Qwen3 30B A3B
Qwen · qwen/qwen3-30b-a3b
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
Qwen3 30B A3B ranks #116 of 346 models in the default AI Benchmark Hub order (quality first, then cost). At $0.31 blended per million tokens, it is cheaper than 76% of models with published API pricing. Its 40,960-token context window is 6.4× smaller than the catalog median (262,144 tokens).
Context
Max output: 16384
Pricing
Output / 1M: 0.50
Blend / 1M: 0.31
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.31per 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 | $0.31 |
| 10,000,000 | $3.10 |
| 100,000,000 | $31.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Qwen
- Qwen3.8 Max (0902)$4.00 / 1M · Q 98.4
- Qwen3.8 27B$1.71 / 1M · Q 93.0
- Qwen3.7 Max$2.95 / 1M · Q 87.3
- Qwen3.6 Max Preview$3.59 / 1M · Q 84.5
- Qwen3.6 Plus$1.14 / 1M · Q 83.1
Closest API price
- Qwen3.8 Flash$0.31 / 1M
- Qwen3 235B A22B Instruct 2507$0.32 / 1M
- Qwen3 VL 8B Instruct$0.29 / 1M
- Qwen3 8B$0.29 / 1M
- DeepSeek V3.2$0.33 / 1M