GPT Realtime 1.5
JSON →An improved version of GPT Realtime with enhanced latency and audio quality for voice applications.
Specs
context window 32K tokens
max output 4K tokens
input price $4 / 1M tokens
output price $16 / 1M tokens
Capabilities
streamingtool-usefunction-calling
Dates
releasedJun 2025
knowledge cutoffMar 2025
Resources
API
full doc /v1/models/gpt-realtime-1.5