GPT-Realtime-2.1 API
About
Build advanced reasoning agents with GPT-Realtime-2.1, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $4.00/1M input and $24.00/1M output tokens, native tool calling support. Access GPT-Realtime-2.1 via the OpenAI API with up to 32K output tokens.
Capabilities
Input Modalities
textaudioimage
Output Modalities
textaudio
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsClosed
Temperature
Fixed
Attachment
Supported
Limits
Context Window
128K
Tokens
Input Limit
96K
Tokens
Max Output
32K
Tokens
Pricing
Standard (per 1M tokens)
Input
$4.00
Output
$24.00
Caching (per 1M tokens)
Read
$0.40
Audio (per 1M tokens)
Input
$32.00
Output
$64.00
Frequently Asked Questions
GPT-Realtime-2.1 by OpenAI costs $4.00 per 1M input tokens and $24.00 per 1M output tokens. Cached reads cost $0.40 per 1M tokens.
Model Details
API Integration