This model is 22 months old. The same company has since released something newer: NVIDIA Nemotron 3.5 Lightning 30B-A3B (BF16) (2026-08-11). The details below are still accurate for this model — it just is not what we would recommend today.
Llama 3.1 Nemotron 70B Instruct
NVIDIA🇺🇸 United States
Context window128K tokens
Input / 1M tokens$0.2
Output / 1M tokens$0.2
Version History
1.0major
Nvidia released Llama 3.1 Nemotron 70B Instruct, an instruction-tuned variant of Meta's Llama 3.1 70B model optimized for developer applications.