Fable 5 and Mythos 5 access suspended temporarily Gemini can help with research and literature work Use natural real-time speech translation in 70+ languages right away Claude Fable 5 makes hard work easier to hand off Use real-time voice translation in 70+ languages Google Cloud makes AI threat response easier to manage Claude is better at tough knowledge work and coding Low-latency live voice translation gets easier Use Colab from the terminal to get compute fast Preferences and schedules remembered automatically, reducing repeated explanations Use a high-performance multimodal model on laptops Find the right Claude implementation partner faster Project Glasswing expands to more critical software Let Codex watch and work on Windows tasks Use OpenAI inside existing AWS operations more easily Anthropic raises $65B in Series H funding Claude Opus 4.8 now available on web and API Anthropic releases Claude Opus 4.8 with faster workflows Claude stays steadier during longer work sessions Claude Opus 4.8 is better for long, complex work Fable 5 and Mythos 5 access suspended temporarily Gemini can help with research and literature work Use natural real-time speech translation in 70+ languages right away Claude Fable 5 makes hard work easier to hand off Use real-time voice translation in 70+ languages Google Cloud makes AI threat response easier to manage Claude is better at tough knowledge work and coding Low-latency live voice translation gets easier Use Colab from the terminal to get compute fast Preferences and schedules remembered automatically, reducing repeated explanations Use a high-performance multimodal model on laptops Find the right Claude implementation partner faster Project Glasswing expands to more critical software Let Codex watch and work on Windows tasks Use OpenAI inside existing AWS operations more easily Anthropic raises $65B in Series H funding Claude Opus 4.8 now available on web and API Anthropic releases Claude Opus 4.8 with faster workflows Claude stays steadier during longer work sessions Claude Opus 4.8 is better for long, complex work

Official sources only. Rumors, leaks, and get-rich schemes are excluded.

← Back to top

AI BriefingOpenAIFeature Updates21:05

AI summarized from verified sources

OpenAI Launches WebSocket Mode in Responses API for Faster Agents

Cuts agent latency 40%, enabling real-time business tools easily.

SOURCE CHECK

2 sources

VERIFIED

Sources

Primary / openai.com

Official Blog

Supporting / x.com

Official Blog

Key Points

1Caches state to minimize API overhead.
2Up to 4K tokens/sec with GPT-5.3-Codex-Spark.
3Keeps familiar API with previous_response_id.
439% faster in alpha tests.

OpenAI introduced persistent WebSocket connections in Responses API, caching conversation state to cut redundant processing in tool calls. Agent workflows speed up by up to 40%, letting devs build faster apps. Proven in alpha with Vercel and Cursor.

What changed

OpenAI introduced persistent WebSocket connections in Responses API, caching conversation state to cut redundant processing in tool calls. Agent workflows speed up by up to 40%, letting devs build faster apps. Proven in alpha with Vercel and Cursor.

Why it matters

Cuts agent latency 40%, enabling real-time business tools easily.

What to watch

Cuts agent latency 40%, enabling real-time business tools easily. Key checks: Caches state to minimize API overhead. / Up to 4K tokens/sec with GPT-5.3-Codex-Spark. / Keeps familiar API with previous_response_id..