I am using the API to send an assistant (w/ gpt-4-vision-preview) a screenshot and the URL the screenshot is from. In the past 48 hours, I have noticed a huge spike in the cost of these queries. We were spending $4-$5 a day, and suddenly we’re spending $20+. The number and size of the payloads does…

I was coming in to suggest this as you found your answer. I’m general you should always optimize your input before passing it into expensive models. Essentially, you should crop out or mask unimportant details and scale the image to some max dimension. Edit: I wanted to add that one thing you mig…

I may have figured it out – some of the screenshots in the past 48 hours have been much larger than the previous average.

Would you say that scaling the image down to a max height will hinder vision-preview’s ability to detect elements within the image (e.g. logos, text boxes)? I feel like I’m better off cropping the image to a max height than trying to scale it.

I just found { detail: 'low' } so I’ll try that first.

I think both cropping and scaling have their places. For instance, if your image is too large, the API will scale it down invisibly in the background before sending it to the model, For low res mode, we expect a 512px x 512px image. For high res mode, the short side of the image should be less th…

Thank you for the recommendations. We’re still fine-tuning this particular use case, but SAM sounds like it could be useful. We don’t know the contents of the screenshots ahead of time (that’s why we’re having chatgpt analyze them for us) but we know the elements we’re expecting to find, so SAM migh…

Can I ask more details about the screenshots you’re working with? I would guess you’re analyzing some kind of UI elements, website layouts, or something of that nature, but if I knew more about what you’re broadly trying to get the model to do I might have some other, more targeted, suggestions.

[image] jeffrey.pinyan: So we’re having ChatGPT analyze them for logos, username/password/etc. text-boxes, etc. ChatGPT or through the API? How are the sites being reported—are users submitting the screenshots themselves or are you going to the URL with a headless browser and capturing the s…

Sorry, through the API. Sometimes the screenshot is provided by the person reporting the URL, and sometimes it is grabbed via headless browser.

Question… I’m sure you’ve considered this, but I’m wondering if you can explain the reasoning to me so I’m up to speed. If you’ve got the ability to access the page, directly and some of the chief items you are concerned with evaluating are logos, why are you not grabbing the page images directly …

Unexpected surge in cost: assistant + gpt-4-vision-preview

API

jeffrey.pinyan June 27, 2024, 6:37pm 9

We are looking at screenshots of web sites that have been reported for phishing. So we’re having ChatGPT analyze them for logos, username/password/etc. text-boxes, etc.

Topic		Replies	Views
Getting data from other peoples images on vision API Bugs gpt-4	1	137	August 17, 2024
I am paying +$1 for a single request on analysing a 200kb image API gpt-4	5	786	June 1, 2024
Question: GPT Vision + Appending to the messages object for sequential requests API gpt-4 , gpt-4-vision , gpt4-vision	6	1964	February 2, 2024
Question about GPT-4 Vision API and Limits in Image Analysis API api	4	668	January 27, 2025
Strange/Bad behavior of Open AI API with vision models API gpt-4 , api	7	1102	February 24, 2025

Unexpected surge in cost: assistant + gpt-4-vision-preview

Related topics