> ## Documentation Index > Fetch the complete documentation index at: https://docs.octen.ai/llms.txt > Use this file to discover all available pages before exploring further. # Extract > Extracts clean markdown content from URLs. Supports batch processing, query-focused highlights, page classification, and multimedia resources. ## OpenAPI ````yaml /api-reference/openapi.json post /extract openapi: 3.1.0 info: title: Octen API description: >- Octen API provides Broad Search, Web Search, Image Search, Video Search, Extract, Embeddings, VL Embeddings, Answer, and Deep Research services. The Web Search API searches ranked web results with optional filters, highlights, and full content. The Image Search API searches for images from a text query or an image. The Video Search API searches for videos from a text query. The Broad Search API decomposes a query into multiple sub-queries, searches them in parallel, and returns results grouped by sub-query. The Extract API extracts clean content from URLs, with optional query-focused highlights, page classification, and multimedia resources. The Embeddings API converts text into vector representations. The VL Embeddings API converts multimodal inputs into vector representations. The Answer API decomposes queries into multiple sub-queries for comprehensive search and synthesis. The Deep Research API runs a multi-round adaptive research pipeline that produces a structured research plan, executes iterative searches, and streams a final long-form report. version: 1.0.0 servers: - url: https://api.octen.ai security: - bearerAuth: [] - apiKeyAuth: [] paths: /extract: post: summary: Extract description: >- Extracts clean markdown content from URLs. Supports batch processing, query-focused highlights, page classification, and multimedia resources. operationId: extract requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractRequest' examples: basic: summary: Basic Extract value: urls: - https://octen.ai/ - https://docs.octen.ai/api-reference/search intentQuery: summary: Intent-focused Highlights with Query value: urls: - >- https://www.who.int/news-room/fact-sheets/detail/influenza-(seasonal) query: vaccination guidelines withMedia: summary: With Multimedia Resources value: urls: - https://octen.ai/ include_images: true include_videos: true include_audio: true advancedMode: summary: Advanced Mode value: urls: - https://x.com/kzouapt mode: advanced withLinks: summary: With Page Links value: urls: - https://octen.ai/ include_links: scope: prefer_internal max_links: 200 responses: '200': description: Successful extraction response content: application/json: schema: $ref: '#/components/schemas/ExtractResponse' example: code: 0 msg: success request_id: req_abc123def456 data: results: - url: https://octen.ai/ status: success resolved_mode: standard title: Octen | The Search infrastructure for AI full_content: >- # Search infrastructure for AI Real-time indexing | Low latency | High reliability Start Building | View Docs ## Search Beyond Text Beyond text queries: Octen's multimodal search understands images and videos alongside text... highlights: null time_published: null time_last_crawled: '2026-07-03T09:35:43Z' page_structure: primary: Index Page secondary: Home Page category: primary: Computers, Electronics & Technology secondary: Search Engines favicon: https://octen.ai/favicon.ico cover_image: url: >- https://octen.ai/_next/static/media/octen-cover.dc74905e.png images: - url: >- https://octen.ai/_next/static/media/multi-modal-img.ccffddff.png - url: >- https://octen.ai/_next/static/media/showcase-multimodal1.449ae003.png videos: - url: https://octen.ai/static/video/multimodal-video.mp4 links: - url: https://octen.ai/pricing anchor_text: Pricing is_external: false - url: https://docs.octen.ai/overview/welcome anchor_text: View Docs is_external: false - url: https://github.com/Octen-Team/octen-skills anchor_text: GitHub is_external: true - url: https://docs.octen.ai/api-reference/search status: success resolved_mode: standard title: Search - Octen full_content: >- # Search API Octen Search API enables ranked web results with query-focused highlights, time filtering, and multimodal assets... highlights: null time_published: '2024-10-15T00:00:00Z' time_last_crawled: '2026-07-03T09:34:29Z' page_structure: primary: Content Page secondary: Code category: primary: Computers, Electronics & Technology secondary: Search Engines favicon: https://docs.octen.ai/favicon.ico cover_image: url: >- https://octen.ai/_next/static/media/octen-cover.dc74905e.png meta: usage: total_urls: 2 successful_urls: 2 successful_by_mode: standard_urls: 2 advanced_urls: 0 latency: 1832 warning: '' '400': description: >- Invalid params — Returned when a required parameter is missing or invalid. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 msg: Invalid params. Missing parameter urls request_id: req_abc123def456 '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/InsufficientBalance' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' components: schemas: ExtractRequest: type: object required: - urls description: Request body for the Extract API. properties: urls: type: array items: type: string description: >- List of URLs to extract content from. Maximum URLs per request: 20. Maximum length per URL: 2048. Failed URLs are not billed. example: - https://example.com/article-1 - https://example.com/article-2 mode: type: string enum: - standard - advanced - auto default: standard description: >- Processing mode. `standard` prioritizes speed, `advanced` prioritizes success rate on hard-to-reach pages, and `auto` picks one per URL. `advanced` and `auto` can take longer, so raise `timeout` accordingly. query: type: string maxLength: 500 description: >- Intent-focused keywords. When provided, returns query-relevant highlights per URL; otherwise returns the complete page content. max_age_seconds: type: integer default: 86400 minimum: 300 maximum: 31536000 description: >- Maximum age (in seconds) of cached content. URLs whose cached version exceeds this threshold will be re-fetched. Values outside the allowed range are adjusted to the nearest bound. format: type: string enum: - markdown - text default: markdown description: Format of the returned content. timeout: type: integer default: 30 minimum: 1 maximum: 60 description: >- Per-URL extraction timeout in seconds. Values outside the allowed range are adjusted to the nearest bound. include_images: type: boolean default: false description: Whether to return image URLs detected on the page. include_videos: type: boolean default: false description: Whether to return video URLs detected on the page. include_audio: type: boolean default: false description: Whether to return audio URLs detected on the page. include_links: type: object description: Controls whether to return links detected on the page. properties: scope: type: string enum: - prefer_internal - prefer_external default: prefer_internal description: >- Which links to prioritize. `prefer_internal` favors links within the page's registered domain; `prefer_external` favors external links. Prioritized links come first, and links of the same kind keep their order on the page. max_links: type: integer default: 200 minimum: 1 maximum: 1000 description: Maximum number of links to return per URL. ExtractResponse: type: object properties: code: type: integer description: Business status code. 0 indicates success. msg: type: string description: A message describing the result. request_id: type: string description: The unique identifier for this request. data: $ref: '#/components/schemas/ExtractData' meta: $ref: '#/components/schemas/ExtractMeta' ErrorResponse: type: object properties: code: type: integer description: Business status code. Non-zero values indicate an error. msg: type: string description: A message describing the error. request_id: type: string description: Unique identifier for the request. required: - code - msg - request_id ExtractData: type: object description: The main extract response payload. properties: results: type: array description: >- Extraction result for each requested URL. Order matches the input urls array. items: $ref: '#/components/schemas/ExtractResult' ExtractMeta: type: object description: Additional metadata for the extract request. properties: usage: $ref: '#/components/schemas/ExtractUsage' latency: type: integer description: Total request latency in milliseconds. warning: type: string description: >- Warning messages for the request, separated by semicolons. An empty string when there is nothing to report. ExtractResult: type: object description: >- A single extraction result. Batch requests may return 200 OK overall while individual items fail; failed items are marked with `status: "failed"` and an `error_message`, and are not billed. properties: url: type: string description: The requested URL. status: type: string enum: - success - failed description: Extraction status for this URL. resolved_mode: type: string enum: - standard - advanced description: >- The mode this URL is billed at. For `auto`, the mode chosen for this URL. Returned when `status` is `success`. title: type: string nullable: true description: Page title, extracted from HTML `` or `<meta>` tags. full_content: type: string nullable: true description: >- Complete page content in the requested format. Returned when `query` is not provided. highlights: type: array nullable: true items: type: string description: >- Query-relevant snippets, sorted by relevance. Returned when `query` is provided. time_published: type: string format: date-time nullable: true description: Content publication time, ISO 8601 format. time_last_crawled: type: string format: date-time description: Most recent time Octen crawled this URL, ISO 8601 format. page_structure: allOf: - $ref: '#/components/schemas/ExtractPageStructure' description: >- Detected page structure. Returns `null` when the structure cannot be determined. category: allOf: - $ref: '#/components/schemas/ExtractCategory' description: >- Detected content category. Returns `null` when the category cannot be determined. favicon: type: string nullable: true description: The page's favicon URL. Returned by default when available. cover_image: type: object nullable: true description: >- The page cover image. Returned only when `include_images` is `true` and the page has a cover image. properties: url: type: string description: Image URL. images: type: array items: $ref: '#/components/schemas/ExtractMediaResource' description: >- Image resources detected on the page. Returned when `include_images` is `true` and the page contains images. videos: type: array items: $ref: '#/components/schemas/ExtractMediaResource' description: >- Video resources detected on the page. Returned when `include_videos` is `true` and the page contains videos. audio: type: array items: $ref: '#/components/schemas/ExtractMediaResource' description: >- Audio resources detected on the page. Returned when `include_audio` is `true` and the page contains audio. links: type: array items: $ref: '#/components/schemas/ExtractLink' description: >- Links detected on the page, deduplicated. Returned for successful results when `include_links` is set and links are detected on the page. error_message: type: string description: >- Failure reason. Only present when `status` is `failed`. See the Error Codes reference for the complete list of result-level error messages. ExtractUsage: type: object description: Usage and billing breakdown for the extract request. properties: total_urls: type: integer description: Total number of URLs in the request. successful_urls: type: integer description: >- Number of successfully extracted URLs (billed). Failed URLs are not counted. successful_by_mode: type: object description: Breakdown of successful URLs by `resolved_mode`. properties: standard_urls: type: integer description: Successful URLs billed at the standard rate. advanced_urls: type: integer description: Successful URLs billed at the advanced rate. ExtractPageStructure: type: object description: Detected page structure for an extraction result. properties: primary: type: string enum: - Index Page - Content Page - No Main Content description: Top-level page type. secondary: type: string nullable: true description: >- Sub-type within the primary structure. 50+ possible values. `null` when no sub-type applies. ExtractCategory: type: object description: Detected content category for an extraction result. properties: primary: type: string description: Top-level content category. 23 possible values. secondary: type: string nullable: true description: >- Sub-category within the primary category. 160+ possible values. `null` when no sub-category applies. ExtractMediaResource: type: object description: A single multimedia resource detected on the page. properties: url: type: string description: Resource URL. ExtractLink: type: object description: A single link found on the page. properties: url: type: string description: Absolute URL of the link target. anchor_text: type: string description: >- The link's visible text on the page. Empty when the link has no visible text. is_external: type: boolean description: >- Whether the link points to a different registered domain than the page. responses: Unauthorized: description: Invalid API Key — Returned when the API key is missing or invalid. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 msg: Invalid API Key request_id: req_abc123def456 InsufficientBalance: description: >- Insufficient balance in account — Returned when the account balance is insufficient to complete the request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 403 msg: Insufficient balance in account request_id: req_abc123def456 RateLimited: description: >- Exceeding the rate limit — Returned when the request exceeds the configured rate limit. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 429 msg: Exceeding the rate limit request_id: req_abc123def456 InternalError: description: Internal error — Returned when an unexpected server-side error occurs. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 500 msg: Internal error request_id: req_abc123def456 securitySchemes: bearerAuth: type: http scheme: bearer description: >- Bearer token used for request authentication. Alternatively, you can send the API key in the `x-api-key` header. Note: A payment method is required to use the API. apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key used for request authentication. Alternatively, you can send the key as a Bearer token in the `Authorization` header. Note: A payment method is required to use the API. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.