LLM Reference
NVIDIA NIM

Using Step 3.7 Flash on NVIDIA NIM

Implementation guide · Step · StepFun

Provisioned

NVIDIA NIM exposes Step 3.7 Flash through model ID step-3.7-flash. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call step-3.7-flash — see the documentation for request format.

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

TypePrice (per 1M)
Image input$1.00
Video input$1.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt Caching

About Step 3.7 Flash

Step 3.7 Flash is StepFun's open-weights multimodal Mixture-of-Experts model for agentic coding, tool use, long-context reasoning, image understanding, and video understanding. It combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder, activates about 11B parameters per token, supports a 256K-token context window, and exposes low, medium, and high reasoning levels for speed/depth tradeoffs. StepFun reports leading open-model results on ClawEval-1.1, SimpleVQA with Search, and SWE-bench Pro at launch. Weights are available on Hugging Face under Apache 2.0.

Model Specs

Released2026-05-29
Parameters198B (11B active)
Context256k
ArchitectureMixture of Experts

Provider

NVIDIA NIM
NVIDIA NIM

NVIDIA

Santa Clara, California, United States