_error` carries the provider's own error body. message: type: string description: Human-readable explanation. detail: nullable: true description: >- Validation issues for `invalid_request`; the provider's error body for `provider_error`. required: - type - message additionalProperties: false required: - error additionalProperties: false '402': description: Insufficient credits content: application/json: schema: type: object properties: error: type: object properties: type: type: string enum: - unauthorized - invalid_request - provider_not_available - provider_not_configured - provider_error - not_found - insufficient_credits description: >- Stable machine-readable category. `invalid_request` carries validation issues in `detail`; `provider_error` carries the provider's own error body. message: type: string description: Human-readable explanation. detail: nullable: true description: >- Validation issues for `invalid_request`; the provider's error body for `provider_error`. required: - type - message additionalProperties: false required: - error additionalProperties: false '502': description: Provider error content: application/json: schema: type: object properties: error: type: object properties: type: type: string enum: - unauthorized - invalid_request - provider_not_available - provider_not_configured - provider_error - not_found - insufficient_credits description: >- Stable machine-readable category. `invalid_request` carries validation issues in `detail`; `provider_error` carries the provider's own error body. message: type: string description: Human-readable explanation. detail: nullable: true description: >- Validation issues for `invalid_request`; the provider's error body for `provider_error`. required: - type - message additionalProperties: false required: - error additionalProperties: false '503': description: Provider not configured content: application/json: schema: type: object properties: error: type: object properties: type: type: string enum: - unauthorized - invalid_request - provider_not_available - provider_not_configured - provider_error - not_found - insufficient_credits description: >- Stable machine-readable category. `invalid_request` carries validation issues in `detail`; `provider_error` carries the provider's own error body. message: type: string description: Human-readable explanation. detail: nullable: true description: >- Validation issues for `invalid_request`; the provider's error body for `provider_error`. required: - type - message additionalProperties: false required: - error additionalProperties: false security: - bearerAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer description: >- An API key from the dashboard, `sk_live_…`, sent as `Authorization: Bearer sk_live_…`. ````