Back to Benchmarks

qwen-2.5-72b-instruct

text-generation
Uploaded: 23.09.2024
⏱️ Benchmarks
✨ Query this model
Region:
Hong KongBelgiumIowa
Seq Length:
ShortLong
Providers
provider icon
deepinfra
provider icon
fireworks-ai
Learn more about how we are collecting this data here
Input Cost
Output Cost
Output Tks / SecP90_{P90}
TTFTP90_{P90}
ITLP90_{P90}
E2E LatencyP90_{P90}
Cold Start
0.35 $/1M tks
0.4 $/1M tks
30.6 tks/sec
637.01 ms
32.68 ms
6192.52 ms
0 sec
Not computed
Not computed
Not computed
Not computed
Not computed
Not computed
Not computed