gemini_openapi
Gemini multimodal content generation endpoint (`generateContent`). Supports text + inline image/video inputs and can return both **TEXT** and **IMAGE** modalities. ### Image Generation Models (2025) | Model ID | Notes | |---|---| | `gemini-3.1-flash-image` | High speed; supports `imageSize: "512"` | | `gemini-2.5-flash-image` | Balanced speed & quality | | `gemini-3-pro-image` | Highest quality, advanced reasoning | ### Authentication Pass your API key via the `x-goog-api-key` request header, or use OAuth 2.0 Bearer tokens. ### Base URLs - Production: `https://generativelanguage.googleapis.com/v1` - Preview / beta features: `https://generativelanguage.googleapis.com/v1beta`
Connect this API to an AI agent Browse all specs
What you can do with gemini_openapi via MCP
Every endpoint below becomes a governed tool your AI agent (Claude, ChatGPT, or a customer-facing VX agent) can call — with scoped permissions, sandbox testing, and audit logs.
| Method | Path | Operation | Description |
|---|---|---|---|
| POST | /models/{model}:generateContent |
postModels{model}:generatecontent | Generate content from a multimodal prompt |
Authentication
ApiKeyHeader
API key — sent as the x-goog-api-key header
Google Generative Language API key
How to use this spec
- Create a free VX Agents account (sandbox tools included).
- Open the marketplace and connect “gemini_openapi” to an agent.
- Expose it as an MCP server for Claude/ChatGPT, or chat with it directly.