ai-nvidia

Name: ai-nvidia
Availability: InStock
Author: enduser123

Route requests to 200+ NVIDIA NIM models via an OpenAI-compatible API.

Updated Apr 26, 2026

Search Tags:#ai #multimodal #streaming #api-gateway #nim #nvidia

Ready to run

npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-nvidia

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ai-nvidia
Source: https://github.com/EndUser123/cc-marketplace/tree/main/plugins/cc-skills-ai-api/skills/ai-nvidia
Command: npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-nvidia

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

NVIDIA NIM unified AI API provides access to 200+ models through a single interface with intelligent routing, streaming, multimodal support, and GPU-accelerated inference. Use this skill when integrating NVIDIA NIM, building multi-model applications, implementing streaming responses, or working with NVIDIA's hosted models.

Core Features & Use Cases

Unified API gateway for 200+ models via OpenAI-compatible interface
Intelligent routing, streaming, multimodal support, and GPU-accelerated inference
Model discovery, health checks, streaming patterns, and production best practices
Use Case: Build multi-model chat apps that switch models transparently and stream responses to users.

Quick Start

Get an API key at build.nvidia.com and start using the NVIDIA NIM OpenAI-compatible API with your preferred SDK.

Frequently Asked Questions about ai-nvidia

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I access NVIDIA NIM models through a single OpenAI-compatible API?▼

NVIDIA NIM provides a unified API gateway to 200+ models using an OpenAI-compatible interface. You can access these models by obtaining an API key from build.nvidia.com and routing requests through your preferred SDK.

What is intelligent routing and how does it work for multi-model chat applications?▼

Intelligent routing in multi-model applications allows transparent model switching and fallback. The unified gateway handles provider and model identifiers, directing requests to the appropriate GPU-accelerated inference endpoint based on your configuration.

Can I implement streaming responses with NVIDIA NIM for real-time chat interfaces?▼

Yes, NVIDIA NIM supports streaming responses for real-time chat applications. The API gateway handles streaming patterns, allowing you to stream model outputs directly to users as they are generated.

Does the NVIDIA NIM unified API support multimodal inputs?▼

Yes, the NVIDIA NIM unified AI API supports multimodal inputs. This allows you to send text, images, and other data formats to the 200+ available models through the single OpenAI-compatible interface.

How do I handle API keys and model discovery for NVIDIA NIM?▼

To handle API keys, obtain credentials from build.nvidia.com. Model discovery is managed through the gateway's routing logic, which identifies available provider and model identifiers to enable fallback and health checks.

What are the limitations when using a unified gateway for GPU-accelerated inference?▼

Limitations of the unified gateway include dependency on API key availability and proper routing configuration. You must manage provider identifiers and health checks to ensure production stability during multi-model fallback scenarios.