Step 3.7 Flash
Step 3.7 Flash is StepFun's language model with a 256K context window, available from 2 providers, starting at $0.2 / 1M input and $1.15 / 1M output. A high-efficiency multimodal Mixture-of-Experts LLM combining a large language backbone with a vision encoder for native image and video understanding.
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video✓
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.2 | $1.15 | $0.04 | |
| $0.2 | $1.15 | $0.04 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Step 3.7 Flash, ranked by cheapest on-demand price. The model needs about 483 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| p4de.24xlarge |  AWS | 8× A100 | 640 GB | $27.45/hr | us-east-1 | |
| Standard_ND96amsr_A100_v4 |  Azure | 8× NVIDIA A100 (80GB) | 640 GB | $32.77/hr | westus2 | |
| g7e.48xlarge | AWS | 8× RTX PRO Server 6000 | 768 GB | $33.14/hr | us-east-1 | |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Step 3 VL 10B | — | — | — | — | — |
| Step Image Edit 2 | — | — | — | — | — |
| Step 1X Edit 1.2 | — | — | — | — | — |
| Step 1X Edit | — | — | — | — | — |