Gemini 3.7 Flash

Retired Oct 2026

An algorithmic refinement of Gemini 3.6 Flash rather than a new pretraining run, Google's workhorse model for coding and agentic work.

Context: 1M tokens
Max output: 66K
Cutoff: Mar 2026
Released: Aug 2026

Visit Google Cloud Compare vs other LLMs →

GPUhub

Fully Dedicated GPU Servers

No Virtualization. No Shared GPUs

Stable Performance for AI Training & Inference

Full Control for Production Workloads

Learn more

Capabilities

What Gemini 3.7 Flash accepts and can do, as published by Google Cloud.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Video Accepts video as input.
Audio Accepts audio as input.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
Web search Search the web for up-to-date information.
Code execution Write and execute code in a sandboxed environment.
File upload Process uploaded documents, spreadsheets, and other files.

Common questions

What is Gemini 3.7 Flash good for?

Coding and agent work, an algorithmic refinement of Gemini 3.6 Flash rather than a new pretraining run, with the same tools.

When is Gemini 3.7 Flash not a good fit?

Budget-driven, high-volume work: it sits above the Flash-Lite models in Google's price range. Closed weights, so no self-hosting, and output is text only.

How does Gemini 3.7 Flash compare with Gemini 3.8 Flash?

Google calls it the next iteration in the Gemini 3 family, with advances over Gemini 3.7 Flash in software engineering and agentic knowledge work, and keeps the effort levels that trade quality against cost and latency. Same 1M-token context and text, image, audio and video input. Gemini 3.7 Flash came out a month earlier.

Can I self-host Gemini 3.7 Flash?

No. Google Cloud does not publish the weights; Gemini 3.7 Flash is available only through hosted APIs.