Google

Gemini Embedding is a text embedding model for semantic search and vector-based tasks. Developed by Google AI, this model is optimized for its specific use case category.

Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video...

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to Gemini Flash 1.5, while maintaining quality on par with larger models like Gemini Pro 1.5. It introduces notable e...

Code completion model.

A specialized research-focused model designed for deep analysis, literature review, and comprehensive research tasks. Optimized for synthesizing information from multiple sources and providing thoroug...

Lightweight embedding model.

Gemini 1.0 with vision (deprecated).

Previous generation pro model.

Gemini 2 Flash with extended reasoning capabilities.

A cost-effective multimodal model optimized for general-purpose tasks requiring balanced performance. Gemini 2.0 Flash delivers strong capabilities across text, image, and code understanding while mai...

An experimental version of Gemini 2.0 Flash with image generation capabilities. Combines text understanding with the ability to generate images based on prompts.

The stable version 001 release of Gemini 2.0 Flash, providing a cost-effective multimodal model for general-purpose tasks. This versioned release ensures consistent behavior and reproducible results f...

An experimental preview of Gemini 2.0 Flash featuring the latest capabilities and improvements. This version provides early access to new features while maintaining the fast inference speeds character...

A preview version of Gemini 2.0 Flash optimized for image generation tasks. Designed for creating visual content from text descriptions.

An experimental version of Gemini 2.0 Flash with enhanced reasoning capabilities. This model features a "thinking" mode that allows it to work through complex problems step-by-step before providing fi...

A dated experimental version of Gemini 2.0 Flash with thinking capabilities from January 21, 2025. Features improved reasoning capabilities over earlier thinking model versions.

A dated experimental version of Gemini 2.0 Flash with thinking capabilities from December 19, 2024. Provides enhanced reasoning through explicit step-by-step problem solving.

Streamlined and ultra-efficient model designed for simple, high-frequency tasks. Gemini 2.0 Flash-Lite prioritizes speed and affordability while maintaining essential multimodal capabilities.

A preview version of Gemini 2.0 Flash-Lite, providing early access to streamlined capabilities optimized for high-frequency, simple tasks. This model supports multimodal capabilities including vision ...

A dated preview version of Gemini 2.0 Flash-Lite from February 5, 2025. Provides a fixed checkpoint for reproducible results. This model supports multimodal capabilities including vision and image und...

Professional-grade Gemini 2.0 model.

An experimental version of Gemini 2.0 Pro offering higher capability than Flash variants. Designed for complex tasks requiring advanced reasoning, coding, and multimodal understanding.

A dated experimental version of Gemini 2.0 Pro from February 5, 2025. Provides high-capability performance for complex tasks with a specific model checkpoint.

Vision-optimized Gemini 2.0 Pro.

A specialized preview model designed for computer use and automation tasks. Enables AI-driven interaction with computer interfaces, including clicking, typing, and navigating applications.

Lightning-fast and highly capable model that delivers a balance of intelligence and latency. Gemini 2.5 Flash offers controllable thinking budgets for versatile applications, making it ideal for a wid...

A specialized image-focused variant of Gemini 2.5 Flash, codenamed Nano Banana. Optimized for image understanding and generation tasks with fast inference.

A preview version of the image-focused Gemini 2.5 Flash variant, codenamed Nano Banana. Provides early access to enhanced image capabilities.

Preview of Gemini 2.5 Flash.

A dated preview of Gemini 2.5 Flash from May 20, 2025. Provides a fixed model checkpoint for reproducible experiments and applications.

A September 2025 preview of Gemini 2.5 Flash with the latest capabilities and improvements before stable release. This model supports multimodal capabilities including vision and image understanding.

A specialized preview of Gemini 2.5 Flash with text-to-speech capabilities. Combines fast inference with high-quality voice synthesis for real-time audio applications.

Built for massive scale, Gemini 2.5 Flash-Lite balances cost and performance for high-throughput tasks. Optimized for efficiency without sacrificing multimodal capabilities.

A dated preview version of Gemini 2.5 Flash-Lite from June 17, 2025. Optimized for efficiency and high-throughput tasks with a fixed checkpoint.

A September 2025 preview of Gemini 2.5 Flash-Lite, optimized for efficiency and cost-effectiveness in high-throughput applications. This model supports multimodal capabilities including vision and ima...

Google's high-capability model for complex reasoning and coding. Features adaptive thinking and a 1 million token context window, designed for complex agentic and multimodal challenges. Gemini 2.5 Pro...

A dated preview version of Gemini 2.5 Pro from March 25, 2025. Provides access to advanced capabilities with a fixed model checkpoint for reproducibility.

Gemini 2.5 Pro is Google's latest and most capable model, featuring a massive 1 million token context window. This preview version (06-05) represents the cutting edge of Google's multimodal AI capabil...

A specialized preview of Gemini 2.5 Pro with text-to-speech capabilities. Designed for applications requiring high-quality voice synthesis alongside advanced language understanding.

Fast Gemini 3 for speed and efficiency.

Lightweight Gemini 3 optimized for mobile devices.

High-end model for demanding applications.

Latest flagship Gemini model with advanced reasoning and multimodal capabilities.

Balanced mid-tier Gemini model.

Audio analysis model.

Advanced code analysis and generation model.

Specialized model for document processing and extraction.

An experimental Gemini model from December 6, 2024. Provides early access to new capabilities and improvements in development. This model supports multimodal capabilities including vision and image un...

Gemini Flash Latest with optimized speed for rapid response generation. This model supports multimodal capabilities including vision and image understanding.

The latest stable version of Gemini Flash-Lite, automatically updated to the most recent stable release. Optimized for efficiency and high-throughput tasks.

Image generation from text.

Real-time streaming multimodal model.

Smallest Gemini model.

The latest stable version of Gemini Pro, automatically updated to the most recent stable release. Provides high-capability performance for complex tasks.

Experimental advanced reasoning engine for complex tasks.

A specialized model for robotics and embodied reasoning (ER) applications. Designed to understand and reason about physical environments, robot actions, and spatial relationships.

Latest text embedding model.

Video analysis and understanding.

Previous Gemma generation 7B model.

Previous generation 27B model.

Compact 12B instruction-tuned model.

A lightweight, instruction-tuned version of Gemma 3 with 1 billion parameters. Designed for edge deployment and resource-constrained environments while maintaining good instruction-following capabilit...

Open-source 27B instruction-tuned model.

Ultra-lightweight 4B model.

Extended context Gemma 3 27B.

Extended context version of Gemma 3 27B supporting up to 1M token context.

An efficient variant of Gemma 3 with approximately 2B equivalent parameters, optimized for edge deployment and mobile applications. Part of the Gemma 3n efficient model series.

An efficient variant of Gemma 3 with approximately 4B equivalent parameters, balancing capability and efficiency for edge and mobile deployment.

An experimental model designed specifically for educational applications. LearnLM is optimized for tutoring, explanation generation, and adaptive learning interactions. This model supports multimodal ...

Advanced multimodal model.

A high-capability image-focused model codenamed Nano Banana Pro. Designed for advanced image understanding and generation with professional-grade quality. This model supports multimodal capabilities i...

A high-capability image-focused model codenamed Nano Banana Pro. Part of the Gemini 3 Pro family with specialized capabilities for advanced image understanding and generation.

Legacy PaLM chat model (deprecated).

Legacy PaLM text model (deprecated).