Hi guys. I wonder if any of you got this problem before.
Just 2 days ago, I experimented with realtime API (with Twilio) based on the instruction given by OpenAI’s documentation.
After first run which was successful, my account started receiving insufficient_quota response. But I couldn’t figure out why. Our organization current monthly bill is at $4+. Our limit is set at way above that. So I thought the data could be delayed. I decided to check our Usage report. Same thing, nothing extraordinary. Everything is within limits for our tier (tier 4). 2 days have passed now, billing and usage reports remain unchanged.
What else could I do? What else could be wrong?
And it’s no longer just with realtime API (which is in beta), all other APIs using 4o or 4o-min are affected, too.
Here’s the API call’s response.
Received event: response.done {'type': 'response.done', 'event_id': 'event_ARcc5tYjpDEXO1LY73SEO', 'response': {'object': 'realtime.response', 'id': 'resp_ARcc4xH9gGrzgClcqZLJU', 'status': 'failed', 'status_details': {'type': 'failed', 'error': {'type': 'insufficient_quota', 'code': 'insufficient_quota', 'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.'}}, 'output': [], 'usage': {'total_tokens': 0, 'input_tokens': 0, 'output_tokens': 0, 'input_token_details': {'text_tokens': 0, 'audio_tokens': 0, 'cached_tokens': 0, 'cached_tokens_details': {'text_tokens': 0, 'audio_tokens': 0}}, 'output_token_details': {'text_tokens': 0, 'audio_tokens': 0}}}}