Last refreshed 2026-06-29. Next refresh: weekly.
Why use Step 3.7 Flash on NVIDIA NIM?
NVIDIA NIM offers Step 3.7 Flash with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Step 3.7 Flash across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: step-3.7-flashstep-3.7-flashRequest example
step-3.7-flash.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare Step 3.7 Flash Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| StepFun | $0.20 | $1.15 |
| OpenRouter | $0.20 | $1.15 |
| NVIDIA NIM | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Image input | $1.00 |
| Video input | $1.00 |
Capabilities
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.