Open-weight MoE model
StepFun's Step 5 Preview is an open-weight mixture-of-experts model with 600 billion total parameters and 27 billion active parameters per token.
Loading page…
Automation / product dossier
Open-weight 600B MoE model with 27B active parameters and a 1M-token context for coding and agent tasks.
Product brief
Step 5 Preview is StepFun's open-weight MoE for coding, financial research and long-running agents. It has 600B total parameters, 27B active per token and a 1M-token context, with deployment support for vLLM, SGLang and Transformers.
Why we selected it
An open-weight model with concrete technical specifications: 600B total parameters, 27B active per token, a 1M-token context, and support for three deployment frameworks. Particularly relevant to researchers and builders
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
StepFun's Step 5 Preview is an open-weight mixture-of-experts model with 600 billion total parameters and 27 billion active parameters per token.
Provides a context window of one million tokens.
Supports deployment with vLLM, SGLang, and Transformers.
Best-fit use cases
FAQ
Step 5 Preview is StepFun's open-weight mixture-of-experts model intended for coding, financial research, and long-running agents.
The model has 600 billion total parameters, with 27 billion active per token.
Step 5 Preview has a one-million-token context window.
The listed deployment frameworks are vLLM, SGLang, and Transformers.