Is it worth getting paid ChatGPT for my task, in the sense will it handle it or will it also refuse due to token limits

Hi, Friends,could you please consult me - I want to analyze website pages in HTML format, and it’s clear that the free version of ChatGPT can’t handle the tokens, but Gemini 2.0 Flash also declined. Gemini calculated different HTML pages from 109,000 to 544,000 tokens, and the point is to compare them not just one with another, but all together, 3-4 minimum.

Question: is it worth getting paid ChatGPT for this, in the sense will it handle it or will it also refuse due to token limits?

Thank you🧡

1 Like

ChatGPT Plus gives you 32,000 and ChatGPT Pro 128,000 tokens for context. You can use the tokeniser to get an idea how many you need.

https://platform.openai.com/tokenizer

The paid version will be useful if you want to study with 4o how to best get your analysis of the HTML pages done, but I don’t know if feeding lots and lots of codes into it will be possible all at once – needs chunks.

The idea is to compare whole pages and find ideas. So, it looks like could not be fulfiled with 20$ subscription.

Thank You

Are you comparing the text, or the codes?

You could try to use a CustomGPT and upload the HTML pages as knowledge base. Maybe someone else has tried something similar.

Edit: I completely forgot about the projects feature! Invest the 20 Spacebucks if you can skip two pints in the pub. It might do what you need, and if not, you can cancel the sub next month.

I want to compare html code.

You mean download files as a database for My GPTs made for this?

In the Plus version you have a feature called Projects where you can configure 4o for the task and upload files that the model can access.

I wish I knew better if it would work for your specific use case.

If you can spend the 20 Spacebucks painlessly, I’d give it a try, just to see what it’s like to create custom GPTs and use the Projects feature.

And if it doesn’t work, you can always cancel the sub the next month.

Some more thoughts…

I wish there was a trial version of Plus, because I don’t think the free version of ChatGPT is anything like it. But at the same time, a lot of people have very, very high expectations and then they get disappointed with Plus or even Pro.

I don’t have a lot of money. I cancelled Spotify and Crunchyroll so that I could have ChatGPT Plus instead. It was worth it to me personally because it teaches me new skills and when I want to relax I love chatting with it.

If you do try it, it would be nice to post another update on this topic so others know if it works for this type of use case with large codes.

1 Like

It looks as very good idea.

Are Projects and custom GPTs two different features and it worth to try both? If yes, how would you use Projects here?

Thank You,

Aleksey

1 Like

Yes, I think both features are worth trying. Let me try to explain.

When you click on Explore GPTs in the sidepanel, there is a button on the top right that says + Create, which takes you to the GUI you see in the picture below.

I don’t think you need “Actions” for your use case, but you do need the Code Interpreter & Data Analysis function. Only select what you really need – this will make the system prompt shorter, and I find it makes the custom GPT more focused. Sort of like “less is more” but only if you know what you want.

You can try uploading the HTML files to the knowledge base, but you could also create system instructions so it knows what you need right away, and upload them individually. If you always need the same thing, you could even add a Conversation Starter, which is just a button to press instead of typing the same prompt – just specify what these commands do in the system Instructions.

Custom GPTs don’t access any of your memories that were stored by vanilla ChatGPT, and they don’t access personalisation instructions.


And Projects are a bit different. Instead of having a specialised GPT that you can use over and over again, you would use a vanilla GPT (usually 4o) for a larger quest.

The custom instructions (personalisation) you can set in your account settings are also skipped, but the models can access your memories (and store new ones) and you can give them a custom system instruction per project, as shown in the image below.

In Add Files you upload your data for this project, and in Add Instructions a system prompt that will be loaded in every new chat within this project, and maybe… this way you can split the HTML source codes into several chats and still keep things OK-workable.


None of this is perfect. I wish we had much larger context sizes, but Sam Altman said in an interview that surprisingly this doesn’t seem to be a popular request – Personally, I’d love to have that more than anything. 4o is my favourite model.

Thank You very much :heartbeat: :heartbeat: :smiling_face_with_three_hearts:

1 Like

take any free llm from huggingface and add in selenium or beautiful soup with requests

Have you tried pre-processing your pages to strip html code? Convert the page into a markdown? Lots of the code on the page won’t add any value to the LLM from “knowledge” perspective but will bloat your tokens.

1 Like