Qwen: Qwen3 Coder 30B A3B Instruct by qwen | Mume AI
Qwen3 Coder 30B A3B Instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
by Qwen|262K context|$0.07/M input tokens|$0.27/M output tokens
Endpoints
Available providers for this model, with details on pricing, context limits, and real-time health metrics.
