88Z AI, 15 October — StepFun has officially released the weights for its Step 5 Preview model, which are now available on Hugging Face and ModelScope. Utilizing a sparse MoE architecture, the model features 600 billion total parameters with only 27 billion activated. It supports a context window of one million tokens and natively handles both text and visual inputs. The model demonstrates strong performance in long-horizon agent tasks such as AI coding and finance, ranking second globally in 第三方模型接口 call volume.
At a glance
- Step 5 Preview weights are live on Hugging Face and ModelScope, featuring a sparse MoE architecture with 600B total and 27B activated parameters.
- The model supports a million-token context and multimodal inputs, excelling in long-horizon agent tasks and ranking second globally in 第三方模型接口 usage.
The update
StepFun has announced the official release of the Step 5 Preview model weights, now accessible via Hugging Face and ModelScope. Built on a sparse Mixture of Experts (MoE) architecture, the model comprises 600 billion total parameters while activating only 27 billion during inference, ensuring computational efficiency. It supports a context window of one million tokens and natively processes both text and visual inputs. In practical applications, Step 5 Preview excels in long-horizon agent tasks such as AI coding and financial analysis. Currently, it ranks second globally in call volume on 第三方模型接口, reflecting significant market interest and application potential.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 阶跃StepFunSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.