QQwen · Released Feb 4, 2026
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...
- Released
- Feb 4 2026
- Context window
- 262K 236K out
- Input / 1M tokens
- $0.12 from Free
- Output / 1M tokens
- $0.80 from Free
Where to run it
20 providers compared
Free to try on InferX — free endpoints are often limited-time and rate-limited. Included in Alibaba Coding Plan (China), Alibaba Coding Plan. Cheapest: LLM Gateway, DevPass (LLM Gateway) at $0.11 / $0.68 per 1M input / output tokens — 75% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| InferXfree · may be limited-time | Free | Free | — | 260K | 66K | — | Free |
| Alibaba Coding Plan (China)subscription plan | Plan | Plan | Plan | 262K | 66K | — | Plan |
| Alibaba Coding Plansubscription plan | Plan | Plan | Plan | 262K | 66K | — | Plan |
| LLM Gateway | $0.11 | $0.68 | $0.06 | 262K | 262K | — | Cheapest |
| DevPass (LLM Gateway) | $0.11 | $0.68 | $0.06 | 262K | 66K | — | Cheapest |
| ParasailBF16 | $0.12 | $0.80 | $0.07 | 262K | 236K | 100%24h | +16% |
| Kilo Gateway | $0.12 | $0.80 | $0.07 | 262K | 236K | — | +16% |
| Merge Gatewayno tool calling | $0.15 | $0.80 | $0.075 | 262K | 66K | — | +25% |
| Cortecs | $0.17 | $0.89 | — | 256K | 256K | — | +39% |
| Eden AI | $0.17 | $0.90 | — | 128K | 66K | — | +41% |
| NanoGPT | $0.25 | $0.80 | $0.08 | 262K | 66K | — | +55% |
| Regolo AI | $0.30 | $1.20 | — | 262K | 16K | — | +110% |
| Jiekou.AI | $0.20 | $1.50 | — | 262K | 66K | — | +110% |
| Hugging Face | $0.20 | $1.50 | — | 262K | 66K | — | +110% |
| Ofox | $0.20 | $1.50 | — | 262K | 66K | — | +110% |
| Prime Inference | $0.30 | $1.50 | — | 262K | 236K | — | +140% |
| Vercel AI Gateway | $0.50 | $1.20 | — | 256K | 256K | — | +170% |
| Together AI | $0.50 | $1.20 | — | 262K | 262K | — | +170% |
| Amazon Bedrock | $0.50 | $1.20 | — | 262K | 66K | — | +170% |
| Opper | $0.58 | $2.32 | — | 262K | 66K | — | +307% |
Value
Price vs. performance
Qwen3 Coder Next Other Qwen Other labs Value frontier · SciCode vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
2 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 36.2% | #90of 102 | Claude Opus 5.566.9% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 0.0% | #92of 111 | GPT-5.6 Sol32.3% |
Specs
Details
- Model ID
qwen/qwen3-coder-next- Developer
- Qwen
- Release date
- Feb 4, 2026 ·
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- API price
- $0.12 / $0.80 per 1M input / output tokens
- Providers
- 20
- Input types
- text
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.