Qwen2.5 VL 72B
by Qwen · chat
72B parameter vision-language model excelling at image/document understanding, OCR, chart analysis, and visual reasoning with 33K context.
Pricing
Input: $0.2375/M tokens · Output: $0.7125/M tokens
Capabilities
Vision, Streaming
Context: 33K tokens
Max output: 8K tokens
Routes: 1/1 healthy
Performance
TTFT: 649ms · Latency: 4325ms · Throughput: 4.8 tok/s