Models

Dense 32B model with hybrid thinking, solid multilingual ability and good instruction following at a low price.

qwen/qwen3-32b131K context$0.15/M input$0.6/M output

Efficient mixture-of-experts coding model with 3B active parameters, built for repository-scale code understanding and agentic coding.

qwen/qwen3-coder-30b-a3b262K context$0.15/M input$0.6/M output