Azure OpenAI Assistant API: Retrieve API Fails Due to Rate Limit Exceeded Error

Using the code run = client.beta.threads.runs.retrieve(thread_id=thread_id, run_id=run_id), the response returns:

LastError(code='rate_limit_exceeded', message='Rate limit is exceeded. Try again in 16 seconds.')

Only 2-3 out of 10 prompts are successful.

Could you please help understand when the rate limit exceeded error is thrown and how to avoid it?