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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000015 | $0.150 |
| completion | 0.0000006 | $0.600 |