Natively multimodal (text, audio, vision); low-latency real-time voice mode; priced below prior flagship.
See related coverage: /model-releases/gpt-4o-omni-model-retrospective/
Natively multimodal (text, audio, vision); low-latency real-time voice mode; priced below prior flagship.
See related coverage: /model-releases/gpt-4o-omni-model-retrospective/