BIFROST
DocsAPIProvidersArchitecture
Dashboard
Operational

Nvidia NIM

Llama and other models via NVIDIA NIM API.

Pricing

Free 40 requests per minute on build.nvidia.com.

Models

nvidia/llama-3.3-70b-instruct
meta/llama-3.1-8b-instruct

Capabilities

✓ Text✓ Tools✓ Streaming

Base URL

https://integrate.api.nvidia.com/v1

Configuration

Environment variable:
NVIDIA_API_KEY=nvapi-...

Or configure via dashboard:
Dashboard → Provider Keys → Add Key → nvidia

Example

curl https://api.bifrost.dev/v1/chat/completions \
  -H "Authorization: Bearer $BIFROST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/llama-3.3-70b-instruct",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Setup

  1. Create an account at build.nvidia.com
  2. Navigate to API Keys in your account settings
  3. Generate a new API key
  4. Set the NVIDIA_API_KEY environment variable
  5. Configure the provider in the Bifröst dashboard
← Previous
SambaNova
Next →
Nscale