Will test out the new model. Naming of these models could have been much better.
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
ChatGPT Switches Default Model to GPT-4.1 Mini for All Users, Subscribers Get GPT-4.1
- Thread starter MacRumors
- Start date
- Sort by reaction score
I'm not sure why OpenAI would switch all users to the 4.1 model, much less the mini version, since the "o" in "4o" stands for "omni", meaning it can take not just text as input, but also images and audio (but not video yet), and it can also include images in its responses (the other two can't), and it has a more conversational style. But maybe it's that more conversational style that OpenAI wants to get away from, or just keep it as a non-default option, after the debacle with the 4o model's flamboyantly unctuous responses that ended about a week ago when OpenAI "adjusted" that approach when people couldn't stand it.
I just asked the 4o model to compare all three models. It said:
• GPT-4.1-mini is like a very smart intern—quick, cost-efficient, and competent in most general tasks, but not as deep or nuanced as the larger models.
• GPT-4.1 is the analytical specialist—great for complex reasoning, but slower and less adaptable.
• GPT-4o is the conversational polymath—fast, expressive, and capable of working across text, images, and audio.
ChatGPT also says about its 4o model: "It's slightly more interpretive than strictly factual." If this means less nonsense and hallucinations with the other two top models, the better.
I just asked the 4o model to compare all three models. It said:
• GPT-4.1-mini is like a very smart intern—quick, cost-efficient, and competent in most general tasks, but not as deep or nuanced as the larger models.
• GPT-4.1 is the analytical specialist—great for complex reasoning, but slower and less adaptable.
• GPT-4o is the conversational polymath—fast, expressive, and capable of working across text, images, and audio.
ChatGPT also says about its 4o model: "It's slightly more interpretive than strictly factual." If this means less nonsense and hallucinations with the other two top models, the better.
Last edited:
Yep, Chat-GPT just put another 2.5 years between it and Apple's non-existent AI. It seems that every month that goes by Apple falls further and further behind. I mean I guess trying to Siri from 2010 to 2016 is a monumental task, but Apple will not win any races by taking 2 years to advance 1 year. Maybe Apple should outsource AI development to some other 3rd world country. It might speed up things.
Ah, but which model did you ask? because maybe 4o-mini is "great at recommending another model."
It would be unsurprising if GPT-4.1 replaces GPT-4o as the default soon. The API pricing of GPT-4.1 is even lower.
Using ChatGPT to help plan with vacation itinerary, it's been fairly helpful. Specially as I have to plan to adjust travelling with a 2 year old toddler. Meanwhile, Siri can't even tell me the weather for tomorrow.
I could confirm that GPT-4.1 can analyse images very well, and it can start the process of generating images. ChatGPT actually uses a different model named "GPT Image 1" to generate images.
I have 4.1 available (I'm a subscriber with Team plan) but it's not being set as default, I have to manually select it every time
I have this version
NB: FREE version
==================
Hi! 👋 I’m ChatGPT, currently running on GPT-4-turbo, which is a faster and more efficient variant of GPT-4 developed by OpenAI.
What does that mean for you?
- 🖼️ I can understand both text and images — you can upload pictures, and I can help analyze or explain them.
- 🧠 My training includes knowledge up to June 2024.
- 🌐 I can also search the web (when needed) to provide fresh, real-time information.
- 💬 I’m designed to handle long, thoughtful conversations smoothly and quickly.
- 🌍 I speak multiple languages fluently — including English, Romanian, Spanish, and many more.
🔍 Key Differences: GPT-4 vs GPT-4-turbo
| Feature | GPT-4 | GPT-4-turbo |
| Speed | Slower | Faster 🚀 |
| Cost (to use via API) | More expensive | Cheaper 💸 |
| Efficiency | Standard | More optimized ⚙️ |
| Context length | Up to 8K tokens (some 32K) | Up to 128K tokens 🧠 |
| Availability in ChatGPT | Not used | Used in ChatGPT (pro) ✅ |
Tokens = chunks of words I can remember in a conversation. More tokens = longer memory per interaction.
Also mine is not confused at all.
Yours is broken 🤣🤣🤣
Apple ID is based in the uk.
Realistically! real IP address
Interesting. I asked 4o if its 4.1 models could analyze images sent to it by the user, and generate images too, and it said no to both. Though I'm not surprised--I've asked ChatGPT various questions about itself over the past year or so, and sometimes it gets its replies wrong.
Fr?
Re Gemini I asked medical advice >> always prompts me to go to a doctor.
ChatGPT sorted a lot of small issues I have. AGAIN tried and tested and all worked
Saved a lot of trips to my gp and physiotherapist 🤣🤣🤣
What an awful naming convention. Is 4.1 supposed to be better than 4o? You know your naming convention is bad when even Google has a better handle on theirs.
Ask these questions to ChatGPT, it will be happy to explain the advantages of each model.
I have, and it's answers are all over the place and change. Once I asked 4.1, and it told me that 4o was the latest... all the while 4.5 is staring at me from the drop down.
Even when it's right, you won't really get a clear explanation of the differences, which I partially suspect is because there's not always clear reasons why they differ in this way or that.
Nearly a month after this article and I’m still waiting for 4.1 to be default… 🤣 I have to change it every time.
It's weird. The mac app always defaults to 4o. The iphone app used to keep 4.1 selected for days or weeks, but I've noticed recently that it seems to revert back to 4o much more readily. I haven't used the web version for a long time, so I'm not sure there.