2.0-Flash-lite model overloaded once again

Gemini API
, ,
1

Hi,
I’m using 2.0-flash-lite model in my app. Today I got a server overloaded error which I can see is not uncommon. It persist for a past 8 hours. Does anyone now what when issue will stop ? In status it seams everything works, but the issue is recurring. How long will it take Google to fix it???
My API response:

{
  "error": {
    "code": 503,
    "message": "The model is overloaded. Please try again later.",
    "status": "UNAVAILABLE"
  }
}
3

Hi @matzyn,

Thank you for reporting this. To help us diagnose the “503 Model Overloaded” issue, could you please let us know if you are using the free tier or a paid tier? This information is helpful because requests from paid tiers are prioritized, especially during periods of high traffic.

5

Currently using free tier.

1 Like
7

Hi @matzyn,

Are you still experiencing this issue?

Thank you!

9

Hi,
This month almost none. I get 429 error(too many request) even though I don’t see myself hitting rate limit

11

Hi,
This month almost none. I get 429 error(too many request) even though I don’t see myself hitting rate limit?

1 Like
13

Hi @matzyn and @Muhammad_husnain,
Please let me know if you are still facing this issue?
Please provide the following details:

  • Complete Error Message: The full JSON response.
  • Billing Tier: (e.g., Free, paid etc.
  • Model Name & Region: (e.g., gemini-2.5-pro in europe-west1 etc).
  • Platform: (AI Studio, Vertex AI SDK, or REST ).
  • Task Description: Briefly, what are you using the API for? (e.g., "summarizing large PDFs"etc).
  • Provide the project number (not the project ID) via direct message