Compare models
GPT-Realtime-Whisper
Streaming speech-to-text model for realtime transcription
Performance
Speed
Input
Output
Reasoning tokens
Pricing
Realtime audio duration
Price / minute
$0.017
Input / 1M tokens
-
Cached input / 1M tokens
-
Cache writes / 1M tokens
-
Output / 1M tokens
-
Context
Window
16,000
Max Output Tokens
2,000
Knowledge Cutoff
Sep 30, 2024
Endpoints
v1/chat/completions
v1/responses
v1/realtime/transcription_sessions
v1/batch
Supported Features
Streaming
Function calling
Structured outputs
Image input
Rate Limits
Minutes-of-audio per minute
Free
-
Build
350
Launch
1,000
Grow
1,300
GPT-6 Astra
Our most capable model for the most demanding work.
Reasoning
Speed
Input
Output
Reasoning tokens
Pricing
Text tokens
Price / minute
-
Input / 1M tokens
$10.00
Cached input / 1M tokens
$1.00
Cache writes / 1M tokens
$12.50
Output / 1M tokens
$50.00
Context
Window
1,050,000
Max Output Tokens
128,000
Knowledge Cutoff
Apr 30, 2026
Endpoints
v1/chat/completions
v1/responses
v1/realtime/transcription_sessions
v1/batch
Supported Features
Streaming
Function calling
Structured outputs
Image input
Rate Limits
TPM
Free
-
Build
1,000,000
Launch
4,000,000
Grow
40,000,000