StepFun: Step 3.5 Flash

Text input Text output Free Option
Author's Description

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.

Key Specifications
Cost
$$
Context
256K
Parameters
196B (Rumoured)
Released
Jan 29, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Reasoning Top P Frequency Penalty Max Tokens Include Reasoning Stop Temperature
Features

This model supports the following features:

Reasoning Tools
Performance Summary

Step 3.5 Flash, StepFun's open-source foundation model, demonstrates exceptional performance across a wide range of benchmarks. Leveraging a sparse Mixture of Experts (MoE) architecture, it efficiently activates 11B of its 196B parameters, contributing to its impressive speed. The model consistently performs among the fastest, ranking in the 77th percentile for speed across eight benchmarks. Furthermore, it offers highly competitive pricing, placing in the 86th percentile. Reliability is a standout feature, with Step 3.5 Flash achieving a perfect 100% success rate across all evaluated benchmarks, indicating minimal technical failures. Across all eight benchmark categories—Hallucinations, Instruction Following, Coding, General Knowledge, Email Classification, Reasoning, Ethics, and Mathematics—Step 3.5 Flash achieved a perfect 100% accuracy. This remarkable consistency highlights its robust capabilities in diverse tasks, from complex reasoning and coding to nuanced instruction following and ethical considerations. Its key strengths lie in its unparalleled accuracy across all tested domains, combined with its speed efficiency and cost-effectiveness. The model exhibits no notable weaknesses based on the provided benchmark data, consistently delivering top-tier results in accuracy, often at competitive price points and impressive speeds.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.1
Completion $0.3
Input Cache Read $0.02

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
StepFun
StepFun | stepfun/step-3.5-flash 256K $0.1 / 1M tokens $0.3 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration