Models
The full catalog is data-driven -- every model below comes from the registry, not a hard-coded list. New hosted models show up here as soon as they're added, with no frontend changes required.
Hosted by LLM Studio
Qwen 3 0.6B
studio/qwen3-0.6b
Tiny, fast general-purpose chat model. Good default for low-cost hosted usage.
- Parameters
- 0.6B
- Context window
- 32,768 tokens
- Provider
- studio
Gemma 3 270M
studio/gemma3-270m
Extremely lightweight model for simple, latency-sensitive chat.
- Parameters
- 270M
- Context window
- 32,768 tokens
- Provider
- studio
Qwen 3 Embedding 0.6B
studio/qwen3-embedding-0.6b
Hosted embedding model for knowledge-base indexing and retrieval.
- Parameters
- 0.6B
- Context window
- 32,768 tokens
- Provider
- studio
Bring your own key
GPT-5.1
openai/gpt-5.1
OpenAI's flagship general-purpose model.
- Context window
- 400,000 tokens
- Provider
- openai
GPT-5.1 Mini
openai/gpt-5.1-mini
Smaller, faster, cheaper OpenAI model for everyday tasks.
- Context window
- 400,000 tokens
- Provider
- openai
Claude Sonnet 5
anthropic/claude-sonnet-5
Anthropic's balanced flagship model for coding and agentic work.
- Context window
- 200,000 tokens
- Provider
- anthropic
Claude Haiku 4.5
anthropic/claude-haiku-4-5
Anthropic's fastest model.
- Context window
- 200,000 tokens
- Provider
- anthropic
Gemini 2.5 Pro
google/gemini-2.5-pro
Google's flagship reasoning model with a very long context window.
- Context window
- 1,000,000 tokens
- Provider
Gemini 2.5 Flash
google/gemini-2.5-flash
Fast, low-cost Gemini model.
- Context window
- 1,000,000 tokens
- Provider
Mistral Large
mistral/mistral-large-latest
Mistral AI's flagship model for complex reasoning and code.
- Context window
- 128,000 tokens
- Provider
- mistral
Mistral Small
mistral/mistral-small-latest
Fast, low-cost Mistral model for everyday tasks.
- Context window
- 128,000 tokens
- Provider
- mistral