Skip to content
Step Fun

Step 3.5 Flash 196B

flagship
Step Fun · released 2025-08-01 · text
currently routing · 4.2k rpm
128M tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
proprietary
License
/ ABOUT

Step 3.5 Flash 196B is a fast and efficient language model from StepFun (formerly StepFun/Step), featuring 196 billion parameters and optimized for high-throughput inference. The Flash designation indicates it's designed for speed, providing strong quality with reduced latency compared to the full Step model.

The model handles general language tasks including chat, reasoning, coding, and multilingual generation, with particular strength in Chinese language applications. It supports a large context window suitable for processing long documents and complex multi-turn conversations.

Step 3.5 Flash is recommended for production applications needing a balance of quality and speed, serving as the efficient option in StepFun's model lineup.

BENCHMARKS Artificial Analysis Index
Intelligence 38

Providers for Step 3.5 Flash 196B

1 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
bf16
0.00%