Price Per TokenPrice Per Token
Meta-llama
Meta-llama
vs
OpenAI
OpenAI

Llama 3.3 70B Instruct vs GPT-OSS-20b

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 3.3 70B Instruct wins:

  • No clear advantages in compared metrics

GPT-OSS-20b wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Supports vision
  • Has reasoning mode
Price Advantage
GPT-OSS-20b
Benchmark Advantage
GPT-OSS-20b
Context Window
GPT-OSS-20b
Speed
GPT-OSS-20b

Pricing Comparison

Benchmark Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureLlama 3.3 70B InstructGPT-OSS-20b
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyLlama 3.3 70B InstructGPT-OSS-20b
LicenseOpen SourceOpen Source
AuthorMeta-llamaOpenAI
ReleasedDec 2024Aug 2025

Llama 3.3 70B Instruct Modalities

Input
text
Output
text

GPT-OSS-20b Modalities

Input
text
Output
text

Frequently Asked Questions

GPT-OSS-20b has cheaper input pricing at $0.03/M tokens. GPT-OSS-20b has cheaper output pricing at $0.10/M tokens.
GPT-OSS-20b scores higher on coding benchmarks with a score of 18.5, compared to Llama 3.3 70B Instruct's score of 10.7.
Llama 3.3 70B Instruct has a 131,072 token context window, while GPT-OSS-20b has a 131,072 token context window.
Llama 3.3 70B Instruct does not support vision. GPT-OSS-20b supports vision.