Qwen3.6 Plus
Qwen released 2026-04-02
MiniMax M3 is both better and cheaper.
It scores +4.9 higher and costs 28% less ($0.525/M against $0.731/M) on this workload — and it does everything this model does.
DeepSeek V4 Flash 0731 is cheaper still (86% less) but drops no image, video input.
Every price dimension
| Input | $0.325/M |
|---|---|
| Output | $1.95/M |
| Cache write | $0.406/M |
Past 256,000 tokens the price changes. Input goes to $1.30/M (4×) and output to $3.90/M. The headline rate does not apply to a long-context workload.
Independent scores
| Intelligence | 40.5 |
|---|---|
| Coding | 54.5 |
| Agentic | 29 |
| LMArena Elo | 1436.8default |
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
- dataviz #31of 142 1251
- svg #31of 98 1202
- codecategories #33of 145 1260
Capability
| Context window | 1M |
|---|---|
| Max output | 66K |
| Input modes | text, image, video |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...