NVIDIA NIM API key setup
Optimized inference containers for NVIDIA GPUs. Enterprise-grade performance.
Get your key
- Open the NVIDIA NIM API keys page: build.nvidia.com/
- Create an account and generate an API key.
- Paste it into the Dracon BYOK provider keys — stored encrypted (AES-256-GCM), used browser-direct, works in every Dracon tool.
Free tier
Yes. Free endpoint, no credit card. Current featured models rotate — check the provider's pricing page for the current model list and context. no credit card required
Rate limits: ~40 RPM
Connection details
- Base URL
https://integrate.api.nvidia.com/v1- API shape
- OpenAI-compatible
- Env var
NVIDIA_API_KEY- Models
- meta/llama-3.3-70b-instruct, deepseek-ai/deepseek-v3.1
- Model lineup
- Llama 3.3 70B, Mistral Large, Qwen 3 235B, Gemma 3 12B, Nemotron 3 8B
Gotchas
Browser-direct blocked: the live /models and /chat/completions responses omit Access-Control-Allow-Origin for the Dracon origin (verified 2026-08-24). Use this key from a non-browser client or Router export.
Our verdicts on this kind of provider
Independent comparisons we keep current as pricing and free tiers shift. A guide is setup; a verdict is whether it's worth setting up.