My service is down getting this since last night for every request : GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent: [503 Service Unavailable] The model is overloaded. Please try again later.
Same here. Most requests are getting this 503 error. I tried switching to the VertexAI (@google-cloud/vertexai) package to see if that made a difference since the @google/generative-ai package seems less actively developed. That seemed to work, but I had limited success fully testing since the API limits are unfortunately defaulted to 5 RPM. I filed a quota increase request to match the 1000 RPM you get with the paid tier using the generative-ai package, and will see if switching to that makes a difference whenever that quota request goes through.
All in all, extremely frustrating though. No indication anywhere from Google that there’s an issue, and multiple different poorly documented client SDKs that seemingly have different behaviors.
A few other things I tried with no success:
- switching where I was calling the SDK to a different region (this worked to fix a similar temporary issue that happened 6 months ago, no luck this time though)
- switching from “gemini-1.5-pro-latest” to “gemini-1.5-pro-002”
- switching the api version from the default “v1beta” to “v1” (this failed for me because JSON support doesn’t seem to exist in v1, and that’s pretty critical for using this programatically)
Switching down to gemini-1.5-pro-001 seems to be working for me for now, but given that 002 is in theory a stable model that’s a pretty poor outcome.
1 Like
how did u resolved it 
If you are facing the same error, then the problem is not with your codebase. it is happening cause of the high demand of the model, you have to wait for sometime or change the model (take openAI model for 5$ it is worth it).
For my case, I solved it by cleaning up all files that I upload to file api.
Here’s we have 20G hard limit for storage that we can upload files.
Getting the same issue:
503 UNAVAILABLE. {‘error’: {‘code’: 503, ‘message’: ‘The model is overloaded. Please try again later.’, ‘status’: ‘UNAVAILABLE’}}
Hello guys,
Just getting the same error message randomly.
Service unavailable - try again later or consider setting this node to retry automatically (in the node settings)
[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent: [503 Service Unavailable] The model is overloaded. Please try again later.
Any insights about this issue? Has been happening a lot lastly.
This is happening like the 70% of the time, this is such a shame, i paid over 250€ for Adv for my App on the PlayStore and almost half of the user just deleted the application.
This is happening like the 70% of the time, this is such a shame, I want to start my app but almost before release I noticed error happening so much time. Fix it!!! For know I have to search for other model providers .
Having the same error as well. No matter the model I choose, I’m on free tier as well and using ADK.
execution: 503 UNAVAILABLE. {‘error’: {‘code’: 503, ‘message’: ‘The model is overloaded. Please try again later.’, ‘status’: ‘UNAVAILABLE’}}"
Getting same errors here (model overload) I’ve changed env. variable for location from us-central1 to us-east4. Seemed to work for a bit and then same errors. switched models from 2.5 pro to 2.5 flash. Same issues.
I’ve found the Gemini output to be the best but even though I’m spending my API money with them, I’m getting a lot of failures due to this. Yes I could run it again but it’s not something I would like to push to production and may need to consider another model from another company for a while .. Gemini is great but this reliability is concerning
The model is currently overloaded. Please try again later
Again again and again
It’s unbelievable and unacceptable that a company like Google is not large enough or does not have the desire to solve this chronic problem. Move it!
Hi all,
As we have so many models, can you report using the following structure:
1. Which model is being used that caused the error?
2. Which platform are you using the model?
3. Which region are they trying from?
4. Which tier are they on?
5. Paste the exact error message.
Hello, I am responding to your message to say that now, but actually for more than a week, fortunately everything has been sorted out, at least as far as I am concerned. I don’t know about in general, but for me, yes, the prompt responds correctly and at the right speed. I’m very happy that the developers have managed to fix the problem, whether they did something or whether the problem in general has been resolved in some way. I just hope that this problem doesn’t recur in the future, but I remain hopeful that it won’t. Best regards and have a good day 
I have the same issue here. Here is the list of my troble below.
- Which model is being used that caused the error?
The model I use is gemini-2.5-pro
2. Which platform are you using the model?
The platform is API from Python.
3. Which region are they trying from?
I am not sure the exact name of my region defined by Google, but I live in Tokyo. So, east asia-pacific area ??
4. Which tier are they on?
I used from free tier.
5. Paste the exact error message.
Error: 503 UNAVAILABLE. {‘error’: {‘code’: 503, ‘message’: ‘The model is overloaded. Please try again later.’, ‘status’: ‘UNAVAILABLE’}}
There is another problem in counting the usage of my account, 503 error is counted as a normal usage. This is very weird and I saw other people pointing out this problem in this or other thread. Please fix this error as soon as possible, too.
I dont know if this helps anyone but, I had the same issue when making parallel or sequential requests in bulk, turns out the error happened because I opened clients with those requests aswell which caused the 503 error so it doesnt always mean there is a problem with Google’s infra