GPT Realtime Mini
JSON →A compact, cost-efficient realtime model for lightweight voice and text streaming tasks.
Specs
context window 128K tokens
max output 4K tokens
input price $0.6 / 1M tokens
output price $2.4 / 1M tokens
Capabilities
streamingtool-usefunction-calling
Dates
releasedJun 2025
knowledge cutoffMar 2025
Resources
API
full doc /v1/models/gpt-realtime-mini