> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. # Oxylabs AI Search > Query the major AI answer engines and get back the AI-generated answer text plus its cited source URLs for GEO/AEO visibility monitoring. Run a real query against a major AI answer engine and get back the AI-generated `answer_text` together with the cited source URLs — built for GEO/AEO, so you can monitor how a brand or product is surfaced and cited across AI answers. Pick the engine with `source` (`chatgpt`, `gemini`, `perplexity`, `google_search` for Google AI Overviews, or `google_ai_mode`) and send the parameters that source expects: `prompt` for chatgpt/gemini/perplexity, `query` with `render: "html"` for the Google-type sources, plus `parse: true` and a country-level `geo_location` such as `"United States"`. The request body is passed through unchanged to the upstream engine, and the parsed shape inside each `results[]` entry varies by source — `google_search` returns `ai_overviews[]` with `answer_text` and `references[]{source, url}` (the shape documented here), while chatgpt/gemini return `response_text` + `citations[]`, perplexity returns `top_sources[]`/`sources_results[]`, and google\_ai\_mode returns `content.citations[]{text, urls[]}`. Billed at a flat **\$0.001** per successful result; 400/429/5xx/6xx and upstream 4xx responses are not billed. AI sources (chatgpt/gemini/perplexity) take \~40–60s and Google-type sources \~4–8s, so set your client timeout to at least **90s**. ## OpenAPI ````yaml openapi/oxylabs.json POST /oxylabs/ai-search openapi: 3.0.0 info: title: Oxylabs AI Search API version: 1.0.0 description: >- Oxylabs AI Search for GEO/AEO (Generative / Answer Engine Optimization) exposed through the AIsa gateway. A single passthrough endpoint queries the major AI answer engines — ChatGPT, Gemini, Perplexity, Google AI Overviews, and Google AI Mode — and returns the AI-generated answer text together with the cited source URLs, so you can monitor brand/product visibility and citations across AI answers. Billed at a flat $0.001 per successful result (a Realtime single query returns 1 result = $0.001). All three tiers (normal, VIP, SVIP) are priced identically at $0.001 — cost pass-through with zero profit. Only successful 2xx responses are billed; 400, 429, 5xx, and 6xx responses are not billed, and upstream 4xx responses are not billed. AI sources (chatgpt, gemini, perplexity) typically take ~40–60s; Google-type sources take ~4–8s — set your client timeout to at least 90s. servers: - url: https://api.aisa.one/apis/v1 security: - bearerAuth: [] paths: /oxylabs/ai-search: post: tags: - https://developers.oxylabs.io/scraper-apis/web-scraper-api summary: Query an AI answer engine for GEO/AEO visibility. description: >- Synchronous passthrough to the upstream Oxylabs Realtime endpoint (POST /v1/queries). Pick an AI answer engine with `source` and send the parameters that source expects; the request body is passed through unchanged. The response returns the AI-generated answer text and the cited source URLs, letting you track how a brand or product is surfaced and cited across AI answers. Billed at a flat $0.001 per successful result; 400/429/5xx/6xx and upstream 4xx responses are not billed. AI sources (chatgpt, gemini, perplexity) take ~40–60s and Google-type sources ~4–8s, so use a client timeout of at least 90s. requestBody: required: true content: application/json: schema: type: object description: >- Passthrough body. `source` selects the AI answer engine; the remaining fields are the parameters that source expects (see per-source notes on each property). Additional upstream parameters are passed through as-is. additionalProperties: true properties: source: type: string enum: - chatgpt - gemini - perplexity - google_search - google_ai_mode description: >- The AI answer engine to query. `google_search` returns Google AI Overviews. Each source expects a specific subset of the parameters below. example: google_search prompt: type: string description: >- The natural-language prompt. Used by `chatgpt` (max 4000 chars), `gemini` (max 8000 chars), and `perplexity`. Use `query` instead for the Google-type sources. example: best noise cancelling headphones 2026 query: type: string description: >- The search query. Used by `google_search` and `google_ai_mode`. Use `prompt` instead for chatgpt/gemini/perplexity. example: best noise cancelling headphones 2026 search: type: boolean description: >- For `chatgpt`, set to true to have ChatGPT browse the web before answering. example: true render: type: string enum: - html description: >- For `google_search` and `google_ai_mode`, set to "html" to render the page before parsing. example: html parse: type: boolean description: >- Return structured, parsed results instead of raw output. Recommended for every source. example: true geo_location: type: string description: >- Country-level geo-location for the query, e.g. "United States". example: United States required: - source examples: google_search: summary: Google AI Overviews (google_search) value: source: google_search query: best noise cancelling headphones 2026 parse: true render: html geo_location: United States chatgpt: summary: ChatGPT answer with web browsing value: source: chatgpt prompt: best noise cancelling headphones 2026 search: true parse: true geo_location: United States responses: '200': description: >- Query completed successfully. `results[]` holds one result per query. The parsed shape inside `content` varies by source (see property descriptions); the example below shows the `google_search` (Google AI Overviews) shape. content: application/json: schema: type: object properties: results: type: array description: >- One entry per query. A Realtime single query returns exactly one result, which is the billed unit. items: type: object properties: content: type: object description: >- Parsed answer payload. The structure varies by source: - `google_search` → `content.results.ai_overviews[]` with `answer_text` and `references[]{source, url}` (shown below). - `chatgpt` / `gemini` → `response_text` plus `citations[]`. - `perplexity` → `top_sources[]` / `sources_results[]`. - `google_ai_mode` → `content.citations[]{text, urls[]}`. properties: results: type: object description: Google-type parsed results container. properties: ai_overviews: type: array description: Google AI Overviews returned for the query. items: type: object properties: answer_text: type: array description: >- The AI-generated answer, split into fragments that may carry inline references. items: type: object properties: fragments: type: array items: type: object properties: references: type: array items: {} references: type: array description: Cited sources for this overview. items: type: object properties: source: type: string url: type: string components: securitySchemes: bearerAuth: type: http scheme: bearer ````