Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000012 | $0.120 |
| completion | 0.0000008 | $0.800 |
| input_cache_read | 0.00000007 | $0.070 |
{
"temperature": 1,
"top_p": 0.95,
"frequency_penalty": null
}