Qwen3.7 Flash — AI Model Comparison

Author

Context1M

Tool calling

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.

Tokens, last 14 days

Prompt24.1M

Completion4.67M

Total28.8M

Performance

Latency (p50)1.15 s

Throughput (p50)97.9 tok/s

Pricing

Input$0.01/M tokens~~market price $0.03/M tokens~~

Output$0.07/M tokens~~market price $0.13/M tokens~~

Cached input$0.003/M tokens~~market price $0.006/M tokens~~

Features

Inputtext, image

Outputtext

APIResponses, Chat Completions, Messages

Vision

Open model page