Qwen3.5 122B-A10B
by Alibaba · family qwen · listed Feb 2026RTVW
Qwen vision-language model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input$0.40
Output$3.20
Cache read—
Cache write—
Against the market
On the record
- Model id
qwen3.5-122b-a10b- Context window
- 262K tokens
- Max output
- 66K tokens
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-02-23
- Last updated
- 2026-02-23
- Provider docs
- www.alibabacloud.com/help/en/model-studio/models
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- OrcaRouter$0.115 in · $0.917 out
- SiliconFlow$0.26 in · $2.08 out
- Kilo Gateway$0.26 in · $2.08 out
- OpenRouter$0.26 in · $2.08 out
- SiliconFlow (China)$0.29 in · $2.32 out
- Deep Infra$0.29 in · $2.40 out
- NanoGPT$0.36 in · $2.88 out
- Hugging Face$0.40 in · $3.20 out
- NovitaAI$0.40 in · $3.20 out
- Mixlayer$0.40 in · $3.20 out
- NEAR AI Cloud$0.40 in · $3.20 out
- Cortecs$0.444 in · $3.11 out