Gemini models (original) (raw)

Skip to main content

• Gemini API

  • Docs
  • API reference

• Get API key

• Cookbook

• Community

• Get started

• Overview

• Quickstart

• API keys

• Libraries

• Interactions API

• Models

• Gemini

• Gemini 3

• Imagen (image generation)

• Veo (video generation)

• Lyria (music generation)

• Embeddings

• Robotics

• Pricing

• Rate limits

• Core capabilities

• Text

• Video

• Documents

• Structured outputs

• Function calling

• Long context

• Tools and agents

• Overview

• Deep Research

• Google Search

• Google Maps

• Code execution

• URL context

• Computer Use

• File Search

• Live API

• Get started

• Capabilities

• Tool use

• Session management

• Ephemeral tokens

• Guides

• Batch API

• Files API

• Context caching

• OpenAI compatibility

• Media resolution

• Token counting

• Prompt engineering

• Resources

• Migrate to Gen AI SDK

• Release notes

• Deprecations

• API troubleshooting

• Billing info

• Policies

• Terms of service

• Available regions

• Additional usage polices

OUR MOST INTELLIGENT MODEL

Gemini 3 Pro

The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet, delivering richer visuals and deeper interactivity, all built on a foundation of state-of-the-art reasoning.

Expand to learn more

Try in Google AI Studio

Model details

Gemini 3 Pro Preview

Gemini 3 Pro Image Preview

FAST AND INTELLIGENT

Gemini 2.5 Flash

Our best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.

Expand to learn more

Try in Google AI Studio

Model details

Gemini 2.5 Flash

Gemini 2.5 Flash Preview

Gemini 2.5 Flash Image

Gemini 2.5 Flash Live

Gemini 2.5 Flash TTS

ULTRA FAST

Gemini 2.5 Flash-Lite

Our fastest flash model optimized for cost-efficiency and high throughput.

Expand to learn more

Try in Google AI Studio

Model details

Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite Preview

OUR ADVANCED THINKING MODEL

Gemini 2.5 Pro

Our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.

Expand to learn more

Try in Google AI Studio

Model details

Gemini 2.5 Pro

Gemini 2.5 Pro TTS

Previous Gemini models

OUR SECOND GENERATION WORKHORSE MODEL

Gemini 2.0 Flash

Our second generation workhorse model, with a 1 million token context window.

Expand to learn more

Gemini 2.0 Flash delivers next-gen features and improved capabilities, including superior speed, native tool use, and a 1M token context window.

Try in Google AI Studio

Model details

Gemini 2.0 Flash

Gemini 2.0 Flash Image

OUR SECOND GENERATION FAST MODEL

Gemini 2.0 Flash-Lite

Our second generation small workhorse model, with a 1 million token context window.

Expand to learn more

A Gemini 2.0 Flash model optimized for cost efficiency and low latency.

Try in Google AI Studio

Model details

Model version name patterns

Gemini models are available in either stable, preview, latest, or_experimental_ versions.

Stable

Points to a specific stable model. Stable models usually don't change. Most production apps should use a specific stable model.

For example: gemini-2.5-flash.

Preview

Points to a preview model which may be used for production. Preview models will typically have billing enabled, might come with more restrictive rate limits and will be deprecated with at least 2 weeks notice.

For example: gemini-2.5-flash-preview-09-2025.

Latest

Points to the latest release for a specific model variation. This can be a stable, preview or experimental release. This alias will get hot-swapped with every new release of a specific model variation. A 2-week notice will be provided through email before the version behind latest is changed.

For example: gemini-flash-latest.

Experimental

Points to an experimental model which will typically be not be suitable for production use and come with more restrictive rate limits. We release experimental models to gather feedback and get our latest updates into the hands of developers quickly.

Experimental models are not stable and availability of model endpoints is subject to change.

Model deprecations

For information about model deprecations, visit the Gemini deprecations page.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-12-12 UTC.