Logo
Back to all models

GPT-4o Realtime - In-Depth Overview

OpenAI · GPT-4o

preview

Model ID: gpt-4o-realtime-preview

Get all the details on GPT-4o Realtime, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as multimodal_input, function_calling, realtime_text_input, available API code samples, and performance strengths.

Key Metrics

Input Limit

128K tokens

Output Limit

4.1K tokens

Input Cost

$5.00/1M

Output Cost

$20.00/1M

Sample API Code

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o-realtime-preview",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    stream=True
)
for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")

Required Libraries

openai
openai

Notes

Model capable of realtime text and audio inputs and outputs over WebRTC or a WebSocket interface. This is a preview release. Structured outputs, distillation, and predicted outputs are not supported.

Supported Data Types

Input Types

text
audio

Output Types

text
audio

Strengths & Weaknesses

Exceptional at

realtime audio processing
realtime text processing
low latency conversations

Good at

function calling

Poor at

structured outputs
fine tuning
distillation
predicted outputs

Additional Information

Latest Update

Dec 17, 2024

Knowledge Cutoff

Oct 1, 2023