UTC

Step 5 Preview

StepFun (China) · open weights · served by 26 providers · tool calling, reasoning, image input, video input

stepfun/step-5-preview

Weights
Open
Released
2026-09-16
Knowledge cutoff
Not stated
Context window
1M
Hugging Face repository

stepfun-ai/Step-5-Preview at commit 364b3b03fe, last changed 2026-10-15

Licence
other
Access
Open download
Library
Not stated
Formats
.safetensors
  • No model signature file is published with the weights.

What the Hub's scanners report

28 weight files, 28 with a scan result. No scanner reports an issue with them.

The model at this commit, its 28 weight files with their SHA-256.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • AIHubMixstep-5-preview
  • AI/ML APIstepfun/step-5-preview
  • CommandCodestepfun/Step-5-Preview
  • Deep Infrastepfun-ai/Step-5-Previewdeprecated
  • Eden AIdeepinfra/stepfun-ai/Step-5-Preview
  • Eden AItencent/step-5-preview
  • EmpirioLabs AIstep-5-preview
  • Ezkielynastep-5-preview
  • Kenaristep-5-preview
  • Kilo Gatewaystepfun/step-5-preview
  • DevPass (LLM Gateway)step-5-preview
  • LLM Gatewaytencent/step-5-preview
  • NanoGPTstepfun/step-5-preview
  • Novita AIstepfun/step-5-preview
  • Nvidiastepfun-ai/step-5-preview
  • OpenCodestep-5-preview-freedeprecated
  • OpenCode Gostep-5-preview
  • OpenCode Gostep-5-preview-freedeprecated
  • OpenRouterstepfun/step-5-preview
  • Requestystep-5-preview
  • RunInfrastepfun-ai/Step-5-Preview
  • StepFun (China)step-5-preview
  • StepFun (Global)step-5-preview
  • StepFun Step Plan (Global)step-5-preview
2 more providers

StepFun Step Plan (China) (step-5-preview), Vercel AI Gateway (stepfun/step-5-preview)

Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.