Qwen3 235B A22B Thinking 2507
Qwen · qwen/qwen3-235b-a22b-thinking-2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Qwen3 235B A22B Thinking 2507 ranks #221 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.26 blended per million tokens, it is cheaper than 45% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 117964
Pricing
Output / 1M: 2.30
Blend / 1M: 1.26
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $1.26per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $1.26 |
| 10,000,000 | $12.65 |
| 100,000,000 | $126.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Qwen
- Qwen3.8 Max (0902)$4.00 / 1M · Q 93.0
- Qwen3.8 27B$1.71 / 1M · Q 87.2
- Qwen3.7 Max$2.95 / 1M · Q 82.3
- Qwen3.6 Max Preview$3.59 / 1M · Q 79.9
- Qwen3.6 Plus$1.14 / 1M · Q 78.7
Closest API price
- GLM 5$1.26 / 1M
- Qwen3 VL 30B A3B Thinking$1.30 / 1M
- Qwen3 30B A3B Thinking 2507$1.30 / 1M
- R1 0528$1.33 / 1M
- Aion-2.0$1.20 / 1M