Author's Description
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Step 3.7 Flash, StepFun's 196B-parameter multimodal Mixture-of-Experts model, demonstrates exceptional performance across several key metrics. It consistently ranks among the fastest models available, achieving an Infinityth percentile in speed across eight benchmarks. Furthermore, its pricing is highly competitive, placing it in the 86th percentile across six benchmarks. The model exhibits outstanding reliability with a 98% success rate, indicating minimal technical failures. Analysis of benchmark results reveals significant strengths in several areas. Step 3.7 Flash achieved perfect accuracy in General Knowledge, Email Classification, Reasoning, Ethics, and Mathematics, often being the most accurate model at its price point and speed. Notably, it was the #1 model in accuracy for Mathematics, showcasing an excellent accuracy-to-cost ratio. Its Coding performance is solid at 85.7% accuracy. However, the model exhibits critical weaknesses in Hallucinations and Instruction Following, scoring 0.0% accuracy in both. This indicates a significant challenge in acknowledging uncertainty and precisely adhering to complex instructions.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.2 |
| Completion | $1.15 |
| Input Cache Read | $0.04 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
StepFun
|
StepFun | stepfun/step-3.7-flash-20260528 | 256K | $0.2 / 1M tokens | $1.15 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by stepfun
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| StepFun: Step 3.7 Flash | May 28, 2026 | ~196B | 256K |
Video input
Image input
Text input
Text output
|
★★★★ | ★★★★★ | $$$ |
| StepFun: Step 3.5 Flash | Jan 29, 2026 | ~196B | 256K |
Text input
Text output
|
★★★ | ★★★★★ | $$$ |