← LLM Directory
NVIDIA
LLM ProviderNVIDIA NIM inference platform. Hosts and serves popular open-weight models at scale.
Flagship1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Nemotron 3 Ultra 253B NVIDIA's flagship MoE model. 253B params, 55B active. | $0.800 | $2.40 | 131K |
Hosted4 models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Llama 3.3 70B (NIM) Meta's Llama 3.3 70B served via NVIDIA NIM. | $0.700 | $0.700 | 131K |
DeepSeek R1 (NIM) DeepSeek R1 reasoning model served via NIM. | $0.880 | $3.52 | 131K |
Qwen 2.5 72B (NIM) Qwen 2.5 72B served via NVIDIA NIM. | $0.700 | $0.700 | 131K |
Mistral Small (NIM) Mistral Small served via NVIDIA NIM. | $0.200 | $0.200 | 131K |