Model Detail
StepFun: Step 5 Preview
—StepFun: Step 5 Preview is a multimodal model released by Stepfun. And supports text+image+video->text inputs.
StepFun: Step 5 Preview is priced at $1/M input tokens and $2.7/M output tokens. Operationally the model offers a 1000K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. Pricing in this range is the working middle of the API market — neither the cheapest nor the most expensive option per token, so cost-fit is usually a function of how much output you generate.
StepFun: Step 5 Preview is published on Hugging Face but our pipeline has not yet captured architecture, license, or parameter-count metadata for this entry. The data is refreshed daily, so these fields typically populate within 24–48 hours of release.
StepFun: Step 5 Preview is best fit for mixed text-and-image reasoning tasks such as document understanding, and long-context tasks such as full-codebase analysis or book-length summarization (1000K tokens). Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLMs
arXiv:2607.18915v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), modern systems not only possess strong foundational capabilities and extensive knowledge, but can also solve complex problems via long, multi-step reasoning. However, as reasoning traces b
Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference
arXiv:2610.21657v1 Announce Type: cross Abstract: Flow matching has emerged as a powerful generative family for simulation-based inference (SBI). However, sampling and density evaluation require numerical integration at inference time. This makes posterior sampling in neural posterior estimation cos
Noise-Space Reward Alignment for Few-Step Generative Models
arXiv:2610.21125v1 Announce Type: new Abstract: Few-step generative models produce high-quality samples in one or a few evaluations. However, steering them toward desired properties remains difficult, especially when only black-box reward evaluations are available. While one could apply approaches d
Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
arXiv:2607.04528v3 Announce Type: replace Abstract: Software agents are becoming increasingly important in modern coding workflows, where they solve complex tasks through multi-step interaction with code repositories. A central component of these systems is the execution harness, which governs how t
InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
arXiv:2603.23463v3 Announce Type: replace-cross Abstract: Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-to-image models offer faster generation, but naively applying them to inpainting yields poor harmoni
Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization
arXiv:2610.21063v1 Announce Type: cross Abstract: AI agents now pause for approval before they send money, delete files or email outsiders, and that approval is usually treated as a second factor. We argue it is one only when compromising the agent cannot produce it and when it names exactly what it
