Using GPT-4o Realtime Preview (12-17) on OpenAI API
Implementation guide · GPT-4o Realtime · OpenAI
Serverless
OpenAI API exposes GPT-4o Realtime Preview (12-17) through model ID gpt-4o-realtime-preview-2024-12-17. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-05-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the OpenAI API SDK or REST API to call
gpt-4o-realtime-preview-2024-12-17— see the documentation for request format.
Code Examples
Install
pip install openaiAPI key
OPENAI_API_KEYModel ID
gpt-4o-realtime-preview-2024-12-17Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".
import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
model="gpt-4o-realtime-preview-2024-12-17",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on OpenAI API
Capabilities
VisionCode ExecutionAudio
About GPT-4o Realtime Preview (12-17)
GPT-4o Realtime Preview (12-17) is OpenAI's GPT-4o Realtime model. It is deprecated (originally released 2024-12-17); use it only for reproducing earlier results or evaluating drift over time.
Model Specs
Released2024-12-17
Context128k
ArchitectureDecoder Only
Knowledge cutoff2024-06