# What should I do when I meet rate limit?
**URL:**
**Author:**  [@fifane](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ffifane)%5C
**Post date:** [November 23, 2023, 5:45am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-should-i-do-when-i-meet-rate-limit%2F63239%2F1 "2023-11-23T05:45:03Z")
{‘error’: [{‘message’: ‘update vector: failed with status: 429 error: Rate limit reached. You reached PRO hourly usage limit. Use Inference Endpoints (dedicated) to scale your endpoint.’}]}
What should I do when I meet rate limit reached?
---
**Author:**  [@Culture-and-Morality](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FCulture-and-Morality)%5C
**Post date:** [July 7, 2024, 12:49am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-should-i-do-when-i-meet-rate-limit%2F63239%2F2 "2024-07-07T00:49:39Z")
Did you find any response?
---
**Author:**  [@fifane](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ffifane)%5C
**Post date:** [July 7, 2024, 3:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-should-i-do-when-i-meet-rate-limit%2F63239%2F3 "2024-07-07T03:22:26Z")
I solved this problem long ago. thanks
---
**Author:**  [@meganariley](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmeganariley)%5C
**Post date:** [July 9, 2024, 9:20pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-should-i-do-when-i-meet-rate-limit%2F63239%2F4 "2024-07-09T21:20:59Z")
Hi @Culture-and-Morality Thanks for posting! The free Inference API is a solution to easily explore and evaluate models, and Inference Endpoints is our new paid inference solution for production use cases. So for larger volumes of requests, or if you need guaranteed latency/performance, we recommend using [Inference Endpoints](https://huggingface.co/inference-endpoints) instead to easily [deploy your models](https://ui.endpoints.huggingface.co/new) on dedicated, fully-managed infrastructure. Inference Endpoints will give you the flexibility to quickly create endpoints on CPU or GPU resources, and is billed by compute uptime vs character usage. Further pricing information can be found [here](https://huggingface.co/docs/inference-endpoints/pricing).
Please let me know if you have additional questions. 🤗