qwen/qwen3-30b-a3b-instruct-2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLake | $0.048 | $0.193 | 128K | 99.9% |
| SiliconFlowfp8 | $0.090 | $0.300 | 262K | 69.7% |
| Nebiusfp8 | $0.100 | $0.300 | 262K | 100% |
| AtlasCloudfp8 | $0.100 | $0.300 | 131K | 99.8% |
| WandBbf16 | $0.100 | $0.300 | 262K | 100% |
| Alibaba | $0.130 | $0.520 | 131K | 99.9% |
Qwen3 30B A3B Instruct 2507 costs $0.048 per million input tokens and $0.193 per million output tokens via OpenRouter, making it 14th cheapest of 298 paid models.
Qwen3 30B A3B Instruct 2507 scores 15.0 on the Artificial Analysis Intelligence Index, ranking 143rd of 178 benchmarked models, with a GPQA Diamond score of 66%.
Qwen3 30B A3B Instruct 2507 generates around 72 tokens per second with 221ms time-to-first-token (p50), the 106th fastest tracked model.
Qwen3 30B A3B Instruct 2507 supports a 131K-token context window and can output up to 32K tokens. It accepts text input.