Overview
Qwen VL Max is the best-performing model in the Qwen2.5-VL series. It supports 11 languages and excels at image descriptions, visual reasoning, and short video summaries with simple flat-rate pricing.
Key Features
- Flagship Qwen2.5-VL — Best-performing model in the Qwen2.5-VL series
- 11 languages — Chinese, English, Japanese, Korean, Arabic, Vietnamese, French, German, Italian, Spanish, Russian
- Image understanding — Accurate image descriptions and visual reasoning
- Video understanding — Short video summarization and analysis
- Simple pricing — Flat rate at $0.80 input / $3.20 output per 1M tokens
- OpenAI-compatible API — Drop-in replacement using chat completions format
Pricing
Per Million Tokens
Input Price: $0.8
Output Price: $3.2
Parameters
No input schema available.