← LLM Directory
NVIDIA

NVIDIA

LLM Provider

NVIDIA NIM inference platform. Hosts and serves popular open-weight models at scale.

Flagship1 model

ModelInput / 1MOutput / 1MContext
Nemotron 3 Ultra 253B
NVIDIA's flagship MoE model. 253B params, 55B active.
$0.800$2.40131K

Hosted4 models

ModelInput / 1MOutput / 1MContext
Llama 3.3 70B (NIM)
Meta's Llama 3.3 70B served via NVIDIA NIM.
$0.700$0.700131K
DeepSeek R1 (NIM)
DeepSeek R1 reasoning model served via NIM.
$0.880$3.52131K
Qwen 2.5 72B (NIM)
Qwen 2.5 72B served via NVIDIA NIM.
$0.700$0.700131K
Mistral Small (NIM)
Mistral Small served via NVIDIA NIM.
$0.200$0.200131K

Other Providers