Qwen2.5 VL 72B Instruct
Specifications
- Input
- Output
- Context window
- 33K tokens
- Released
- Jan 2025
Performance
- Speed
- 29 t/s
- TTFT
- 3.7s
- Latency
- 127 ms
- Intelligence
- —
Pricing
- Input
- €0.25 per 1M tokens
- Output
- €0.75 per 1M tokens
About this model
High-end multimodal model delivering strong vision-language reasoning with long-context support.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- No
Knowledge horizon
Released Jan 2025
Today
Since release 17 mo
See also
Add Model to Comparison
Search for a model to add