Vapi is the Voice AI platform for developers.

Vapi AI

"An error occurred in this call: pipeline-error-google-503-server-overloaded-error"
Call ID : c08f34a5-0546-4834-b5b8-f83994fb97a7

To help track down this issue, could you share one or two:

- When exactly this happened (the timestamp)
- What response you expected to get
- What response you actually got instead  
  This would really help us figure out what went wrong!

<@1006897684965244938> I just got this error again today : Model request failed (attempt #1, reason: ([GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse: [503 Service Unavailable] The model is overloaded. Please try again later.))
Timestamp : 13:36:41:203
Call ID : 39b781f5-8aa5-46dc-b4c2-bc2335988b30
Response I was expecting : any response
Response I got : Silence, latency

And again this : An error occurred in this call: pipeline-error-google-503-server-overloaded-error
Cal lID : e5d27d8a-e3c2-4322-8d4b-fa99b19b988a
Timestamp : 13:41:49:448

`logs`
The error occurred when attempting to use the Gemini 2.0 Flash model with your API key (BYOK - Bring Your Own Key). The request failed with a 503 Service Unavailable HTTP status code, which Google returns when their service cannot handle additional requests due to high traffic or resource constraints.
The specific error message is clear: "The model is overloaded. Please try again later." This means Google's servers for this particular model (gemini-2.0-flash) were experiencing capacity issues at that moment. Try a few calls without his Google API key? The issue is with his API key as you can see from the following logs

I don't see the logs, but if the issue is with my key, I'll switch it out or remove my key altogether.  Thank you for clarifying

Try replacing or removing it in the Provider Keys section to resolve the problem.