Qwen2.5 VL 72B
Leading open-source vision-language model
Qwen2.5 VL 72B is one of the most capable open-source vision-language models, able to analyse images, charts, documents, and screenshots with strong accuracy. It outperforms GPT-4V on several vision benchmarks.
Try Qwen2.5 VL 72BSpecifications
Context window128k tokens
Input price$0.400 / 1M tokens
Output price$0.400 / 1M tokens
Credits per query3 cr
Released2025-01
LicenseApache 2.0
Features
VisionTool useJSON modeFunction calling
Benchmark Scores
What do these mean?Sourced from official model cards and academic papers. Higher is better.
,
,
,
,
,
84%
,
,