gpt-4o-realtime-preview

Common Name: GPT-4o Realtime Preview

OpenAI
Released on Oct 1, 2024 12:00 AMDeprecated Feb 27, 2026 12:00 AM

Preview version of GPT-4o supporting real-time audio and text streaming for conversational applications.

Specifications

Context128,000
Maximum Output4,096
Inputtext, audio
Outputtext, audio

Performance (7-day Average)

Uptime
TPS
RURT

Pricing

Input$5.50/MTokens
Cached Input$2.75/MTokens
Output$22.00/MTokens
Input Audio$44.00/MTokens
cached input audio$2.75/MTokens
Output Audio$88.00/MTokens

Usage Statistics

No usage data available for this model during the selected period
View your usage statistics for this model

Documentation

No documentation available
This model (gpt-4o-realtime-preview) uses a dedicated API. Please refer to the official documentation for usage examples.