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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Alibaba | $0.455 | $1.82 | 131K | 100% |
Qwen3 235B A22B costs $0.455 per million input tokens and $1.82 per million output tokens via OpenRouter, making it 159th cheapest of 298 paid models.
Qwen3 235B A22B scores 19.8 on the Artificial Analysis Intelligence Index, ranking 119th of 178 benchmarked models, with a GPQA Diamond score of 70%.
Qwen3 235B A22B generates around 53 tokens per second with 630ms time-to-first-token (p50), the 160th fastest tracked model.
Qwen3 235B A22B supports a 131K-token context window and can output up to 8K tokens. It accepts text input.