​

Rate Limits

The NanoGPT API currently imposes a limit of 25 requests per second. If you need a higher limit than this reach out to us at support@nano-gpt.com and let us know what model(s) and roughly what capacity you would need.

If your usecase requires more than 1 billion tokens daily of a specific model, reach out to us at support@nano-gpt.com. It should be no problem, but we might be able to offer a discount.

If rate limits are implemented in the future, this documentation will be updated accordingly.