Azure OpenAI Error 429 - Request Below Rate Limit

I am also facing same issue even if i am running it with Azure Openai studio chat playground.

Same problem here, same region as well. I have also waited the 86400 seconds and the same error still occurs.

Pedro Daniel Scheeffer Pinheiro

I understand that you have limit and still encountering the issue.

To give more context, As each request is received, Azure OpenAI computes an estimated max processed-token count that includes the following:

• Prompt text and count
• The max_tokens parameter setting
• The best_of parameter setting

As requests come into the deployment endpoint, the estimated max-processed-token count is added to a running token count of all requests that is reset each minute. If at any time during that minute, the TPM rate limit value is reached, then further requests will receive a 429 response code until the counter resets. For more details, see Understanding rate limits.

To minimize issues related to rate limits, it's a good idea to use the following techniques:

• Set max_tokens and best_of to the minimum values that serve the needs of your scenario. For example, don’t set a large max-tokens value if you expect your responses to be small.
• Use quota management to increase TPM on deployments with high traffic, and to reduce TPM on deployments with limited needs.
• Implement retry logic in your application.
• Avoid sharp changes in the workload. Increase the workload gradually.
• Test different load increase patterns.

Also, see A Guide to Limits, Quotas, and Best Practices for more details.

Hope this helps. Do let me know if you have any further queries.

Good morning Ashok,

I have the same issue as OP, but as far as I know I only use 1 call to the API. I use API version 2024-05-01-preview and I want to create embeddings via a deployed model.

I use the LangChain library (langchain) and Chroma (langchain-chroma) in Python. This is how I create the embeddings:

self.embedding_function = AzureOpenAIEmbeddings(model="text-embedding-ada-002", api_key=az_creds["key"], azure_endpoint=az_creds["ep"], 
azure_deployment=az_creds["emb_dn"])

chunks: list[Document] = //gets a value somewhere in my code
Chroma.from_documents(chunks, self.embedding_function)

After running this, I still get the 429 from the API, despite only calling it once in my whole application and not calling it anywhere else. I have waited the 86400 seconds (24 hours), but still the same error. Seems like an API issue to me.

The error I get is a slight variation on OP's error though:

openai.RateLimitError: Error code: 429 - {'error': {'code': '429', 'message': 'Requests to the Embeddings_Create Operation under Azure OpenAI API version 2024-05-01-preview have exceeded call rate limit of your current OpenAI S0 pricing tier. Please retry after 86400 seconds. Please go here: https://aka.ms/oai/quotaincrease if you would like to further increase the default rate limit.'}}

Bas Hulskamp If the above suggestions didn't help, kindly create a support request so that team can look into this internally and provide the resolution as earliest.