qwen/qwen3-coder-next
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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Ionstreamfp8 | $0.110 | $0.800 | 262K | 100% |
| Parasailbf16 | $0.120 | $0.800 | 262K | 100% |
| StreamLake | $0.180 | $0.900 | 256K | — |
| AtlasCloudfp8 | $0.180 | $1.35 | 262K | — |
| Novitafp8 | $0.200 | $1.50 | 262K | — |
Qwen3 Coder Next costs $0.110 per million input tokens and $0.800 per million output tokens via OpenRouter, making it 64th cheapest of 298 paid models.
Qwen3 Coder Next scores 28.3 on the Artificial Analysis Intelligence Index, ranking 85th of 179 benchmarked models, with a GPQA Diamond score of 74%.
Qwen3 Coder Next generates around 84 tokens per second with 565ms time-to-first-token (p50), the 85th fastest tracked model.
Qwen3 Coder Next supports a 262K-token context window and can output up to 262K tokens. It accepts text input.