LLM Reference
OpenAI API

gpt-realtime on OpenAI API

GPT Realtime · OpenAI

Serverless

Last refreshed 2026-05-10. Next refresh: weekly.

Why use gpt-realtime on OpenAI API?

OpenAI API offers gpt-realtime with pay-as-you-go pricing at $4.00/1M input tokens. OpenAI is a leading AI research and deployment company dedicated to developing safe and beneficial artificial general intelligence (AGI) for humanity.

Input / 1M
$4.00
Output / 1M
$16.00
Cache
read $0.40
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export OPENAI_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI()  # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
Model ID
gpt-realtime

Request example

import os
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
    model="gpt-realtime",
    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.

Pricing

TypePrice (per 1M)
Input tokens$4.00
Output tokens$16.00
Image input$5.00
Audio input$32.00

Capabilities

MultimodalAudio

About gpt-realtime

Realtime model capable of text and audio inputs and outputs via the Realtime API.

FAQ

What does gpt-realtime cost on OpenAI API?

On OpenAI API, gpt-realtime costs $4.00 per 1M input tokens and $16.00 per 1M output tokens.

What is the context window for gpt-realtime on OpenAI API?

gpt-realtime supports a 32k token context window on OpenAI API.

What API model ID do I use for gpt-realtime on OpenAI API?

Use the model ID gpt-realtime when calling OpenAI API's API.

Who created gpt-realtime?

gpt-realtime was created by OpenAI as part of the GPT Realtime model family.

Is gpt-realtime open source?

gpt-realtime is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2025-10-06
Context32k
ArchitectureDecoder Only
Knowledge cutoff2023-10

Related Models on OpenAI API