gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Developer
OpenAI
Release Date
August 5, 2025
Context Window
131,072 tokens≈ 175 words
API Access
Publicly AvailableIntegrate via official API
Input Cost
$0.03per million tokens
Output Cost
$0.15per million tokens
SHARE MODEL:
Vetted Benchmarks
No recorded benchmark scores available for this model.
How does this model compare?
Evaluate benchmark standing and performance rankings vs all other tracked models.