Gemini 2.0 Flash-Lite

Retired Jun 2026

The lightest Gemini 2.0 model, built for high-throughput text generation.

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

Visit Google Cloud Compare vs other LLMs →

Vast.ai

Per-second billing. Pay only for what you use.

50+ GPU models from RTX 3060 to B200, from $0.04/hr

No minimums, no long-term contracts.

SOC2 certified · PyTorch, CUDA & TensorFlow templates ready

Learn more

Capabilities

What Gemini 2.0 Flash-Lite 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.

Common questions

What is Gemini 2.0 Flash-Lite good for?

High-throughput text generation from multimodal input, at the light end of the Gemini 2.0 lineup.

When is Gemini 2.0 Flash-Lite not a good fit?

Any new work: Google retired it in June 2026. It had no web search or code execution, and its short maximum output limited long answers.

How does Gemini 2.0 Flash-Lite compare with Gemini 2.5 Flash-Lite?

Google says Gemini 2.5 Flash-Lite has higher quality than Gemini 2.0 Flash-Lite across coding, math, science, reasoning and multimodal tasks, with lower latency, and adds optional thinking plus web search and code execution. Same 1M-token context and text, image, audio and video input. Gemini 2.0 Flash-Lite came out 5 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-Lite?

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