Gemini 3.7 Flash - GENGEN API

A fast general-purpose Gemini model with multimodal input and configurable reasoning.

Model ID

gemini-3.7-flash

Pass this exact public ID in the top-level model field. Do not substitute an upstream provider alias.

Chat completions
Function calling
Code execution
Computer use
Responses API
Video understanding
SSE streaming
Multimodal understanding
Reasoning See Function calling and Gemini tools for tool declarations, result submission, and provider-specific capabilities.

Property	Value
Provider	`google-agent-platform`
Modality	`reasoning`
Processing	`Synchronous response`
Endpoint	`/api/gengen/v1/chat/completions`
Context window	`1M tokens`
Streaming	`Supported (Server-Sent Events)`
Max input tokens	`1,048,576`
Max output tokens	`65,536`

Availability and final customer prices can change. Check the Dashboard model catalog before production use.

See the API reference overview for authentication, request conventions, and response schemas.