StepFun logo

Step-3.5-Flash

Multimodal
StepFun

Step 3.5 Flash is a fast and efficient language model by StepFun, optimized for low-latency inference while maintaining strong performance in reasoning, coding, and general knowledge tasks. It offers an excellent balance between speed and quality for production deployments.

Key Specifications

Parameters
196.0B
Context
65.5K
Release Date
February 1, 2026
Average Score
78.6%

Timeline

Key dates in the model's history
Announcement
February 1, 2026
Last Update
February 12, 2026
Today
October 5, 2026

Technical Specifications

Parameters
196.0B
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)
$0.10
Output (per 1M tokens)
$0.40
Max Input Tokens
65.5K
Max Output Tokens
8.2K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests
SWE-Bench Verified
• Self-reported
74.0%

Other Tests

Specialized benchmarks
AIME 2025
• Self-reported
97.0%
Tau-bench
• Self-reported
88.0%
LiveCodeBench v6
• Self-reported
86.0%
IMO-AnswerBench
• Self-reported
85.0%
BrowseComp
Context Manager • Self-reported
69.0%
Terminal-Bench 2.0
• Self-reported
51.0%

License & Metadata

License
apache-2.0
Announcement Date
February 1, 2026
Last Updated
February 12, 2026

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.