What are the rate limits for the models?

[bytexenon]

Select Topic Area

Question

Body

If I understand correctly, the current rate limit for the o1-preview model is about ~2 prompts per hour, is there any official list for the rate limits of the other models?

[ShawnFumo]

I see this, though it isn't clear if it is per user or combined for the business/enterprise tiers: https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits