Nemotron-4 340B and Llama-3.1-Nemotron-70B: synthetic data generation, reward modeling, and enterprise alignment engines optimized with TensorRT-LLM.
2 models tracked · cheapest input: NVIDIA Llama 3.1 Nemotron 70B at $0.35/M · official pricing page
nvidia/nemotron-4-340b-instruct
Input /M
$1.50
Output /M
$3.00
Context
128K
NVIDIA's flagship synthetic data generation and reward modeling engine optimized with TensorRT-LLM at $1.50/$3.00.
nvidia/llama-3.1-nemotron-70b-instruct
Input /M
$0.35
Output /M
$0.70
Context
128K
NVIDIA-aligned high-precision model scoring at the top of Chatbot Arena for open-weight 70B tiers at $0.35/$0.70.
Other providers
All NVIDIA NIM prices verified Aug 19, 2026. Prices change frequently — each model page links to the authoritative source.