Qwen3.5 122B A10B
by Merge Gateway · family qwen · listed Feb 2026RTW
Qwen vision-language model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input$0.115
Output$0.917
Cache read$0.023
Cache write—
Against the market
On the record
- Model id
qwen/qwen3.5-122b-a10b- Context window
- 131K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-02-23
- Last updated
- 2026-02-23
- Provider docs
- docs.merge.dev/merge-gateway
Back of the envelope
≈
Also listed at
- AIHubMix$0.113 in · $0.901 out
- OrcaRouter$0.115 in · $0.917 out
- SiliconFlow (China)$0.12 in · $0.956 out
- OpenRouter$0.26 in · $2.08 out
- SiliconFlow$0.26 in · $2.08 out
- NanoGPT$0.26 in · $2.08 out
- Kilo Gateway$0.26 in · $2.08 out
- Deep Infra$0.29 in · $2.40 out
- Ofox$0.29 in · $2.29 out
- DevPass (LLM Gateway)$0.40 in · $3.20 out
- Hugging Face$0.40 in · $3.20 out
- LLM Gateway$0.40 in · $3.20 out
- Mixlayer$0.40 in · $3.20 out
- Jalapeno Cloud$0.40 in · $3.20 out
- Alibaba$0.40 in · $3.20 out