Key Metrics
Input Limit
128K tokens
Output Limit
4.1K tokens
Input Cost
$0.60/1M
Output Cost
$2.40/1M
Sample API Code
Refer to OpenAI Python library documentation.Required Libraries
openai
openai
Notes
Specific snapshot version of GPT-4o mini Realtime, dated 2024-12-17. Snapshots let you lock in a specific version of the model so that performance and behavior remain consistent. Use for locking in a specific model version for consistent performance and behavior.
Capabilities
realtime interaction
text input
audio input
text output
audio output
function calling
Supported Data Types
Input Types
text
audio
Output Types
text
audio
Strengths & Weaknesses
Exceptional at
Realtime audio interaction
Realtime text interaction
Very fast response speed
Good at
Conversational AI
Function calling
General tasks at average intelligence
Poor at
Image processing (not supported)
Structured outputs (not supported)
Fine-tuning (not supported)
Distillation (not supported)
Predicted outputs (not supported)
Additional Information
Latest Update
Dec 17, 2024
Knowledge Cutoff
Oct 01, 2023