# NVIDIA API key (/docs/providers/nvidia-key)

The NVIDIA API key account answers with a key from NVIDIA. The wallet lists it as NVIDIA under "With an API key", with the id `nvidia-key`.

## What the visitor needs [#what-the-visitor-needs]

An NVIDIA API key. NVIDIA bills the account that owns the key.

## Connect [#connect]

1. The visitor creates an API key in NVIDIA's console, on the account that should pay.
2. In the wallet, the visitor picks NVIDIA under "With an API key".
3. The visitor pastes the key in the "NVIDIA API key" field and presses Connect.

The wallet keeps the key in its encrypted vault, without the spaces around it. It makes no test call, and a wrong key shows up as the provider's error on the first answer. The key has no expiry in the wallet and stays in the vault until the visitor removes the account.

## Models [#models]

The wallet has no model list for NVIDIA. The account answers with `nvidia/nemotron-3.5-super-vl`, and the side panel shows no model buttons for its sites.

## Usage and limits [#usage-and-limits]

The wallet reads `x-ratelimit-remaining-tokens` and `x-ratelimit-limit-tokens` on each answer that carries them. The room left is the remaining tokens divided by the limit. Without these headers, the card keeps saying "Usage shows after the first answer", and Auto ranks the account among the accounts with no reading.

## Calls [#calls]

Answers come from `https://integrate.api.nvidia.com/v1/chat/completions` in the OpenAI chat completions protocol, with the key. All four request options reach NVIDIA.