o1-2024-12-17

Key Metrics

Sample API Code

Not specified

Notes

Snapshot version of the o1 model, corresponding to the state on 2024-12-17. Currently aliased by 'o1'. Previous full o-series reasoning model. The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. Reasoning token support.