Qwen3.7 Flash Thinking
Lightweight multimodal Qwen model for high-throughput text, image, and video tasks
Model facts
- Context window
- 984K tokens
- Maximum output
- 66K tokens
- Cheapest paid input
- $0.03 per 1M tokens
- Cheapest paid output
- $0.13 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, text, image, video.
Observed price history
- 2026-08-24: $0.03 input / $0.13 output per 1M tokens
API providers
- NanoGPT — model id qwen3.7-flash:thinking; $0.03 input / $0.13 output per 1M tokens; provider documentation