Through browser model respond as expecte but in API its not getting below error,
{
“error”: {
“code”: 500,
“message”: “An internal error has occurred. Please retry or report in Troubleshooting guide | Gemini API | Google AI for Developers”,
“status”: “INTERNAL”
}
}
3 Likes
Switched to gemini-2.5-flash model
That’s not a real solution. That’s like buying a Toyota Tacoma, but the engine won’t start, so you switch to a Toyota Camry instead. They’re not the same thing 
. Sure, they both get you from Point A to Point B, but there’s a big difference in what they can carry and terrain they can traverse.
Same with 2.5-Flash vs 2.5-Pro. There’s a difference in their capabilities and sometimes you really need the 2.5-Pro model.
2 Likes
Agreed. I am just testing the API its weird 2.5 Pro is not responding. I will leave it to team to figure out what happened.
im having the same problem
1 Like
Same problem. 80% of requests fail with this error.
Hi @Kristik , @Mohamed_Amine @p_g @Andavar_Alagarsamy,
Are you still experiencing this issue? If so, please provide the details of your request, which will help us debug the issue further.
Thank you!
We dont receive fhe empty text response from the model anymore we get model overloaded
I am still experiencing this issue. I use gemini-2.5-pro in my python script and it worked fine, but last three days almost every API request ends up being Internal Error (500).
My friends also work with this model and they are experiencing the same issue. Gemini-2.0-flash works, but i really need 2.5-pro for my project.
Constant failure for me at this point. Gemini 2.5 Pro has been inconsistently working for the last week, often rendering errors or not responding to user input.
✕ [API Error: {“error”:{“message”:“{\n "error": {\n "code": 500,\n "message": "An internal error has occurred. Please retry or report in
https://developers.generativeai.google/guide/troubleshooting\”,\n "status": "INTERNAL"\n }\n}\n",“code”:500,“status”:“Internal Server Error”}}]
2 Likes
Same here, using Gemini CLI:
✕ [API Error: {“error”:{“message”:“{\n "error": {\n "code": 500,\n "message": "An internal error has occurred. Please retry
or report in https://developers.generativeai.google/guide/troubleshooting\”,\n "status": "INTERNAL"\n
}\n}\n",“code”:500,“status”:“Internal Server Error”}}]
Model: Gemini 2.5 PRO
The 500 error occurs almost(in my case always) exclusively on “pro” requests, while “flash” requests and all operations in ai studio function correctly. I have confirmed that this issue is not related to the gemini api library version.
Same here (exclusively with gemini-2.5-pro)
Same issue on my side, impossible to make a request to pro (no issue on all the other models).
Account on tier 1, but still with some free credits (expiring in 2 months)
Hi All,
I was unable to reproduce the issue on my end. Could you please provide the exact API call, including both payload and parameters that consistently generates the 500 error? This information would be invaluable in further debugging the issue.
Thank you!
This error is in the Pro model
Gemini AI: {“error”:{“message”:“{\n "error": {\n "code": 500,\n "message": "An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting\”,\n "status": "INTERNAL"\n }\n}\n",“code”:500,“status”:“Internal Server Error”}}
3 Likes
It’s highly unprofessional. These errors have been going on for several days and weeks. It would be one thing to have a warning or some update about it, but we’re kept into the dark. And it’s not even the free tier, but even the paid ones who are being affected as well. With the number of people reporting it, you’d think they would at least say something, but no, we’re treated as if we are not the ones contributing to the api with our requests.
At this point, they’re still saying they couldn’t reproduce the issue, so perhaps they still haven’t escalated it to the development team even after several weeks?
2 Likes
It’s a real shame that we’ve had the same problems for weeks and nobody cares.
gemini-2.5-pro, free Tier
I’m getting the same error: '500, ‘message’: ‘An internal error has occurred.’
It started about a week ago, and now I’m only getting this type of error response. On the first request.
At first, I was getting a lot of ‘429 too many requests’ errors, then it progressed to errors like ‘The Model is Overloaded,’ and now this 500 error.