qwen/qwen3.6-35b-a3b
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Parasailfp8 | $0.150 | $1.00 | 262K | 97.9% |
| AtlasCloudfp8 | $0.161 | $0.965 | 262K | 98.2% |
| AkashMLfp8 | $0.170 | $1.20 | 262K | 95% |
| SiliconFlowfp8 | $0.200 | $1.60 | 262K | 94.8% |
| WandBfp8 | $0.250 | $1.25 | 262K | 100% |
Qwen3.6 35B A3B costs $0.150 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 77th cheapest of 298 paid models.
Qwen3.6 35B A3B scores 31.5 on the Artificial Analysis Intelligence Index, ranking 73rd of 178 benchmarked models, with a GPQA Diamond score of 82%.
Qwen3.6 35B A3B generates around 177 tokens per second with 248ms time-to-first-token (p50), the 19th fastest tracked model.
Qwen3.6 35B A3B supports a 262K-token context window and can output up to 262K tokens. It accepts text, image, video input.