Navigation
NVIDIA NIM
DirectOptimized inference containers for NVIDIA GPUs. Enterprise-grade performance.
5Models
2Plans
Provider Info
"API Env Var"
NVIDIA_API_KEY
"Rate Limits"
~40 RPM
"Available Models (5)"
Llama 3.3 70B
Mistral Large
Qwen 3 235B
Gemma 3 12B
Nemotron 3 8B
Subscription Plans
"Free Tier Available"
~40 RPM, no credit card required — No credit card required