Nvidia Nemotron 70b by NanoGPT — Specs, Pricing & Capabilities | whichllm

Model ID nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Provider NanoGPT

Family nemotron

Status -

Knowledge Cutoff -

Release Date 2025-04-15

Input Modalities text

Output Modalities text

Context Window 16384

Input Limit 16384

Output Limit 8192

Tool Calling No

Reasoning No

Structured Output No

Temperature Control -

Open Weights No

Input Cost / 1M tokens $0.36

Output Cost / 1M tokens $0.41

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -