Vapi is the Voice AI platform for developers.

Vapi AI

this is the error that hung up the call: call.in-progress.error-vapifault-google-429-exceeded-quota

Hi there,

Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from **9:00 AM to 8:00 PM Pacific Standard Time (PST)**.

We’ll get back to you as soon as possible during our normal business hours.

If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly.

Warm regards,
**Vapi**
Customer Support Team

**Your call ended due to exceeding Google's API quota (`call.in-progress.error-vapifault-google-429-exceeded-quota`).**

To resolve this, configure Vapi to use your own Google API key with a higher quota. In your assistant or workflow settings, add your API key like this:

```json
{
  "provider": "google",
  "apiKey": "YOUR_GOOGLE_API_KEY"
}
```

*Update your configuration and retry the call to avoid hitting shared quota limits.*  
For more details, see the [Call Ended Reasons documentation](https://docs.vapi.ai/calls/call-ended-reason).

Source:
- [Call Ended Reasons documentation](https://docs.vapi.ai/calls/call-ended-reason)

will this make the cost of the LLM go to my google billing account instead of paying with vapi credit?

Hi codey, could you please provide us with the call ID?

here! 019c8150-5f53-722b-a273-9119e4cd3efa

also there's an issue when i try to add my own API key to avoid this, it tells me "The provided credentials are not valid." and a red error message says "Error in Saving Credentials
Couldn't Validate Google Credential. Error: {"error":
{"code":404,"message": "This model models/gemini-2.0-flash is no longer available to new users. Please update your code to use a newer model for the latest features and improvements." "status"."NOT_FOUND"}}" 


Which is weird because the key i put is for genai so it can use any model, never put anything related to gemini 2.0 flash on my end

Sorry for the delays as we are currently experiencing an extremely high volume of support requests. We'll soon get back to you.