Model Comparison
Step-3.5-Flash
vs
gpt-oss-120b
Feb 15, 2026
Pricing
Input
$
0.1
/ M Tokens
$
0.05
/ M Tokens
Output
$
0.3
/ M Tokens
$
0.45
/ M Tokens
Metadata
Create on
Feb 1, 2026
Aug 4, 2025
License
APACHE 2.0
APACHE-2.0
Provider
StepFun
OpenAI
Specification
State
Available
Available
Architecture
Sparse Mixture-of-Experts (MoE) transformer architecture
Mixture of Experts
Calibrated
No
Yes
Mixture of Experts
Yes
Yes
Total Parameters
196B
120B
Activated Parameters
11B
5.1B
Reasoning
No
No
Precision
FP8
FP8
Context length
262K
131K
Max Tokens
66K
8K
Supported Functionality
Serverless
Supported
Supported
Serverless LoRA
Not supported
Not supported
Fine-tuning
Not supported
Not supported
Embeddings
Not supported
Not supported
Rerankers
Not supported
Not supported
Support image input
Not supported
Not supported
JSON Mode
Not supported
Supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Not supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Supported
Not supported
Step-3.5-Flash in Comparison
See how Step-3.5-Flash compares with other popular models across key dimensions.
