Models
One name per model, however many providers serve it.
StepFun: Step 5 Preview
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).
stepfun/step-5-previewOct 8, 20261M context362,096 Toman/M input tokens973,560 Toman/M output tokensStepFun: Step 3.7 Flash
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.
stepfun/step-3.7-flashMay 28, 2026262K context75,152 Toman/M input tokens416,752 Toman/M output tokens
2 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

