Step 5 Preview is a flagship foundation model designed for real-world Agentic tasks. Step 5 Preview achieves frontier-level performance in AI programming, software engineering, and professional knowledge work, with particularly outstanding capabilities in the financial domain. It uses a sparse MoE architecture with 600B total parameters, activating 27B parameters per token, supporting a 1M token context window and visual input.
Inference Service Provider
The inference service provider for stepfun/step-5-preview is StepFun.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Supported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1048576 | Max Output Length | 1048576 |
Context Window | 1048576 | Max Input Length (Thinking Mode) | 1048576 |
Max Output Length (Thinking Mode) | 1048576 | Max Chain-of-Thought Length | 1048576 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Input | 7 | Per 1M tokens |
Output | 20 | Per 1M tokens |
Input(Implicit Cache) | 0.35 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 500 |
TPM (Tokens Per Minute) | 10,000,000 |