> ## Documentation Index > Fetch the complete documentation index at: https://docs.llmlayer.ai/llms.txt > Use this file to discover all available pages before exploring further. # Extract API - Multi-mode page extraction > Extract from a single web page in one call. Combine any modes: structured JSON ('json', $0.005), a markdown summary ('summary', $0.005), an answer to a question ('qa', $0.005), all page links ('links', $0.001), and a brand profile with logos/colors/socials ('brand', $0.002). Pricing is summed per selected mode; advanced proxy adds $0.004 once when a scrape runs. If the request fails before any AI cost is incurred (page fetch failure, empty content, brand fetch failure), you are fully refunded. ## OpenAPI ````yaml post /api/v2/extract openapi: 3.0.0 info: title: LLMLayer API version: 2.0.0 description: >- The Web API for AI Agents - Search, scrape, extract content, crawl websites, and generate AI-powered answers with multiple LLMs servers: - url: https://api.llmlayer.dev security: [] tags: - name: Answer API description: >- Web-enhanced AI responses combining search with multiple LLM models. Supports streaming, custom prompts, and structured JSON output. - name: Web Search description: >- Direct web search across multiple content types (general, news, shopping, videos, images, scholar) without AI processing. - name: Content Extraction description: >- Extract content from websites, PDFs, and YouTube videos in multiple formats. - name: Web Crawling description: >- Map websites and crawl multiple pages with depth control. Supports streaming with markdown output. paths: /api/v2/extract: post: tags: - Content Extraction summary: Extract API - Multi-mode page extraction description: >- Extract from a single web page in one call. Combine any modes: structured JSON ('json', $0.005), a markdown summary ('summary', $0.005), an answer to a question ('qa', $0.005), all page links ('links', $0.001), and a brand profile with logos/colors/socials ('brand', $0.002). Pricing is summed per selected mode; advanced proxy adds $0.004 once when a scrape runs. If the request fails before any AI cost is incurred (page fetch failure, empty content, brand fetch failure), you are fully refunded. operationId: extract requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractRequest' responses: '200': description: >- Extraction results. All result fields (structured_data, summary, answer, links, brand) are always present; modes you did not request are null. content: application/json: schema: $ref: '#/components/schemas/ExtractResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '422': description: >- The page returned no extractable content (fully refunded), or the JSON output was truncated before completion. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': $ref: '#/components/responses/RateLimitError' '500': $ref: '#/components/responses/InternalServerError' security: - BearerAuth: [] components: schemas: ExtractRequest: type: object required: - url properties: url: type: string description: >- The page URL to extract from. Must be http(s). PDF URLs are not supported — use /get_pdf_content instead. example: https://www.ycombinator.com/blog modes: type: array items: type: string enum: - json - summary - qa - links - brand default: - json description: >- Extraction modes to run in one call. Any combination; duplicates are ignored. Pricing is summed per mode: json/summary/qa $0.005 each, links $0.001, brand $0.002. example: - json - summary json_schema: description: >- Required when modes includes 'json'. Accepts a formal JSON schema, an example object (e.g. {"title": "string", "price": "number"}), or a plain-text description of the fields you want. oneOf: - type: string - type: object query: type: string description: >- The question to answer from the page — required when modes includes 'qa'. instructions: type: string description: >- Optional extra guidance applied to all AI modes (json, summary, qa). E.g. 'dates in DD/MM/YYYY format'. response_language: type: string default: auto description: >- Output language for summary/qa ('auto' matches the user/page language). E.g. 'en', 'fr', 'es'. advanced_proxy: type: boolean default: false description: >- Use advanced proxy for sites with bot protection. Adds $0.004 once per request, only when a scrape runs (brand-only requests never scrape). main_content_only: type: boolean description: >- Omit this field to let the API pick the best default per selection: links-only requests scrape the full page (nav/footer links matter), AI modes use main content only. ExtractResponse: type: object description: >- All five result fields are always present; modes you did not request are null. The json mode result is returned as structured_data. properties: url: type: string description: Final URL after redirects. title: type: string nullable: true description: Page title. metadata: type: object nullable: true description: >- Page metadata (description, OpenGraph fields, language, ...) as found by the scraper. structured_data: type: object nullable: true description: Structured data matching your schema (when 'json' in modes). summary: type: string nullable: true description: Markdown summary of the page (when 'summary' in modes). answer: type: string nullable: true description: Markdown answer to your question (when 'qa' in modes). links: type: array nullable: true items: $ref: '#/components/schemas/ExtractLink' description: >- All links found on the page, deduplicated, max 500 (when 'links' in modes). brand: type: object nullable: true description: >- Brand profile: domain, title, description, colors, logos, backdrops, socials, industries, key links and pages (when 'brand' in modes). cost: type: number description: >- Total cost in USD — sum of the selected modes (+$0.004 advanced proxy when a scrape runs). example: 0.01 response_time: type: string description: Total processing time in seconds. example: '3.42' statusCode: type: integer example: 200 ErrorResponse: type: object required: - detail properties: detail: type: object required: - error_type - error_code - message properties: error_type: type: string enum: - validation_error - authentication_error - provider_error - rate_limit - internal_error - scraping_error - search_error - map_error description: Category of error error_code: type: string description: Specific error code for programmatic handling example: missing_query message: type: string description: Human-readable error message details: type: object additionalProperties: true nullable: true description: Additional error context and debugging information ExtractLink: type: object properties: url: type: string description: Absolute URL of the link. text: type: string description: Anchor text of the link (may be empty). internal: type: boolean description: True when the link points to the same site (including subdomains). responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: missing_query: value: detail: error_type: validation_error error_code: missing_query message: Query parameter cannot be empty missing_json_schema: value: detail: error_type: validation_error error_code: missing_json_schema message: JSON schema is required for JSON response type invalid_max_pages: value: detail: error_type: validation_error error_code: invalid_max_pages message: max_pages must be between 1 and 100 Unauthorized: description: Authentication error - missing or invalid API key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: error_type: authentication_error error_code: missing_llmlayer_api_key message: 'Provide LLMLayer API key via ''Authorization: Bearer ''' RateLimitError: description: Rate limit exceeded or insufficient credits content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: provider_rate_limit: value: detail: error_type: provider_error error_code: openai_rate_limit message: Rate limit exceeded for openai. Please try again later details: provider: openai InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unexpected_error: value: detail: error_type: internal_error error_code: unexpected_error message: An unexpected error occurred. Please try again later scraping_error: value: detail: error_type: scraping_error error_code: url_scrape_failed message: Failed to scrape content from the provided URL details: url: https://www.ycombinator.com error: Connection timeout securitySchemes: BearerAuth: type: http scheme: bearer description: >- Bearer token authentication using your LLMLayer API key. Include in Authorization header as: Bearer YOUR_LLMLAYER_API_KEY ````