All AI models · LLM benchmarks · Methodology

NVIDIA

Nemotron 70b

Nemotron model for efficient reasoning, coding, and specialized AI agents

Model facts

Context window
16K tokens
Maximum output
8K tokens
Cheapest paid input
$0.357 per 1M tokens
Cheapest paid output
$0.408 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.357 input / $0.408 output per 1M tokens

API providers

  • NanoGPT (Nvidia) — model id nvidia/Llama-3.1-Nemotron-70B-Instruct-HF; $0.357 input / $0.408 output per 1M tokens; provider documentation