Qwen3.7 Max
Qwen released 2026-05-21
$2.21 per million tokens, balanced
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +5.1 higher and costs 95% less ($0.105/M against $2.21/M) on this workload — and it does everything this model does.
Gemini 3.7 Flash is cheaper still (66% less) but drops 131K → 66K max output.
Every price dimension
| Input | $1.48/M |
|---|---|
| Output | $4.42/M |
| Cached input | $0.295/M |
| Cache write | $1.84/M |
Independent scores
| Intelligence | 46.7 |
|---|---|
| Coding | 66 |
| Agentic | 30.9 |
| LMArena Elo | 1474.3preview |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Best rankings by task
- godotgamedev #8of 43 1224
- 3d #12of 136 1316
- svg #12of 98 1260
- python-pptxslides #12of 35 1220
- webapps #13of 56 1246
- codecategories #14of 145 1302
- gamedev #14of 144 1309
- dataviz #14of 142 1299
Capability
| Context window | 1M |
|---|---|
| Max output | 131K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...