Gemini 2.0 Flash

Retired Jun 2026

The Gemini 2.0 workhorse and the successor to Gemini 1.5 Flash.

Context: 1M tokens
Max output: 8K
Cutoff: Aug 2024
Released: Feb 2025

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 2.0 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.
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.

Common questions

What is Gemini 2.0 Flash good for?

The Gemini 2.0 workhorse for multimodal work with tools, and the successor to Gemini 1.5 Flash.

When is Gemini 2.0 Flash not a good fit?

Any new work: Google shut it down on June 1, 2026 and names Gemini 3.6 Flash as the replacement. Its short maximum output limited long answers, and there was no file upload.

How does Gemini 2.0 Flash compare with Gemini 2.5 Flash?

Google says Gemini 2.5 Flash builds on Gemini 2.0 Flash and adds thinking that developers can switch on, off or budget. Google calls it a major step up in reasoning that keeps the speed of Gemini 2.0 Flash when thinking is off. Same 1M-token context and text, image, audio and video input. Gemini 2.0 Flash came out 4 months earlier and has an older knowledge cutoff (August 2024 against January 2025) and a smaller max output (8K against 66K tokens).

Can I self-host Gemini 2.0 Flash?

No. Google Cloud does not publish the weights; Gemini 2.0 Flash is available only through hosted APIs.