All Models

Step 3.5 Flash

Reasoning Tool Calling Open Weights

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.

Providers 5
Released Jan 29, 2026
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

37.8
Intelligence Index
31.6
Coding Index

Available Providers (5)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Nvidia stepfun-ai/step-3.5-flash $0.00/MTok $0.00/MTok 256K 16.4K
StepFun step-3.5-flash $0.10/MTok $0.29/MTok 256K 256K
ZenMux stepfun/step-3.5-flash $0.10/MTok $0.30/MTok 256K 64K
OpenRouter stepfun/step-3.5-flash $0.10/MTok $0.30/MTok 256K 256K
NanoGPT stepfun-ai/step-3.5-flash $0.20/MTok $0.50/MTok 256K 256K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output