NVIDIA Integration - Autohand Docs

Q: How do I configure the Autohand NVIDIA integration?

Set NVIDIA_API_KEY, select the nvidia provider, and choose a model ID available to the NVIDIA account.

Quick answer

What is the Autohand NVIDIA integration?

The Autohand NVIDIA integration connects the coding agent to NVIDIA-hosted models through an OpenAI-compatible inference endpoint. It uses an NVIDIA API key and an account-supported model identifier.

Status: Available
Requires: An NVIDIA API key and access to the selected hosted model.
Configure with: Set NVIDIA_API_KEY, select the nvidia provider, and choose a model ID available to the NVIDIA account.
Best for: Hosted model inference through NVIDIA services.

Know before you start: The available catalog, quotas, endpoints, and model behavior depend on the current NVIDIA account and service.

Overview

NVIDIA is available as the nvidia provider. Use it when your team wants NVIDIA-hosted model access, GPU-backed inference infrastructure, or a provider catalog that includes NVIDIA, Mistral, DeepSeek, and related model families.

Setup

export NVIDIA_API_KEY="your-nvidia-api-key"

autohand --provider nvidia --model deepseek-ai/deepseek-v4-pro

CLI configuration

{
  "provider": "nvidia",
  "nvidia": {
    "apiKey": "${NVIDIA_API_KEY}",
    "baseUrl": "https://integrate.api.nvidia.com/v1",
    "model": "deepseek-ai/deepseek-v4-pro"
  }
}

Option	Description	Default
`apiKey`	Your NVIDIA API key	-
`baseUrl`	NVIDIA inference endpoint	`https://integrate.api.nvidia.com/v1`
`model`	NVIDIA-hosted model ID	`deepseek-ai/deepseek-v4-pro`

Models

Select NVIDIA-hosted models with /model or configure a custom model ID from your NVIDIA account.

Example model	Best for
`deepseek-ai/deepseek-v4-pro`	Advanced coding and reasoning
`mistralai/mixtral-8x7b-instruct-v0.1`	General-purpose instruction following
`nvidia/usdcode`	NVIDIA-specific coding and content workflows

Common questions

NVIDIA integration FAQ

How do I configure the Autohand NVIDIA integration?

Set NVIDIA_API_KEY, select the nvidia provider, and choose a model ID available to the NVIDIA account.

What does the Autohand NVIDIA integration require?

An NVIDIA API key and access to the selected hosted model.

What limitations should I know about?

The available catalog, quotas, endpoints, and model behavior depend on the current NVIDIA account and service.