GPT Realtime
JSON →A low-latency model optimized for real-time conversational applications and streaming interactions.
Specs
context window 32K tokens
max output 4K tokens
input price $4 / 1M tokens
output price $16 / 1M tokens
Capabilities
streamingtool-usefunction-calling
Dates
releasedDec 2024
knowledge cutoffOct 2024
Resources
API
full doc /v1/models/gpt-realtime