I got Rate limit error while accessing the gpt-5-mini using API calls.

Question

I got Rate limit error while accessing the gpt-5-mini using API calls.

Sen0299 120

Hi, I got below error. How to increase this limit in Azure portal for this model ?

RateLimitError: Error code: 429 - {'error': {'message': 'Your requests to gpt-5-mini for gpt-5-mini in eastus2 have exceeded rate limit.', 'type': 'too_many_requests', 'param': None, 'code': 'rate_limit_exceeded'}}

0 comments

Answer accepted by question author

0 additional answers

Your answer

Answer 1

@Sen0299 I hope you are doing well,

Welcome to Microsoft Q&A,

The 429 rate_limit_exceeded error means the deployment has reached its configured throughput limit.For standard deployments, Azure OpenAI quota is allocated in Tokens Per Minute (TPM), and the corresponding Requests Per Minute (RPM) limit is derived from that allocation. You can increase the allocation from the Microsoft Foundry portal:

Manage → Quota → Token per minute → select the deployment → Request Quota https://learn.microsoft.com/en-us/answers/questions/2243296/how-to-increase-tokens-per-day-quota-limit

User's image

You can also reduce TPM allocated to another deployment of the same model/region if unused quota is available.

Microsoft documents this here: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/quota

Also consider implementing retry/backoff for 429 responses rather than immediately retrying requests.

If this answer helped clarify the platform capabilities and save you troubleshooting time, please consider marking it as Accepted. This helps others in the community find similar solutions.