Qwen3.7 Flash
by CrossModel · family qwen · listed Jul 2026RTV
Lightweight multimodal Qwen model for high-throughput text, image, and video tasks
Current rates USD per 1M tokens
Input$0.04
Output$0.13
Cache read$0.01
Cache write$0.04
Against the market
On the record
- Model id
qwen/qwen3.7-flash- Context window
- 1M tokens
- Max output
- 66K tokens
- Input modalities
- text, image, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-07-15
- Last updated
- 2026-07-15
- Provider docs
- www.crossmodel.ai/docs
Back of the envelope
≈
Also listed at
- Alibaba (China)$0.0296 in · $0.118 out
- NanoGPT$0.03 in · $0.13 out
- OpenRouter$0.03 in · $0.13 out
- LLM Gateway$0.03 in · $0.13 out
- Vercel AI Gateway$0.03 in · $0.13 out
- DevPass (LLM Gateway)$0.03 in · $0.13 out
- Kilo Gateway$0.03 in · $0.13 out
- Charm Hyper$0.20 in · $0.80 out