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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.120 | $0.500 | 41K | 99.8% |
| Alibaba | $0.130 | $0.520 | 131K | 100% |
| NextBitfp8 | $0.140 | $0.550 | 33K | 68.5% |
Qwen3 30B A3B costs $0.120 per million input tokens and $0.500 per million output tokens via OpenRouter, making it 67th cheapest of 298 paid models.
Qwen3 30B A3B scores 15.3 on the Artificial Analysis Intelligence Index, ranking 141st of 178 benchmarked models, with a GPQA Diamond score of 62%.
Qwen3 30B A3B generates around 95 tokens per second with 316ms time-to-first-token (p50), the 72nd fastest tracked model.
Qwen3 30B A3B supports a 131K-token context window and can output up to 16K tokens. It accepts text input.