Aller au contenu
Atlas de l'IA

GPT-4o

Un modèle général nativement multimodal : texte, image et audio par une même entrée

OpenAI Modèle Fermé
entréeTexteImageAudioTexteAudio

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE C'EST

GPT-4o is a general-purpose model OpenAI released in May 2024; the “o” stands for omni, meaning text, image and audio are handled inside one model. Vision and speech understanding share a single forward pass, and spoken conversation runs at near-real-time latency. Where earlier systems stitched several models into a pipeline, GPT-4o trains multimodality end to end and simplifies the interaction entry point. It is offered through both the API and ChatGPT, and serves as OpenAI’s main multimodal general model.

Pourquoi il compte

It moved multimodality from “several models stitched into a pipeline” to “one model end to end” and cut spoken-dialogue latency to near human-conversation levels; general models have since treated native multimodality as the default target.

Caractéristiques clés

Context window
128K tokens
Modality
Text, image, audio in; text, audio out
Released
2024-05
Open weights
No

Capacités

Concepts liés

Produits comparables