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:

  • Supports tool calls

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
LicenseProprietaryProprietary
AuthorNvidiaNvidia
ReleasedOct 2024Unknown

Llama 3.1 Nemotron 70B Instruct Modalities

Input
text
Output
text

Nemotron-3 Super 120B A12B Modalities

Input
Output

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 262,144 token context window.