gpt-realtime-1.5
Ai Toolgpt-realtime-1.5 is an OpenAI large-language model tuned for ultra-low-latency streaming and conversational use through the OpenAI Realtime API. It is aimed at developers building chat, voice, or agent loops that require fast first-token times and continuous token delivery.
Stories
Completed digest stories linked to this service.
-
OpenAI turns Responses API into an agent runtime, solidifies Sora Videos API, an...2026-03-28OpenAI is shifting from raw endpoints to a hosted runtime for agents and media, with meaningful APIs and some ...
-
Agents JS v0.8.0 ships realtime default upgrade; pair it with prompt caching and...2026-03-23OpenAI’s agents JS library quietly upgraded realtime defaults and stabilized MCP, while new guidance and resea...
-
Realtime LLMs: OpenAI ships gpt-realtime-1.5, benchmarks reframe “fast,” Grok sh...2026-03-12OpenAI’s gpt-realtime-1.5 went live as new analysis and incidents reset expectations for real-time LLM speed, ...
-
Agent stack gets real: Copilot CLI adds MCP controls, LangChain supports OpenAI ...2026-03-11Agent tooling just got more practical: Copilot CLI adds MCP and safety controls, LangChain supports OpenAI com...
-
OpenAI speeds up agent backends with Responses API WebSockets and gpt‑realtime‑1...2026-02-24OpenAI shipped a faster path for real-time, tool-calling agents by adding WebSockets to the Responses API and ...