StepFun
StepFun: Step 3.5 Flash
stepfun/step-3.5-flash
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.
Input
$0.1
/ 1M tokens
Output
$0.3
/ 1M tokens
Context window
262.14K
tokens
Limits
Context
262,144
tokens
Max output
65,536
25% of the context window
Parameters
199,384,301,376
Model facts
Author
StepFun
Tokenizer
Other
Modality
Text -> Text
License
Apache-2.0
Created
Jan 29, 2026
Hugging Face
stepfun-ai/Step-3.5-Flash
Reasoning
Required
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyInclude reasoningMax tokensReasoningTemperatureTool choiceToolsTop kTop p
Capability scores
17
Intelligence index
Better than 43% of models compared