Release dates
— GPT-4o launched with native text, vision, and audio. ↗
GPT-4o
An “omni” model natively spanning text, vision, and audio with substantially lower interaction latency.
MODEL NUMBER004
- First public date
- 2024-05-13
- Organization
- OpenAI
- Family
- GPT
01
Specifications
Only published specifications are shown.
- Architecture
- Undisclosed
- Context
- 128,000 tokens
- Input modalities
- Text · Image · Audio
- Output modalities
- Text · Audio
- Open weights
- No
- Status
- Legacy
02
Overview
Why it mattered
GPT-4o moved native multimodality from a research capability into a real-time mass-market experience.
PreviousGPT-4— · 8K ctx
CurrentGPT-4o— · 128K ctx
04
Architecture & capabilities
Model capabilities
Native multimodalVisionReal-time audio
05
Release history
GPT-4o launched with native text, vision, and audio.
View source06
Related models
Select a card to view the related model.
07
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.