Monitor Gemini Responses
Gemini
Extract Google Gemini
Extract structured data from Google Gemini — generated answer text and cited sources for any prompt, with Markdown and HTML export formats
POST
Monitor Gemini Responses
Overview
The Google Gemini endpoint extracts structured data from Google’s Gemini AI. It captures the generated text response, citations/sources, and supports multiple export formats including Markdown and HTML.Web search behaviorThis endpoint uses Gemini’s default interface, which may automatically perform web searches and provide source citations based on its own determination of whether the query requires current information.
Request parameters
Uses common parameters. Endpoint-specific options:include.rawResponse(boolean): Include raw streaming response events. Defaults tofalse
Response objects
The response includes the following sections. See each subpage for the full schema.Response schema
Includes common response fields plus:Example usage
Common questions
How does cloro retrieve Gemini responses?
cloro does not call the Gemini API. Each request runs through a real browser session against Gemini’s web interface, routed through a proxy in the country you specify. Theresult.text, result.sources, and other fields are extracted from that page; the raw streamed events are available via include.rawResponse: true. See How does cloro retrieve data from AI providers? for the full explanation and implications (model routing, auth walls, geo behaviour).Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Request parameters for monitoring Gemini responses
The prompt to send to Gemini
Required string length:
1 - 10000Example:
"Explain quantum computing"
Country/region code for localized response
Example:
"US"
Optional flags for including additional response formats
Example:
State code for sub-country geo-targeting (e.g., "CA"). Only valid with country "US".
Required string length:
2Pattern:
^[A-Z]{2}$Example:
"CA"