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...
Everything else
| Max output | 33K |
|---|---|
| Input / 1M | $0.07 |
| Output / 1M | $0.27 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $0.34 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | no |
| Open weights | yes |
| Released | 2025-07-31 |
| Knowledge cutoff | 2025-06-30 |
| Retires | — |
| Catalog id | qwen/qwen3-coder-30b-a3b-instruct |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.