Step-3.5-Flash
About 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 with 196B total parameters and only 11B activated per token. It supports a 262K context window and achieves 100-300 tok/s generation throughput via 3-way Multi-Token Prediction (MTP-3). The model excels at coding and agentic tasks, achieving 74.4% on SWE-bench Verified and 51.0% on Terminal-Bench 2.0
Available Serverless
Run queries immediately, pay only for usage
$
0.1
/
$
0.3
Per 1M Tokens (input/output)
Metadata
Specification
State
Available
Architecture
Sparse Mixture-of-Experts (MoE) transformer architecture
Calibrated
No
Mixture of Experts
Yes
Total Parameters
196B
Activated Parameters
11B
Reasoning
No
Precision
FP8
Context length
262K
Max Tokens
66K
Supported Functionality
Serverless
Supported
Serverless LoRA
Not supported
Fine-tuning
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported
JSON Mode
Not supported
Structured Outputs
Not supported
Tools
Supported
Fim Completion
Not supported
Chat Prefix Completion
Supported
Compare with Other Models
See how this model stacks up against others.
