Google·Gemini 3 family

Gemini 3.7 Flash

proprietaryReleased Aug 2026

Google DeepMind's most intelligent workhorse Flash model yet, released three weeks after Gemini 3.6 Flash with substantial gains in coding, agentic tool use, and knowledge work. Delivers stronger first-pass code accuracy, more functional web app generation, and improved multi-step planning, while natively multimodal across text, image, audio, and video with a 1M-token context window and configurable thinking levels.

Capabilities

ChatText completionFunction callingVisionAudioCode generationReasoning

Modalities

textimageaudiovideocode

Context window

1.0M tokens

Providers

Available

Available from 2 providers

Cheapest

Google AI Studio

$4.50/1M tokens

Google AI Studio, Google Cloud Vertex AI

Providers (2)

Sorted by total cost (input + output per 1M tokens). Select a row to view provider details.

Provider	Pricing (per 1M)	Rate limits	Regions	Health	Latency
Google AI Studio	In: $0.75Out: $3.75	15 RPM / 1.0M TPM	us-east-1eu-west-1global	Healthy	0ms
Google Cloud Vertex AI	In: $0.75Out: $3.75	1K RPM / 8.0M TPM	us-east-1eu-west-1global	Healthy	0ms

Quick start

Use this model via Google AI Studio with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.google-ai-studio.com/v1",
  apiKey: process.env.GOOGLE_AI_STUDIO_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gemini-3.7-flash",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

console.log(response.choices[0].message.content);

Using Google AI Studio API · OpenAI-compatible SDK