---
format: "aidr-story-markdown/v1"
id: "fb3c354fbfe34ef32c712d127b97b573a231b00b6ab8e7fd4654cf6e21b36444"
canonical_url: "https://aidr.today/fb3c354f?lang=en"
title: "Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-08T16:20:20.000Z"
category: "Tools"
topics: ["llm","devtools"]
source_urls: ["https://openrouter.ai/stepfun/step-5-preview","https://news.ycombinator.com/item?id=50007764"]
summary: "StepFun's Step 5 Preview model is available on OpenRouter. It features a sparse Mixture-of-Experts architecture with 27B active and 600B total parameters, a 1,000,000 token context window, and a maximum output of 64,000 tokens."
---

# Step 5 Preview, a 1M\-context MoE from StepFun, shows up on OpenRouter

> [Open the canonical story](<https://aidr.today/fb3c354f?lang=en>)

**Published:** 2026-10-08T16:20:20.000Z
**Category:** Tools
**Topics:** llm, devtools

## Summary

StepFun's Step 5 Preview model is available on OpenRouter\. It features a sparse Mixture\-of\-Experts architecture with 27B active and 600B total parameters, a 1,000,000 token context window, and a maximum output of 64,000 tokens\.

## Sources

- [Story source](<https://openrouter.ai/stepfun/step-5-preview>)
- [Discussion](<https://news.ycombinator.com/item?id=50007764>)