A agentindex
Tools · LLM provider

NVIDIA NIM

NVIDIA's inference microservices for hosting open and frontier models.

Visit site
Proprietary Self-hostable freemium
LLM provider
In these stacks
Write code with AIBuild my own agent
LicenseProprietary
PriceFree tier
UsageMetered
Model supportmulti
Languages—
GitHub stars—
Last activity—
Verified2026-06-28
Verified byseed

NVIDIA's inference microservice platform serving the Nemotron model family, Llama, Mistral, and hundreds of open models via optimized NIM containers, with a free tier on build.nvidia.com and self-hostable containers for enterprise.

Strengths

  • Optimized inference on NVIDIA GPUs with NIM containers
  • Hosts Nemotron and the broadest catalog of open models
  • Self-hostable for regulated or air-gapped environments

Tradeoffs

  • NVIDIA GPU required for best performance
  • Proprietary serving layer

Covers

Self-hosting

Compare with