GPT4o

GPT-4o (Omni) is OpenAI's flagship multimodal model: it processes and generates text, audio, and vision end-to-end, delivering human-like response speeds and superior performance.

GPT-4o, released in May 2024, is OpenAI's latest flagship model: an omni-modal architecture that processes and generates text, audio, and image inputs and outputs through a single neural network. This unified approach drastically cuts latency, achieving an average audio response time of 320 milliseconds (ms), comparable to human conversation. It maintains GPT-4 Turbo's intelligence while being 2x faster and 50% cheaper via the API. The model features a large 128,000-token context window, significantly improving its real-time interaction capabilities and overall efficiency.

https://openai.com/index/hello-gpt-4o