> ## 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 (Realtime, passthrough) > 透传 AI 搜索 source: chatgpt/gemini/perplexity/google_search/google_ai_mode;返回 答案+引用+来源URL。Caller 传完整 body(含 source),原样转发 POST /v1/queries。 Currently disabled. ## OpenAPI ````yaml openapi/oxylabs.json POST /apis/v1/oxylabs/ai-search openapi: 3.1.0 info: description: '' title: Oxylabs Web Scraper API (Realtime) version: '1' x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-configured-paths: - /apis/v1/oxylabs/ai-search x-aisa-document: facts_hash: 81836d970af9848169ed18d545bc3ad5dfe0dcf5bf967a3aecf8177c76e7166a generator_version: '2' protocol_version: '1' schema_version: '1' composer_version: '13' response_pending: [] document_hash: sha256:090a5b43ba0156e7faa8df08d765d45718b53e3be609bad0bca7e4f7d47d8eed x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-provider: oxylabs x-aisa-catalogs: oxylabs: title: Oxylabs Web Scraper API (Realtime) description: '' x-aisa-document: facts_hash: 81836d970af9848169ed18d545bc3ad5dfe0dcf5bf967a3aecf8177c76e7166a generator_version: '2' protocol_version: '1' schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote servers: - url: https://api.aisa.one security: - bearerAuth: [] paths: /apis/v1/oxylabs/ai-search: post: tags: - oxylabs summary: Oxylabs AI-search (Realtime, passthrough) description: >- 透传 AI 搜索 source: chatgpt/gemini/perplexity/google_search/google_ai_mode;返回 答案+引用+来源URL。Caller 传完整 body(含 source),原样转发 POST /v1/queries。 operationId: post_oxylabs_ai_search requestBody: required: true content: application/json: schema: type: object description: >- Passthrough body for the Google answer engines. `source` selects the engine; `query`, `render`, `parse`, and `geo_location` are the parameters Google sources expect. Additional upstream parameters are passed through as-is. additionalProperties: true properties: source: type: string enum: - google_search - google_ai_mode description: >- The Google AI answer engine to query. `google_search` returns Google AI Overviews; `google_ai_mode` returns Google AI Mode. For ChatGPT/Gemini/Perplexity use the async endpoint `post_oxylabs_llm` instead. example: google_search query: type: string description: >- The search query. Required for `google_search` and `google_ai_mode`. example: best noise cancelling headphones 2026 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 google_ai_mode: summary: Google AI Mode (google_ai_mode) value: source: google_ai_mode query: best noise cancelling headphones 2026 parse: true render: html 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 the Google source: - `google_search` → `content.results.ai_overviews[]` with `answer_text` and `references[]{source, url}` (shown below). - `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 default: content: application/json: schema: {} description: >- Error response; upstream passthrough responses may use provider formats components: securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.