This week, OpenAI debuted a more lightweight version of its most advanced large language model (LLM), GPT-4o. Called GPT-4o mini, it will replace GPT-3.5 Turbo as the default model used in the free version of ChatGPT, and for developers, it’s meant to act as a more affordable option compared to GPT-4o, which OpenAI released a few months ago. But exactly how different are these two models, and which one should you use? Here’s what you need to know.
The biggest compromise to GPT-4o mini is that it does not yet support video and audio processing at launch, although images do work. OpenAI says it plans to integrate those features later down the line, but for now, you'll need to stick with GPT-4o proper for them.
Otherwise, the model should give you similar performance to that seen in GPT-4o, at least according to charts provided by OpenAI. Because the way tests are run can differ from company to company, though, some developers prefer to take a wait-and-see approach when it comes to measuring performance.
Because GPT-4o mini is meant to perform similarly to GPT-4o, the biggest long-term difference you’ll see between these two models is going to be pricing, which largely affects developers rather than individual users. GPT-4o currently runs for $5 per 1 million input tokens and $15 per 1 million output tokens. GPT-4o mini on the other hand will run for 15 cents per 1 million input tokens and 60 cents per 1 million output tokens—thereby making it much more affordable, especially for longer projects. OpenAI says that the 1 million output tokens represented in the pricing is roughly the equivalent of around 2,500 pages in a standard formatted book.
Individual users just using the GPT app will still have limited free access to the standard GPT-4o, but 4o-mini will replace 3.5 Turbo once their usage limits on its larger cousin run out.
One area that OpenAI has not deviated on between GPT-4o and GPT-4o mini is safety. The new, smaller model features the same safety mitigations that OpenAI has built into GPT-4o, which includes testing by more than 70 external experts to help identify potential risks the model could pose to its users.
In addition, GPT-4o mini is the first of OpenAI’s models to incorporate a new “hierarchy” model, which the company says will help it improve the model’s ability to reset prompt injections, jailbreak attempts, and other nefarious usage such as system prompt extractions.
GPT-4o mini is available in the ChatGPT app, website, and API now.
It’s been almost four months since Europe’s Digital Markets Act (DMA) forced Apple to start allowing third-party app stores on European iPhones. While
Now that the iOS 18 developer beta is out in the wild, we've learned about some new and interesting features that Apple failed to mention in its WWDC
If you have some mix of Apple, Windows, and Android devices it can be a pain to quickly send a file from one to the other. Airdash is an open-source p
Window management has been a sore subject on Mac for many years. Plenty of people switch to Mac from a Windows machine and find macOS' window manageme
Amazon has a bit of a hold on the e-reader industry. Like Kleenex did with tissues before it, Kindle has become so synonymous with e-readers that it’s
Earlier this week, Apple’s first HomePod officially became “vintage” in the company’s eyes. Now, rumors are swirling about a new HomePod with a screen
We are a dynamic information platform dedicated to delivering timely, relevant, and reliable content across a broad spectrum of topics. From the latest in technology and business to lifestyle, health, and global affairs, we aim to keep our readers informed and inspired.
Our editorial team is committed to maintaining high standards of accuracy and clarity, ensuring that every article provides value and context in an ever-changing world. We believe in the importance of accessible knowledge and strive to make complex topics understandable for everyone.
Whether you're here to stay updated on current events, explore thought-provoking features, or simply learn something new, our goal is to offer a trustworthy source of information that meets the needs of a diverse and curious audience.