Dify Cloud quota for OpenAI can't be used

[sugoh]

Self Checks

• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Dify version

0.14.1

Cloud or Self Hosted

Cloud

Steps to reproduce

1. Go to settings > Model provider
2. Check OpenAI quota is non-zero AND set Priority-use to Quota
3. Go to studio
4. Go to preview
5. Type a message to start chat and hit return
6. See OpenAI rate limit error

My account has credits

Open AI credits are full at 5,000 message credits

✔️ Expected Behavior

The AI to respond

❌ Actual Behavior

Error from OpenAI:

Run failed: [openai] Rate Limit Error, Error code: 429 - {'error': {'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.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

[dosubot]

The issue you're encountering seems to be related to how Dify handles OpenAI's quota and rate limits. Even though you have set the priority to use the quota and have sufficient credits, you're still receiving a rate limit error indicating "insufficient_quota."

Here are a few things to consider:

1. Quota vs. API Key Usage: Ensure that the configuration in Dify is correctly set to use the quota instead of the API key. Sometimes, even if the priority is set to "Quota," the system might default to using the API key if there are any misconfigurations.

2. Quota Management: Double-check the quota settings in Dify to ensure that they are correctly reflecting the available credits. There might be a discrepancy between what is displayed and what is actually available.

3. Error Handling: Dify uses Sentry to handle specific errors, including rate limit errors from OpenAI. However, it seems that the error you're encountering is not being ignored or handled as expected. This might require further investigation into how these errors are being processed within Dify ^[1].

4. OpenAI Account Settings: Verify your OpenAI account settings to ensure that there are no restrictions or issues with your plan or billing details that might affect the quota usage.

If these steps do not resolve the issue, it might be necessary to look deeper into the Dify configuration or OpenAI's API settings to identify any underlying problems.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[crazywoola]

We are investigating this issue.

[crazywoola]

Regarding the frequency limit issue with the OpenAI API, some users on Discord & GitHub have expressed strong dissatisfaction. It is necessary to provide feedback and reassure them as soon as possible to avoid the spread of negative sentiment and public opinion. Since the issue is still in the troubleshooting and verification stage, the response should be as follows:

Thank you for your timely feedback. The team has confirmed the existence of an API call frequency limitation issue, and the technical team is working hard to resolve it. We sincerely apologize for the impact on user experience, especially for paid users.

The technical team is currently taking the following actions:

Communicating with the OpenAI team to coordinate an increase in the limit.
Optimizing system load to ensure service stability.
We will keep everyone updated on the progress in Discord & GitHub. Once again, we apologize for the inconvenience caused and appreciate your understanding and support.