Catalog

Models

Explore models and compare pricing across providers. Select a creator to browse their models.

Gemini 2.0 Flash

Google
LLM

Fast and efficient Gemini model for high-throughput workloads.

1M ctx
2 providers

Gemini 2.5 Flash

Google
LLM

Speed-optimized Gemini with strong reasoning and multimodal capabilities.

1M ctx
5 providers

Gemini 2.5 Pro

Google
LLM

High-capability Gemini model for complex reasoning and coding tasks.

1M ctx
3 providers

Gemini 3 Flash

Google
LLM

Fast and efficient Gemini 3 model for high-throughput workloads.

1M ctx
6 providers

Gemini 3 Pro

Google
LLM

High-capability Gemini 3 model. Deprecated in favor of 3.1 Pro.

1M ctx
2 providers

Gemini 3.1 Flash Lite

Google
LLM

Gemini 3.1 Flash Lite, a proprietary Google model available via OpenRouter.

1.0M ctx
2 providers

Gemini 3.1 Pro

Google
LLM

Google's current flagship model with top benchmark scores and 1M context.

1M ctx
5 providers

Gemini 3.5 Flash

Google
LLM

Gemini 3.5 Flash, a proprietary Google model available via OpenRouter.

1.0M ctx
2 providers

Gemma 3 12B

Google
LLM

Mid-size open-weight Gemma model with vision support.

12B 128k ctx Open
4 providers

Gemma 3 27B

Google
LLM

Largest Gemma 3 model with strong reasoning and instruction following.

27B 128k ctx Open
5 providers

Gemma 3 4B

Google
LLM

Compact open-weight model for edge and mobile deployment.

4B 32k ctx Open
3 providers

Gemma 4 12B

Google
LLM

Latest Gemma generation optimized for reasoning and agentic workflows.

12B 128k ctx Open
No providers yet

Gemma 4 26B A4B

Google
LLM

Gemma 4 26B A4B, an open-weight Google model available via OpenRouter.

262k ctx Open
1 provider

Gemma 4 27B

Google
LLM

Most capable open Gemma model with best intelligence-per-parameter.

27B 128k ctx Open
4 providers