Developers
Learn
Company
Sign in
Chat
Chat with and directly compare LLM endpoints
Benchmarks
Compare LLM endpoints with live performance benchmarks
Documentation
Learn how to use the Unify API
Blog
Read about LLM deployment infrastructure
Newsletter
Stay up to date with the latest in AI
Paper Readings
Join our discussions around cuttin-edge AI research
Talks
Dive deep with us into the AI landscape
Careers
Join our team and let’s Unify AI!
Contact
Reach out to our team
Privacy & Cookies
How we treat your navigation data
Terms Of Service
General requirements for using our Service
Socials
Follow us through our social accounts:
Sign in
Chat
Chat with and directly compare LLM endpoints
Benchmarks
Compare LLM endpoints with live performance benchmarks
Documentation
Learn how to use the Unify API
Blog
Read about LLM deployment infrastructure
Newsletter
Stay up to date with the latest in AI
Paper Readings
Join our discussions around cuttin-edge AI research
Talks
Dive deep with us into the AI landscape
Careers
Join our team and let’s Unify AI!
Contact
Reach out to our team
Privacy & Cookies
How we treat your navigation data
Terms Of Service
General requirements for using our Service
Socials
Follow us through our social accounts:
Back to Benchmarks
llama-2-70b-chat
text-generation
Uploaded: 09.01.2024
⏱️ Benchmarks
📑 API Docs
✨ Query this model
Region:
Hong Kong
Belgium
Iowa
Seq Length:
Short
Long
Providers
anyscale
perplexity-ai
together-ai
replicate
octoai
fireworks-ai
lepton-ai
deepinfra
aws-bedrock
Learn more about how we are collecting this data
here
Input Cost
Output Cost
Output Tks / Sec
P
90
_{P90}
P
9
0
TTFT
P
90
_{P90}
P
9
0
ITL
P
90
_{P90}
P
9
0
E2E Latency
P
90
_{P90}
P
9
0
Cold Start
1 $/1M tks
1 $/1M tks
28.91 tks/sec
1053.12 ms
34.59 ms
7728.83 ms
0 sec
0.7 $/1M tks
2.8 $/1M tks
50.49 tks/sec
981.73 ms
19.81 ms
4507.36 ms
0 sec
0.9 $/1M tks
0.9 $/1M tks
78.05 tks/sec
1149.57 ms
12.81 ms
3827.45 ms
0 sec
0.65 $/1M tks
2.75 $/1M tks
40.24 tks/sec
884.52 ms
24.85 ms
3991.22 ms
0 sec
0.6 $/1M tks
1.9 $/1M tks
25.04 tks/sec
698.19 ms
39.93 ms
7526.62 ms
0 sec
0.9 $/1M tks
0.9 $/1M tks
91.14 tks/sec
458.71 ms
10.97 ms
2137.43 ms
0 sec
0.8 $/1M tks
0.8 $/1M tks
32.95 tks/sec
1077.08 ms
30.35 ms
7601.84 ms
0 sec
0.7 $/1M tks
0.9 $/1M tks
40.65 tks/sec
623.57 ms
24.6 ms
5150.03 ms
0 sec
1.95 $/1M tks
2.56 $/1M tks
19.46 tks/sec
1205.62 ms
51.39 ms
9376.51 ms
0 sec