Last refreshed 2026-05-19. Next refresh: weekly.
Why use GPT-4o Realtime Preview (12-17) on OpenAI API?
OpenAI API offers GPT-4o Realtime Preview (12-17) with competitive pricing. OpenAI is a leading AI research and deployment company dedicated to developing safe and beneficial artificial general intelligence (AGI) for humanity.
Setup recipe
Python + curlpip install openaiexport OPENAI_API_KEY=...import os
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY from env
response = client.chat.completions.create(gpt-4o-realtime-preview-2024-12-17Request example
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)Gotchas
- Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".
- The examples expect OPENAI_API_KEY; rename it only if your application config maps the new variable.
Capabilities
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.
FAQ
What is the context window for GPT-4o Realtime Preview (12-17) on OpenAI API?
GPT-4o Realtime Preview (12-17) supports a 128k token context window on OpenAI API.
What API model ID do I use for GPT-4o Realtime Preview (12-17) on OpenAI API?
Use the model ID gpt-4o-realtime-preview-2024-12-17 when calling OpenAI API's API.
Who created GPT-4o Realtime Preview (12-17)?
GPT-4o Realtime Preview (12-17) was created by OpenAI as part of the GPT-4o Realtime model family.
Is GPT-4o Realtime Preview (12-17) open source?
GPT-4o Realtime Preview (12-17) is not open source; the seed data lists it as proprietary.