Low-cost, Low-latency, Customizable Chatbots for Your Websites and Web Apps Using GPT-4o mini

Author(s): LucianoSphere (Luciano Abriata, PhD)

Originally published on Towards AI.

Spend fractions of cents per user interaction and make them fast and efficient, providing a fluent experience

Look at the following conversation. It’s me trying out my website’s chatbot after upgrading it to GPT-4o mini, which made it faster and cheaper to operate:

Want to try it out?

Here’s my GPT-4o mini-powered chatbot!

Want to build one for your own website or web app?

Read on!

In another release of more science fiction-looking tools that programmers can use seamlessly through their API, OpenAI keeps revolutionizing the accessibility of artificial intelligence with their latest large language model (LLM). This time, with better cost- and time-efficiency than ever.

I’m talking about GPT-4o mini.

This new “small” (but large language…) model is designed to offer cost-effective, low-latency intelligence. It is already available via the Assistants API, Chat Completions API (which we will use here), and Batch API, which means we can integrate it in our software right away!

Priced at just 15 cents per million input tokens and 60 cents per million output tokens, GPT-4o mini is over 60% cheaper than GPT-3.5 Turbo and an order of magnitude more affordable than previous frontier models. Despite its small size, GPT-4o mini achieves (as claimed by OpenAI) impressive performance benchmarks, scoring 82% on MMLU, a test used to evaluate the capabilities of language models through thousands of multiple-choice questions spanning… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI