# ChatGPT 4o Mini Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/chatgpt-4o-mini
> Markdown URL: https://aitinkerers.org/technologies/chatgpt-4o-mini.md
> Technology record last updated: 2026-02-26T13:03:07Z
> Generated: 2026-09-23T07:37:50Z

GPT-4o Mini delivers advanced, multimodal intelligence (text and vision) at an unprecedented cost: 15 cents per million input tokens.

This is OpenAI's most cost-efficient small model, replacing GPT-3.5 Turbo as the new baseline for high-volume AI tasks. It offers a 128K token context window and robust multimodal capabilities (text and vision), all with low latency. Benchmark results confirm its power: 82.0% on MMLU and 87.0% on MGSM, outperforming competitors like Gemini Flash and Claude Haiku. The aggressive API pricing—15 cents per million input tokens—makes advanced AI highly accessible for real-time applications and customer support.

- Official technology site: https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [GESTURE (Graphical Encoding System for Translating Unique Recognisable Expressions)](https://lausanne.aitinkerers.org/talks/rsvp_9R4zaMzbav4)

The GESTURE project aims to solve a sign language translation task by translating a sequence of ASL signs into natural language. By connecting a live camera feed to a Pose Extractor (Google MediaPipe), signs can be detected in real time and translated/classified into their associated word(s) in natural language. Words are then translated into full sentences using an In-Context learning prompt sent to ChatGPT.

- Event context: AI Tinkerers Lausanne June 2025 Meetup — 2025-06-16 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_9R4zaMzbav4

## Related Technologies

- [Google MediaPipe](https://aitinkerers.org/technologies/google-mediapipe) ([Markdown](https://aitinkerers.org/technologies/google-mediapipe.md)) — 1 public demo
- [In-Context Learning](https://aitinkerers.org/technologies/in-context-learning) ([Markdown](https://aitinkerers.org/technologies/in-context-learning.md)) — 2 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Temporal Graph Convolutional Network](https://aitinkerers.org/technologies/temporal-graph-convolutional-network) ([Markdown](https://aitinkerers.org/technologies/temporal-graph-convolutional-network.md)) — 1 public demo