OpenAI's flagship multimodal model. Fast, capable, and widely used.
Performance
Time to first token
859ms
↑ 1%vs prior 24h
Total response time
1512ms
↑ 6%vs prior 24h
Throughput
31.8tok/s
↓ 6%vs prior 24h
Inter-token latency
15.2ms
↑ 16%vs prior 24h