Qwen3 235B A22B
Qwen · qwen/qwen3-235b-a22b
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...
Qwen3 235B A22B ranks #211 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.14 blended per million tokens, it is cheaper than 48% 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: 8192
Pricing
Output / 1M: 1.82
Blend / 1M: 1.14
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $1.14per 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 | $1.14 |
| 10,000,000 | $11.38 |
| 100,000,000 | $113.75 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Qwen
- Qwen3.8 Max (0902)$4.00 / 1M · Q 95.1
- Qwen3.8 27B$1.71 / 1M · Q 89.0
- Qwen3.7 Max$2.95 / 1M · Q 83.8
- Qwen3.6 Max Preview$3.59 / 1M · Q 81.2
- Qwen3.6 Plus$1.14 / 1M · Q 80.0
Closest API price
- Qwen3.6 Plus$1.14 / 1M · Q 80.0
- Qwen3 VL 8B Thinking$1.14 / 1M
- Seed-2.0-Lite$1.13 / 1M
- Seed 1.6$1.13 / 1M
- GPT-5.1-Codex-Mini$1.13 / 1M