Skip to main content

​
NVIDIA

NVIDIA provides an OpenAI-compatible API at https://integrate.api.nvidia.com/v1 for Nemotron and NeMo models. Authenticate with an API key from NVIDIA NGC.

​
CLI setup

Export the key once, then run onboarding and set an NVIDIA model: 
export NVIDIA_API_KEY="nvapi-..."
openclaw onboard --auth-choice skip
openclaw models set nvidia/nvidia/llama-3.1-nemotron-70b-instruct
If you still pass --token, remember it lands in shell history and ps output; prefer the env var when possible.

​
Config snippet

{
  env: { NVIDIA_API_KEY: "nvapi-..." },
  models: {
    providers: {
      nvidia: {
        baseUrl: "https://integrate.api.nvidia.com/v1",
        api: "openai-completions",
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "nvidia/nvidia/llama-3.1-nemotron-70b-instruct" },
    },
  },
}

​
Model IDs

Model refNameContextMax output
nvidia/nvidia/llama-3.1-nemotron-70b-instructNVIDIA Llama 3.1 Nemotron 70B Instruct131,0724,096
nvidia/meta/llama-3.3-70b-instructMeta Llama 3.3 70B Instruct131,0724,096
nvidia/nvidia/mistral-nemo-minitron-8b-8k-instructNVIDIA Mistral NeMo Minitron 8B Instruct8,1922,048

​
Notes

  • OpenAI-compatible /v1 endpoint; use an API key from NVIDIA NGC.
  • Provider auto-enables when NVIDIA_API_KEY is set.
  • The bundled catalog is static; costs default to 0 in source.