StepFun's Step 5 Preview brings a 1M-token context window to OpenRouter
Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter
StepFun's flagship agentic model, Step 5 Preview, is now on OpenRouter with a 1,000,000-token context window and a sparse Mixture-of-Experts design (27B active / 600B total parameters). Priced at $1 per million input tokens and $2.70 per million output tokens, it targets extended software engineering and professional knowledge work, particularly finance. Early traffic comes from agents like OpenClaw and Hermes Agent, with a 92.9% cache hit rate.
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).
- syntaxing
Step models were IMO the first local model you can run on 128GB shared memory that worked well. Really excited to see how it compares to Qwen Flash Next.
Edit: bummer, didn’t know it’s 600B-A27B. No way to run that on 228GB.
- robertlane0
Well, according to Artificial Analysis (which I'll admit I've been using as a bit of a mental crutch to avoid comparing models myself, so YMMV), it's smarter and slightly cheaper than Gemini 3.8 Flash, which has been my benchline for "cheap and smart enough", I'll give it a try on OpenCode for the week but I'm not sure I'll be compelled enough to switch from Muse Spark 1.3.
- jstummbillig
Why is that interesting?