How to hit the NVIDIA NIM (build.nvidia.com) API

NVIDIA hosts models from build.nvidia.com behind an OpenAI-compatible API at https://integrate.api.nvidia.com/v1, including its own Nemotron family. The model list is public.

Authentication

Create a key at build.nvidia.com. Send it as Authorization: Bearer <key>. Listing models needs no key. In the examples it's written {{NVIDIA_API_KEY}}.

Full reference: https://docs.api.nvidia.com/nim/reference/llm-apis

List models

No key needed.

curl https://integrate.api.nvidia.com/v1/models
Run in PostTaco
Example response (trimmed) 
{
  "object": "list",
  "data": [
    {
      "id": "01-ai/yi-large",
      "object": "model",
      "created": 735790403,
      "owned_by": "01-ai"
    },
    {
      "id": "adept/fuyu-8b",
      "object": "model",
      "created": 735790403,
      "owned_by": "adept"
    }
  ]
}

Chat with Nemotron 3 Super

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer {{NVIDIA_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3-super-120b-a12b", "messages": [{"role": "user", "content": "Explain what an API rate limit is in two sentences."}]}'
Run in PostTaco

Chat with Nemotron 3 Ultra

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer {{NVIDIA_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3-ultra-550b-a55b", "messages": [{"role": "user", "content": "What is a Mixture-of-Experts model?"}]}'
Run in PostTaco

Chat with Nemotron 3.5 Lightning

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer {{NVIDIA_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3.5-lightning-30b-a3b", "messages": [{"role": "user", "content": "Give me three names for a taco truck."}]}'
Run in PostTaco