OpenAI has updated its API, moving most reasoning-capable models to a new endpoint that supports interleaved reasoning across tool calls. This change allows users to view summarized reasoning tokens, which are displayed distinctly from standard errors. The new functionality is available for GPT-5 class models and can be toggled on or off using specific flags. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Enables more transparent and controllable reasoning for advanced AI models, potentially improving agentic workflows.
RANK_REASON This is an API update and feature enablement for existing models, not a new model release.