[QUESTION] openai response: x-ratelimit header values -1 and 0

[hemnaathR]

How can we help?

Hello, im using this library with the System.ClientModel ClientRetryPolicy to retry openai calls that come back with HTTP 429 (Rate Limit Exceeded)

Its been working fine but since circa Thursday last week, the header values coming back from the openai calls are coming back with 0 and -1 values :(
[x-ratelimit-limit-tokens, -1], [x-ratelimit-remaining-tokens, -1], [x-ratelimit-reset-tokens, 0]

x-ratelimit-reset-tokens usually gives me an int in seconds that I wait for before retrying the call. I also noticed the retry-after header is missing. Any help would be appreciated. Thanks!

I'm using an Azure OpenAI resource, Responses API, GPT4.1

[jsquire]

Hi @hemnaathR. Thank you for reaching out and we regret that you're experiencing difficulties. The headers that you're inquiring about are service behaviors and not something that the client has insight into nor influence over. The maintainers of the OpenAI client library are unable to assist.

As you're asking about the Azure OpenAI service, your best path forward would be to open an Azure support request or inquire on the Microsoft Q&A site.