An open-source code model from Qwen. The latest Qwen3-Coder series delivers strong Coding Agent capabilities. It excels at tool calling and environment interaction. It supports autonomous programming and delivers outstanding coding performance while maintaining broad general-purpose abilities.How to use \| API reference #### International If you select the International deployment scope, model inference compute resources are dynamically scheduled worldwide, excluding the Chinese mainland. Static data is stored in your selected region. Supported region: Singapore.
function_calling| Model | Context | Max out | Pricing |
|---|---|---|---|
| qwen3-embedding-0.6b | 33K | — | $0.01$0 |
| qwen3-embedding-8b | 41K | — | $0.01$0 |
| qwen3-embedding-4b | 33K | — | $0.02$0 |
| qwen3-coder-30b-a3b | 262K | — | $0.15$0.6 |
| qwen3-next-80b-a3b-instruct | 262K | — | $0.15$1.2 |
| qwen3-next-80b-a3b-thinking | 262K | — | $0.15$1.2 |
| qwen3-vl-235b-a22b-instruct | 262K | — | $0.2$0.88 |
| qwen3-vl-instruct | 262K | — | $0.2$0.88 |
| qwen3-coder | 262K | — | $0.22$1.8 |
| qwen3-235b-a22b-thinking | 131K | — | $0.4$4 |
| qwen3-vl-thinking | 131K | — | $0.4$4 |
| qwen3-coder-next | 256K | 66K | $0.5$1.2 |
| qwen3-coder-plus | 1M | 66K | $1$5 |
| qwen3-max-preview | 262K | — | $1.2$6 |
| qwen3-max-thinking | 256K | — | $1.2$6 |
| qwen3-max | 262K | 33K | $1.2$6 |
/v1/models/vercel/alibaba/qwen3-coder-next