Qwen: 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...

• Context window: 160,000 tokens
• Input: text
• Output: text
• Pricing: $0.07/M input tokens, $0.27/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.