Provider model hub
Google Gemini
AI models.
Browse every Google Gemini model in the public Swarm catalog, with dedicated pages for capabilities, context, thinking controls, and catalog identity.
- Models
- 57
- Provider ID
- Catalog total
- 791
- Snapshot
- 2026-10-07
All Google Gemini models
57 crawlable model pages
Antigravity Agent Preview
Preview release of Antigravity Agent (05-2026)
- Context
- 131.1K tokens
- Thinking
- Not supported
Antigravity Agent Preview (09-2026)
A general-purpose managed agent that autonomously plans, reasons, runs code, manages files, and browses the web inside a secure, isolated Linux sandbox.
- Context
- 1.05M tokens
- Thinking
- Not supported
Model that performs Attributed Question Answering.
Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.
- Context
- 7.2K tokens
- Thinking
- Not supported
Deep Research Max Preview (Apr-21-2026)
Preview release (April 21st, 2026) of Deep Research Max
- Context
- 131.1K tokens
- Thinking
- Not supported
Deep Research Preview (Apr-21-2026)
Preview release (April 21th, 2026) of Deep Research
- Context
- 131.1K tokens
- Thinking
- Not supported
Deep Research Pro Preview (Dec-12-2025)
Preview release (December 12th, 2025) of Deep Research Pro
- Context
- 131.1K tokens
- Thinking
- Not supported
Gemini 2.5 Computer Use Preview 10-2025
Gemini 2.5 Computer Use Preview 10-2025
- Context
- 131.1K tokens
- Thinking
- Not supported
Gemini 2.5 Flash
Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.
- Context
- 1.05M tokens
- Thinking
- off
Nano Banana
Gemini 2.5 Flash Preview Image
- Context
- 32.8K tokens
- Thinking
- Not supported
Gemini 2.5 Flash-Lite
Stable version of Gemini 2.5 Flash-Lite, released in July of 2025
- Context
- 1.05M tokens
- Thinking
- off
Gemini 2.5 Flash Native Audio Latest
Latest release of Gemini 2.5 Flash Native Audio
- Context
- 131.1K tokens
- Thinking
- off
Gemini 2.5 Flash Native Audio Preview 09-2025
Gemini 2.5 Flash Native Audio Preview 09-2025
- Context
- 131.1K tokens
- Thinking
- off
Gemini 2.5 Flash Native Audio Preview 12-2025
Gemini 2.5 Flash Native Audio Preview 12-2025
- Context
- 131.1K tokens
- Thinking
- off
Gemini 2.5 Flash Preview TTS
Gemini 2.5 Flash Preview TTS
- Context
- 8.2K tokens
- Thinking
- Not supported
Gemini 2.5 Pro
Stable release (June 17th, 2025) of Gemini 2.5 Pro
- Context
- 1.05M tokens
- Thinking
- Not supported
Gemini 2.5 Pro Preview TTS
Gemini 2.5 Pro Preview TTS
- Context
- 8.2K tokens
- Thinking
- Not supported
Gemini 3 Flash Preview
Gemini 3 Flash Preview
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Nano Banana Pro
Gemini 3 Pro Image
- Context
- 131.1K tokens
- Thinking
- Not supported
Nano Banana 2
Gemini 3.1 Flash Image.
- Context
- 65.5K tokens
- Thinking
- Not supported
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Nano Banana 2 Lite
Gemini 3.1 Flash Lite Image.
- Context
- 65.5K tokens
- Thinking
- low · medium · high
Gemini 3.1 Flash Live Preview
Gemini 3.1 Flash Live Preview
- Context
- 131.1K tokens
- Thinking
- Not supported
Gemini 3.1 Flash TTS Preview
Gemini 3.1 Flash TTS Preview
- Context
- 8.2K tokens
- Thinking
- Not supported
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.1 Pro Preview Custom Tools
Gemini 3.1 Pro Preview optimized for custom tool usage
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.5 Flash
Gemini 3.5 Flash
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.5 Live Translate Preview
Gemini 3.5 Live Translate Preview
- Context
- 16.4K tokens
- Thinking
- Not supported
Gemini 3.5 Transcribe
A low-latency speech-to-text model with language detection, speaker diarization, word-level timestamps, Smart transcription, and custom vocabulary biasing.
- Context
- Not published
- Thinking
- Not supported
Gemini 3.5 Transcribe Live
A low-latency bidirectional streaming speech-to-text model over the Live API.
- Context
- Not published
- Thinking
- Not supported
Gemini 3.6 Flash
Gemini 3.6 Flash
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.7 Flash
Gemini 3.7 Flash is the next iteration in the Gemini 3 family, based on Gemini 3.6 Flash with improvements to its core reasoning foundation.
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
- Context
- 1.05M tokens
- Thinking
- low · medium · high
Gemini 3.8 Flash-Lite TTS
Fast, cost-efficient text-to-speech model built for high-throughput production workloads, real-time voice agent cascades, and Voice replication.
- Context
- 8.2K tokens
- Thinking
- Not supported
Gemini 3.8 Flash TTS
Flagship creative text-to-speech audio model engineered for studio-grade voice fidelity, expressive acting, Voice design, and Voice replication.
- Context
- 8.2K tokens
- Thinking
- Not supported
Gemini 3.8 Live
Default Live API model for low-latency voice agent experiences and real-time dialogue without reasoning delays.
- Context
- 131.1K tokens
- Thinking
- Not supported
Gemini 3.8 Live Extended Thinking
High-reasoning Live API model for voice interactions, recommended when higher background reasoning is required.
- Context
- 131.1K tokens
- Thinking
- Not supported
Gemini Embedding 001
Obtain a distributed representation of a text.
- Context
- 2K tokens
- Thinking
- Not supported
Gemini Embedding 2
Obtain a distributed representation of multimodal content.
- Context
- 8.2K tokens
- Thinking
- Not supported
Gemini Flash Latest
Latest release of Gemini Flash
- Context
- 1.05M tokens
- Thinking
- Not supported
Gemini Flash-Lite Latest
Latest release of Gemini Flash-Lite
- Context
- 1.05M tokens
- Thinking
- Not supported
Gemini Nano Banana 2.1
Gemini Nano Banana 2.1 is Google's state of the art image generation and editing model with advanced multimodal reasoning, high-resolution rendering, and controllable visual synthesis.
- Context
- 65.5K tokens
- Thinking
- medium · high
Gemini Omni 1.1 Flash
A generally available Interactions API model for conversational video generation, editing, extension, and interpolation.
- Context
- 1.05M tokens
- Thinking
- Not supported
Gemini Omni Flash Preview
Gemini Omni Flash Preview
- Context
- 131.1K tokens
- Thinking
- Not supported
Gemini Pro Latest
Latest release of Gemini Pro
- Context
- 1.05M tokens
- Thinking
- Not supported
Gemini Robotics ER 2 Preview
An embodied-reasoning model for spatial reasoning, video progress understanding, and agentic robot orchestration.
- Context
- Not published
- Thinking
- Not supported
Gemini Robotics ER 2 Streaming Preview
A Live API endpoint for real-time embodied reasoning with text, image, audio, and video input and text output.
- Context
- Not published
- Thinking
- Not supported
Gemma 4 26B A4B IT
Gemma 4 26B A4B IT
- Context
- 262.1K tokens
- Thinking
- Not supported
Gemma 4 31B IT
Gemma 4 31B IT
- Context
- 262.1K tokens
- Thinking
- Not supported
Lyria 3 Clip Preview
Lyria 3 30s model Preview
- Context
- 1.05M tokens
- Thinking
- Not supported
Lyria 3 Pro Preview
Lyria 3 Pro Preview
- Context
- 1.05M tokens
- Thinking
- Not supported
Lyria 3.5
Google Lyria 3.5 flagship full-length music generation model with text and image input and stereo audio plus lyrics output.
- Context
- 131.1K tokens
- Thinking
- Not supported
Lyria RealTime experimental
An experimental engine for high-fidelity real-time musical synthesis with weighted text prompts and raw PCM audio output.
- Context
- Not published
- Thinking
- Not supported
Nano Banana Pro
Gemini 3 Pro Image Preview
- Context
- 131.1K tokens
- Thinking
- Not supported
Veo 3.1 fast
Veo 3.1 fast
- Context
- 480 tokens
- Thinking
- Not supported
Veo 3.1
Veo 3.1
- Context
- 480 tokens
- Thinking
- Not supported
Veo 3.1 lite
Veo 3.1 lite
- Context
- 480 tokens
- Thinking
- Not supported
Public catalog snapshot. A listed model does not guarantee real-time provider or account availability.