Qwen3.6 Max Preview vs Qwen3.7 Max Thinking
Qwen3.7 Max Thinking is cheaper on output tokens, while Qwen3.7 Max Thinking offers a larger context window. Choose Qwen3.6 Max Preview or Qwen3.7 Max Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3.6 Max Preview | Qwen3.7 Max Thinking |
|---|---|---|
| Provider | Alibaba | NanoGPT |
| Input / 1M tokens | $1.30 | $2.50 |
| Output / 1M tokens | $7.80 | $7.50 |
| Context window | 262K | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | Apr 2026 | May 2026 |
| GPQA Diamond score | 87.4 | — |
| FrontierMath score | 23.1 | — |
| LMArena (Chatbot Arena) Elo score | 1447 | — |
| LMArena WebDev Elo score | 1482 | — |
| LiveBench score | — | 75.2 |
FAQ
Is Qwen3.6 Max Preview or Qwen3.7 Max Thinking cheaper?
Qwen3.7 Max Thinking is cheaper on output tokens ($7.50 vs $7.80 per 1M).
Which has the larger context window, Qwen3.6 Max Preview or Qwen3.7 Max Thinking?
Qwen3.7 Max Thinking has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.