Error: The model is overloaded

I am getting this error, and I’m not sure what it means. It’s a 503, suggesting it is a server-side error. I’m using the free tier. I’m within the rate limits of 15 calls/minute and 1 million tokens / minute. I’m using the JavaScript/TypeScript SDK.

error: [GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-002:generateContent: [503 Service Unavailable] The model is overloaded. Please try again later.

Does anyone know what this error means? Is it maybe the case that the free tier is only available when paid tier usage is low?

5 Likes

Welcome to the forums!

As the 50x level indicates - this is an error on Google’s side. It usually means that something went wrong in how they’re dealing with something internally. Sometimes in calling a parallel service to Gemini, but not Gemini itself.

I’m seeing more and more reports of something like this. Can you provide more details or a concrete example of code you’re calling that is is triggering it? Are you using any tools? Large prompts? Media?

2 Likes

In addition to a user text prompt, I’m using cached context with a large PDF and system instructions. I’m trying to accurately extract information from research studies.

2 Likes

I am also getting the same issue.
did you get any solution for this issue?

1 Like

Same issue sisce morning, i was quite frustrated thinking that if i was doing something wrong… Error details: {
message: ‘[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.’,
stack: ‘Error: [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.\n’ +

2 Likes

I’m facing the same problem when trying to retrieve JSON data

(https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent:) [503 Service Unavailable] The model is overloaded. Please try again later.’,

1 Like

Same issue. Around 30% of requests are returning 503. Model overloaded or service unavailable.

1 Like

same issue persist using node js sdk

[DUPLICATE]

Try using Gemini’s experimental model “gemini-exp-1114”. I believe that Google allocated too many resources to the experimental model, possibly due to an imminent update.

Hi! Didn’t work. About 80% of request are giving 503.

It’s been 7 days and this error still persists…

1 Like

Hello, I am also Encountering this error.
Nearly All of my requests are returning 503

[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…

btw what about pro-1.5 model? Does it overloaded as well?

No, I don’t believe so.

Everything was overloaded yesterday. I just checked it 1 minute earlier and everything seems to work fine now.
I hope the issue is resolved for you all too??

For me yes! Finally works

1 Like

Using gemini-1.5-pro I got “[429 too many requests] resource has been exhausted (e.g. check quota).” error

I am also getting this error . I am using langchain and it is traversing the pdf and giving me answer with the help of gemini . But when I am asking the question sometimes it is giving me this error

Same issue here.

Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-002:generateContent: [503 Service Unavailable] The model is overloaded. Please try again later.

I just switched from flash-001 to 002 and now these error are showing. Retry policies let these pass eventually in my case but the errors are pretty often.

I have been getting these errors frequently today with “gemini-1.5-flash-002”:
[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-002:generateContent: [503 Service Unavailable] The model is overloaded. Please try again later.

Some API calls work, but eventually it throws these errors.