Fine-tuned Model Vision Capabilities Lost

API Bugs
,
1

A fine-tuned model (ft:gpt-4.1-2025-04-14:cvm:v1-optimized2:CtvBgA1l) that previously accepted vision inputs (image_url) now rejects them with error 400.

Error code: 400 - {
‘error’: {
‘message’: ‘Invalid content type. image_url is only supported by certain models.’,
‘type’: ‘invalid_request_error’,
‘param’: ‘messages.[1].content.[0].type’,
‘code’: None
}
}

It was working when I had image inputs last week, January 27th 2026. I have run my same source code without any changes utilizing the same fine-tuned model with image + text input, but have been getting this error. I am certain that I have not mistakenly used another model and this specific fine-tuned model.

4 Likes
Why does my vision fine-tuning job keep failing?
2

Yep, doesn’t get more absolutely confirmed than this - look at the model name (the “prefix” that is suffixed to the model name and org):

image
image734×250 10.8 KB

Chat Completions: validation blocked the call

image
image508×269 40.6 KB

Responses API: infinite loop

image
image493×500 43.2 KB

Vision-trained ft:gpt-4o - OK on both endpoints.

2 Likes
3

Thanks for the confirmation, I should’ve tested that before posting.
Just to clarify, your screenshots are showing that it’ is not a problem on my end?

4

In that I get the same API rejection using a fine-tuning gpt-4.1 model with image input on the Chat Completions API endpoint that was working before, it’s not just you.

2 Likes
5

We’re having this issue now as well, had to switch to a non-finetuned model to make requests.

1 Like
6

I am also having the same error. Is the only fix not using a finetuned model?

7

Do we have any update on how this can be solved? The best model i have with 4.1 functionality isnt working anymroe

8

Try: what is your success running on Responses API with your fine-tuning model? Is the output for you also damaged there?

9

Yep. I tested my finetuning model (ft:gpt-4.1-2025-04-14:personal::CaD5lQEs) in the playground. Whenever i add an image input to it, it replies with a empty assistant response. Additionally, at first it was spamming empty assistant message like your earlier replication, but now it just returns one, and then a message like “Rate limit reached for ft:gpt-4.1 in organization org-dDUPYEkyPhlXiTj7R9QnsB09 on tokens per min (TPM): Limit 800000, Used 800000, Requested 765.

1 Like