> ## Documentation Index > Fetch the complete documentation index at: https://docs.andiai.com/llms.txt > Use this file to discover all available pages before exploring further. # Fetch a web page > Fetches a single web page and returns clean extracted content (title, article text, metadata) as JSON, or LLM-ready markdown with format=context. The companion to /api/v1/search: search, pick a result, fetch it in full. ## OpenAPI ````yaml /api-reference/openapi.json get /api/v1/fetch openapi: 3.1.0 info: title: Andi AI Search API version: 1.7.0 description: >- Web search and page-fetch API for people and AI agents. `GET`/`POST /api/v1/search` returns structured results with query operators, domain and date filtering, and multiple output formats. `GET /api/v1/fetch` retrieves and extracts a single page. `GET /api/v1/news/:topic` returns a curated, ranked news feed for one of 23 fixed topics — no query required. Search and fetch support `format=context`, which returns markdown suited to language models; the news endpoint returns JSON only. By default (`searchMode=auto`) the API sets the search effort per query — compute, models, and depth — automatically; the fixed modes (`low-cost`, `fast`, `balanced`, `deep`, `exhaustive`) pin an effort level when you want the same behavior on every call. Requests are billed on outcome-based pricing, reported per call in `metrics.cost_dollars`. servers: - url: https://api.andiai.com description: Production security: - apiKey: [] paths: /api/v1/fetch: get: summary: Fetch a web page description: >- Fetches a single web page and returns clean extracted content (title, article text, metadata) as JSON, or LLM-ready markdown with format=context. The companion to /api/v1/search: search, pick a result, fetch it in full. operationId: fetchPage parameters: - name: url in: query required: true description: Full http(s) URL of the page to fetch. schema: type: string format: uri - name: format in: query required: false description: >- Response format: json (structured, default) or context (LLM-ready markdown). schema: type: string enum: - json - context default: json - name: effort in: query required: false description: >- How thoroughly to retrieve the page: `low` favors speed, `max` spends the most time extracting content — useful for pages that are slow to load or render content client-side. Omit for the server's adaptive default. Invalid values return a `400` listing the valid tiers. Fetch failures (`422`, `503`) are never billed, regardless of `effort`. schema: type: string enum: - low - medium - high - max - name: maxContentLength in: query required: false description: Maximum content characters to return (default 200000). schema: type: integer minimum: 1 - name: query in: query required: false description: >- Optional query string to scope extraction to. When set, the response includes `query_extracts`, `query_snippet`, and `query_hash` fields scoped to this query. schema: type: string responses: '200': description: Extracted page content content: application/json: schema: type: object properties: url: type: string title: type: string description: type: string content: type: string description: Clean extracted text content markdown: type: string description: Clean extracted content as markdown, when available. extracts: type: array items: type: string description: Key passage extracts from the page, when available. snippet: type: string description: Short excerpt from the page. author: type: string date: type: string site_name: type: string image: type: string lang: type: string word_count: type: integer truncated: type: boolean query_extracts: type: array items: type: string description: >- Text extracts from the page most relevant to `query`. Only present when `query` is set. query_snippet: type: string description: >- Short excerpt from the page most relevant to `query`. Only present when `query` is set. query_hash: type: string description: >- Hash identifying the `query` used to scope this response. Only present when `query` is set. partial: type: boolean description: >- Whether this is a partial response returned before the page finished retrieving. Only present when true. retry_after_seconds: type: integer description: >- Seconds to wait before retrying for the full content. Only present on partial responses. metrics: type: object properties: duration_ms: type: integer cost_dollars: type: number description: >- Actual cost of this fetch in USD (post-discount). Failed fetches are not billed. text/markdown: schema: type: string '400': description: Missing or invalid url parameter content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Missing or invalid API key content: application/json: schema: $ref: '#/components/schemas/Error' '402': description: Credit balance exhausted content: application/json: schema: $ref: '#/components/schemas/Error' '422': description: >- The page was reached but its content could not be extracted. Not retriable. Not billed. content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' '503': description: >- The page is still being retrieved, or a transient failure occurred. Retriable — retry after the number of seconds in the `Retry-After` header. Not billed. headers: Retry-After: description: Seconds to wait before retrying. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Content warming message: >- The page is still being retrieved. Retry in 5s for the full content. retry_after_seconds: 5 url: https://example.com/article components: schemas: Error: type: object properties: error: type: string description: Error type or message. message: type: string description: Detailed error description. required: - error - message securitySchemes: apiKey: type: apiKey in: header name: x-api-key description: API key from the [API Console](https://console.andiai.com). ````