Cracked AI Engineering

GPT-OSS-120B

Nvidia

The GPT-OSS-120B AI model by Nvidia offers developers a powerful tool with a context window of 128,000 tokens and advanced reasoning capabilities. Ideal for text input tasks, this model provides an output limit of 8,192 tokens and is available at a competitive pricing of $0/M input and $0/M output tokens. With a training data cutoff of 2025-08, this model is perfect for a wide range of applications requiring large-scale language processing.

Key Specifications

Context Window

128K tokens

Max Output Tokens

8K tokens

Input Pricing

Free

per million tokens

Output Pricing

Free

per million tokens

Capabilities

  • Text Generation
  • Advanced Reasoning
  • File Attachments

Additional Details

Provider
Nvidia
Release Date
August 4, 2025
Advanced Reasoning
Supported
Supported Input Types
text

Compare with Similar Models