NVIDIA NIM
NVIDIA NIM hosted inference. Bring your own key; nothing is billed by us.
Den här sidan är skriven på engelska. Termerna den förklarar är de som söks på engelska, och en översatt fackterm är en annan term.
What the harness already knows
| Provider id | nvidia |
| Base URL | https://integrate.api.nvidia.com/v1 |
| Protocol | OpenAI-compatible chat completions |
| API key | NVIDIA_API_KEY |
| Model discovery | Yes — the model list is asked of the endpoint rather than shipped. |
Connecting it
The endpoint above is built in, so there is nothing to configure. Put the key in the environment and the provider appears in the model picker:
export NVIDIA_API_KEY="..."Keys are issued by NVIDIA NIM — where to get one.
Pointing it somewhere else
A regional host, a gateway, or a server of your own. Overrides in ~/.oharness/config.json are field level, so changing the endpoint does not mean restating the rest of the provider — this is the whole block, shown holding the default so the shape is clear:
{
"providers": {
"nvidia": {
"baseUrl": "https://integrate.api.nvidia.com/v1"
}
}
}What you get either way
The same agent loop, the same tools, the same MCP servers and the same permission rules, whichever provider is underneath — and switching between them mid-session converts nothing, because history is never stored in a vendor’s shape. What an agent harness is covers why that is the hard part, and the providers reference covers the catalogue itself.