OpenAI GPT OSS 120B
text-to-text
Built with a Mixture-of-Experts design, delivers efficient, transparent reasoning, tool use, and agentic capabilities, even with 128K token context windows.
Model Parameters
Advanced settings to control the behavior of the model.
Controls randomness: 0 = deterministic, 2 = very creative
Maximum length of the response (1-128000 tokens)
OpenAI GPT OSS 120B
Log in to chat with any model.