# Track Gemini answers `POST https://api.answerline.dev/v1/monitor/gemini` Get structured output from Google Gemini for any prompt: the generated answer and the sources it cites, exportable as Markdown From $1.00 per 1,000 requests. Failed requests are free. Also runs as an async task of type `GEMINI`. ## Body - `prompt` (string, required): Prompt submitted to Gemini, up to 2,000 characters. A longer prompt is refused with a 400 that states its length. - `country` (string, required): Code of the country or region used to localize the response - `include` (object): Flags that add extra output formats to the response (optional) - `include.markdown` (boolean): Add a markdown version of the response to the result - `include.html` (boolean): A copy of the Gemini page as it was when the answer was captured, stored on our file host and linked in `html`, to check the answer against. It is free. - `include.rawResponse` (boolean): Return the answer as normalized stream events. For the engine's answer as received, use `include.rawWire`. - `include.rawWire` (boolean): Return the engine's own response as received in result.rawWire: the answer stream, the rendered results pages or the RSS feed, without Gemini's detected location or ChatGPT's session tokens; null where it was not captured. Free. See https://answerline.dev/docs/output-formats#raw-wire - `include.screenshot` (boolean): Return a full-page PNG screenshot of the engine's page as it showed the finished answer, in result.screenshot: a link, or one link per results page on Google Search. On ChatGPT, Gemini, AI Mode, Google Search, Perplexity and Grok; other engines refuse it with a 400. Absent when the answer was read without a rendered page or its page was not available. Free. See https://answerline.dev/docs/output-formats#screenshots - `state` (string): US state code (e.g. "CA", "DC" included). Sent without a country, the request asks for the US; sent with any country other than "US", it is refused with a 400, uncharged. ChatGPT and Gemini answer as a person in that state sees it; every other engine accepts it and answers for the whole US, at the price of a request without it. provenance.requestedState reports the state asked. See https://answerline.dev/docs/coverage#states - `answerDepth` ("any" | "full" | "quick"): Accepted so existing requests stay valid; it does not change the answer or the price. Every engine writes one depth: Perplexity answers every request with its Quick Search answer, and provenance.answerDepth says quick. See https://answerline.dev/docs/engine-features/#answer-depth ## Returns - `result.text` (string): Text of Gemini's reply - `result.markdown` (string): Gemini's reply as Markdown - `result.model` (string): The model Gemini names as the one that answered; null when the answer does not name it. - `result.videos` (object[]): Video cards Gemini shows in its answer, in answer order - `result.searchQueries` (string[]): Searches Gemini ran for the answer, when it shows them - `result.html` (string): Present when include.html is true: the link to the stored copy of the Gemini page. - `result.sources` (object[]): Sources that Gemini cited - `result.citationPills` (object[]): Citation pills that appear inline in the Gemini answer. Every element pairs one chip with one source: a chip backed by N sources (Gemini's equivalent of `+N`, or a section-summary chip) yields N elements with the same `citationPillId`, each holding that source's own `label`, `url` and `domain`. Grouping by `citationPillId` rebuilds the pills. `label` is always sent; it may be an empty string if the rail gives that source no title. Empty when the answer has no pills. - `result.places` (object[]): Place cards included in lodging and local answers - `result.rawResponse` (object[]): The answer as normalized stream events (present when include.rawResponse is true). For the engine's answer as received, use include.rawWire. - `result.shoppingCards` (object[]): Product cards Gemini shows beside a shopping-related answer, in display order. Absent when the answer has none. - `result.entities` (object[]): The brands and products Gemini's answer shows as entity cards, in answer order. Absent when the answer has none. - `result.screenshot` (string): Present when include.screenshot is true and the answer came from a rendered page: the link to the PNG screenshot of the Gemini page once the answer finished. - `result.links` (object[]): The links in the answer's text, in the order a reader meets them: one entry per web (http or https) link the answer shows, images and code aside, with the words it shows (text), where it goes (url), its domain and its 1-based position. Sources cited by pills are in citationPills; links to the same page appear in both when the answer does both. Empty when the text links nowhere. ## Responses - 200: Gemini monitoring result (success) - 400: Bad Request - the request failed validation - 401: Unauthorized - authentication failed - 403: Forbidden - INSUFFICIENT_CREDITS: the balance does not cover this request - 404: Not Found - No such route, or the engine is paused - 409: Conflict - the resource is in a conflicting state - 429: Too Many Requests - the call could not start now (`CONCURRENT_LIMIT_EXCEEDED`), or the service dropped the request because it was overloaded (`SERVICE_OVERLOADED`); that case returns `Retry-After` without any limit headers. `RATE_LIMIT_EXCEEDED`, with `Retry-After`, is sent only when one address presented too many unknown keys - 499: Client Closed Request - the client cancelled the request - 500: Internal Server Error - 502: Bad Gateway - the engine failed ## Request curl: ```bash curl -X POST "https://api.answerline.dev/v1/monitor/gemini" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt":"iPhone 17 or Galaxy S26?","country":"US"}' ``` TypeScript: ```ts import { Client } from "@answerline/sdk"; const client = new Client({ apiKey: process.env.API_KEY! }); const answer = await client.monitor.gemini({ "prompt": "iPhone 17 or Galaxy S26?", "country": "US" }); ``` Python: ```python import os from answerline import Client with Client(os.environ["API_KEY"]) as client: answer = client.monitor.gemini( prompt="iPhone 17 or Galaxy S26?", country="US", ) ``` ## Example responses 200: ```json { "success": true, "result": { "text": "Quantum computing applies quantum mechanics to...", "markdown": "**Machine learning** is a branch of artificial intelligence...", "model": "3.5 Flash-Lite", "videos": [ { "title": "I Tested Every Running Shoe Under $150 So You Don't Overpay", "link": "https://www.youtube.com/watch?v=A6l77V2gkGE", "platform": "YouTube", "channel": "RunnersVibe · Running Shoe Reviews", "duration": "5:30", "thumbnail": "https://i.ytimg.com/vi/A6l77V2gkGE/maxresdefault.jpg" } ], "searchQueries": [ "best running shoes under $150", "running shoe reviews 2026" ], "html": "https://files.answerline.dev/html/c45a5081-808d-4ed3-9c86-e4baf16c8ab8/1/page-1.html", "sources": [ { "position": 1, "label": "Wikipedia - Machine Learning", "url": "https://en.wikipedia.org/wiki/Quantum_computing", "description": "Quantum computing uses qubits to process information..." } ], "citationPills": [ { "label": "Photosynthesis — Wikipedia", "citationPillId": 1, "url": "https://en.wikipedia.org/wiki/Quantum_computing", "domain": "en.wikipedia.org", "description": "Quantum computing uses qubits to process information...", "position": 1 }, { "label": "IBM Quantum", "citationPillId": 1, "url": "https://www.ibm.com/quantum", "domain": "ibm.com", "position": 3 } ], "places": [ { "index": 0, "title": "Sofitel Sydney Darling Harbour", "link": "https://www.google.com/travel/search?q=Pullman+Quay+Grand+Sydney+Harbour", "thumbnail": "https://lh3.googleusercontent.com/gps-cs-s/example", "rating": 4.4, "reviews": 1307, "type": "5-star hotel", "description": "Boutique riverside hotel with elegant rooms, a rooftop terrace, a spa & an all-day café.", "price": "$565" } ], "rawResponse": [ null ], "shoppingCards": [ { "position": 1, "title": "Brooks Ghost 16", "productLink": "https://google.com/search?q=Brooks+Ghost+16&prds=productid%3A123", "productId": "16919532047675658099", "price": { "value": 329.99, "currency": "USD", "raw": "$329.99" }, "oldPrice": { "value": 329.99, "currency": "USD", "raw": "$329.99" }, "store": "Runner's Depot", "storeLink": "string", "storeCount": 4, "shipping": "string", "deliveryTime": "string", "rating": 4.4, "reviews": 1261, "brand": "Brooks", "description": "string", "thumbnail": "string", "images": [ "string" ], "catalogId": "14325977521193745857", "gpcId": "11523404812175301769" } ], "entities": [ { "type": "product", "name": "Nike Court Vision Low" }, { "type": "product", "name": "Nike Air Force 1 '07" }, { "type": "product", "name": "New Balance 550 Leather" } ], "screenshot": "https://files.answerline.dev/html/c45a5081-808d-4ed3-9c86-e4baf16c8ab8/1/3f9a1c2e8b7d4a6f9e0c1b2a3d4e5f60/page-1.png", "links": [ { "position": 1, "text": "Nike Pegasus 42", "url": "https://www.nike.com/t/pegasus-42-mens-road-running-shoes", "domain": "nike.com" } ] } } ``` 400: ```json { "success": false, "error": "Request validation failed", "details": [ { "field": "prompt", "message": "Prompt must not be empty" } ] } ``` 502: ```json { "error": { "code": "EXTERNAL_SERVICE_ERROR", "message": "External service error: the service failed", "details": { "service": "CHATGPT" }, "timestamp": "2025-01-15T12:00:00.000Z" } } ```