- Providers
- StepFun
StepFun: API pricing, speed & models
StepFun hosts 1 active AI models, with input pricing from $0.10 per 1M tokens. Compare StepFun's API speed, pricing, and reliability against other inference providers.
First-party only
Catalog throughput150 c/s
Catalog latency300ms
From$0.10 /M tok
Catalog
Type
Price
1 model| Model |
|---|
Step-3.5-FlashExclusivecache pricing · 150 QPS |