NVIDIA Free NIM API Access

Summary

This note provides a comprehensive guide on using the free NVIDIA Inference Microservices (NIM) API, covering account setup, model access, and rate limits. It also includes specific instructions on how to integrate these NVIDIA models into LiteLLM using environment variables or a proxy server configuration.

Concepts

• nvidia-inference-microservices
• litellm-router
• docker
• docker-compose
• nvidia-nim
• litellm
• postgres
• cloudflare-tunnel

Source Info

• Quality: high
• Raw file: raw/LiteLLM/NVIDIA Free NIM API Access.md
• Ingested: 2026-08-02
• URL: https://grok.com/c/410a198d-006d-4e19-9ca3-5f72b33eb16d?rid=65b06f22-cbe6-41e5-96f2-489d7911bf7a