Playground

GPT-OSS 120B

Model Type

Select a model

Parameters

Fine-tune generation settings for each model.

Generation Controls

Temperature

00.72

Lower values yield focused, deterministic responses.

Max Tokens

18192131072

Controls the length of each assistant response.

Reasoning effort

GPT-OSS 120B

Temperature: 0.7Max tokens: 8192

Start a conversation to explore the model behavior.