Qwen3 30B A3B Thinking 2507
Qwen · qwen/qwen3-30b-a3b-thinking-2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Qwen3 30B A3B Thinking 2507 ranks #223 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.30 blended per million tokens, it is cheaper than 45% of models with published API pricing. Its 81,920-token context window is 3.2× smaller than the catalog median (262,144 tokens).
Context
Max output: 32768
Pricing
Output / 1M: 2.40
Blend / 1M: 1.30
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $1.30per 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 | $1.30 |
| 10,000,000 | $13.00 |
| 100,000,000 | $130.00 |
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 87.4
- 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
- Qwen3 VL 30B A3B Thinking$1.30 / 1M
- MiniMax M1$1.30 / 1M
- R1 0528$1.33 / 1M
- Qwen3 235B A22B Thinking 2507$1.26 / 1M
- GLM 5$1.26 / 1M