API Providers Leaderboard

Compare the latency, speed, and pricing of top serverless inference providers for open-weights models.

#ProviderModels AvailableAvg TTFT (s)Avg Speed (t/s)Pricing Level
1Groq15+
0.15s
800
Medium
2Fireworks AI85+
0.20s
180
Low
3OctoAI25+
0.22s
150
Low
4Together AI150+
0.25s
120
Low
5Anyscale35+
0.28s
110
Medium
6DeepInfra40+
0.35s
90
Lowest