Another solid set of updates [for developers] after the GPT-4o release. What's new: GPT-4o mini enables a broad range of tasks with its low cost and latency, such as applications that chain or parallelize multiple model calls (e.g., calling multiple APIs), pass a large volume of context to the model (e.g., full code base or conversation history), or interact with customers through fast, real-time text responses (e.g., customer support chatbots). Today, GPT-4o mini supports text and vision in the API, with support for text, image, video and audio inputs and outputs coming in the future. The model has a context window of 128K tokens, supports up to 16K output tokens per request, and has knowledge up to October 2023. Thanks to the improved tokenizer shared with GPT-4o, handling non-English text is now even more cost effective. And also safer: GPT-4o mini in the API is the first model to apply our instruction hierarchy (opens in a new window) method, which helps to improve the model’s ability to resist jailbreaks, prompt injections, and system prompt extractions. This makes the model’s responses more reliable and helps make it safer to use in applications at scale.

Directly applied it to my app 🤙

Is this an early GPT5 checkpoint?

My favorite point about the new OpenAI models is that the price is decreasing with almost every release, pushing the market to adjust accordingly. It's definitely beneficial from the consumer's perspective, but it likely adds some pressure on the competitors as well (which is also good since most of the competitors are big mega-corps 😄)

Congratulations! I am sure it will improve the results for 3.5 users.

At least the product of the week, if not of the month. But things are moving fast... so the day must do 😘

Excited to implement this model at Balance 🫡 impressive that's cheaper than 3.5 Turbo

I love that AI moving to more practical solutions! So much power lies in it being not "all answering guru" but a part solving a step in complex product journeys!

Cool! This will help us to cut costs significantly on some of our apps! Thank you for the launch, upvoted!

Everyone is asking if AI is a hype… well we need good and cheap models like this to launch practical AI solutions. Congrats OAI!!!

Excited to see what’s possible with this smaller model, congratulations on your launch. I’m excited for what the future holds for LLMs

This is a great new for developers and companies running on Open AI API. At MindPal, we also just updated our AI agents with GPT-4o mini

Fast, Cheap, Smart..what can i say?

Wow this is AI tools 🔥

The GPT-4o mini launch looks incredible! Lower costs, improved performance, and enhanced security features are game changers. It’s impressive how OpenAI is making AI more accessible and efficient, supporting tasks from customer support to complex problem-solving. With its broad capabilities, including handling large volumes of context and multiple model calls, this model is set to revolutionize the AI landscape. Speaking of innovative tools, I recently came across an awesome tool for 10x your SEO game— SEOPro on Shopify appstore definitely worth a look!

Immediately put into use, thank you for reducing costs, giving us more room to develop applications! 🫡

Wow, this is really good news!

Very practical and the reduced costs yayyy!

Wow! This is great, my team will definitely love it !

Excited about GPT-4o mini! What unique advantages does it offer for developers working on complex applications?