Nvidia
Nvidia
vs
Nvidia
Nvidia

Llama 3.3 Nemotron Super 49B V1.5 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 3.3 Nemotron Super 49B V1.5 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Has reasoning mode
  • Supports tool calls

Nemotron-3 Super 120B A12B wins:

  • Larger context window
Price Advantage
Llama 3.3 Nemotron Super 49B V1.5
Benchmark Advantage
Llama 3.3 Nemotron Super 49B V1.5
Context Window
Nemotron-3 Super 120B A12B
Speed
N/A

Pricing Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureLlama 3.3 Nemotron Super 49B V1.5Nemotron-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 3.3 Nemotron Super 49B V1.5Nemotron-3 Super 120B A12B
LicenseProprietaryProprietary
AuthorNvidiaNvidia
ReleasedOct 2025Unknown

Llama 3.3 Nemotron Super 49B V1.5 Modalities

Input
text
Output
text

Nemotron-3 Super 120B A12B Modalities

Input
Output

Related Comparisons

Frequently Asked Questions

Llama 3.3 Nemotron Super 49B V1.5 has cheaper input pricing at $0.00/M tokens. Llama 3.3 Nemotron Super 49B V1.5 has cheaper output pricing at $0.00/M tokens.
Llama 3.3 Nemotron Super 49B V1.5 has a 131,072 token context window, while Nemotron-3 Super 120B A12B has a 262,144 token context window.