Price Per TokenPrice Per Token
Nvidia
Nvidia
vs
Nvidia
Nvidia

Llama 3.1 Nemotron Ultra 253B v1 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.

Join the Price Per Token Community

Key Takeaways

Llama 3.1 Nemotron Ultra 253B v1 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Has reasoning mode
  • Supports tool calls

Nemotron-3 Super 120B A12B wins:

  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
Price Advantage
Llama 3.1 Nemotron Ultra 253B v1
Benchmark Advantage
Nemotron-3 Super 120B A12B
Context Window
Llama 3.1 Nemotron Ultra 253B v1
Speed
Nemotron-3 Super 120B A12B

Pricing Comparison

Benchmark Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureLlama 3.1 Nemotron Ultra 253B v1Nemotron-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 Ultra 253B v1Nemotron-3 Super 120B A12B
LicenseOpen SourceProprietary
AuthorNvidiaNvidia

Llama 3.1 Nemotron Ultra 253B v1 Modalities

Input
Output

Nemotron-3 Super 120B A12B Modalities

Input
Output

Frequently Asked Questions

Llama 3.1 Nemotron Ultra 253B v1 has cheaper input pricing at $0.00/M tokens. Llama 3.1 Nemotron Ultra 253B v1 has cheaper output pricing at $0.00/M tokens.