Nvidia
Nvidia
vs
Nvidia
Nvidia

Llama 3.1 Nemotron 70B Instruct vs Nemotron 3 Super 120B A12B

A detailed comparison of pricing, benchmarks, and capabilities

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Llama 3.1 Nemotron 70B Instruct wins:

  • No clear advantages in compared metrics

Nemotron 3 Super 120B A12B wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
Price Advantage
Nemotron 3 Super 120B A12B
Benchmark Advantage
Llama 3.1 Nemotron 70B Instruct
Context Window
Nemotron 3 Super 120B A12B
Speed
N/A

Pricing Comparison

Benchmark Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureLlama 3.1 Nemotron 70B InstructNemotron 3 Super 120B A12B
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyLlama 3.1 Nemotron 70B InstructNemotron 3 Super 120B A12B
LicenseProprietaryOpen Source
AuthorNvidiaNvidia
ReleasedOct 2024Mar 2026

Llama 3.1 Nemotron 70B Instruct Modalities

Input
text
Output
text

Nemotron 3 Super 120B A12B Modalities

Input
text
Output
text

Frequently Asked Questions

Nemotron 3 Super 120B A12B has cheaper input pricing at $0.07/M tokens. Nemotron 3 Super 120B A12B has cheaper output pricing at $0.40/M tokens.
Llama 3.1 Nemotron 70B Instruct has a 131,072 token context window, while Nemotron 3 Super 120B A12B has a 1,000,000 token context window.