← All models
StepFun models
3 models on Infery.ai.
Step 3.5 Flash
Step 3.5 Flash
step-3.5-flash
Step 3.5 Flash is StepFun's most capable open-source foundation model. 262,144 token context window, maximum output of 65,536 tokens.
262K ctx
12.5 cr in / 1M37.5 cr out / 1M
ChatStreamingToolsJSON
Step 3.7 Flash
Step 3.7 Flash
step-3.7-flash
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.
256K ctx
25 cr in / 1M144 cr out / 1M5 cr cached in / 1M
ChatStreamingVisionToolsJSON
Step 5 Preview
Step 5 Preview
step-5-preview
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B…
1M ctx
125 cr in / 1M338 cr out / 1M12.5 cr cached in / 1M
ChatStreamingVisionToolsJSON