Topic · 5 stories
5 stories tagged responses-api on AI Tamer, newest first.
OpenAI explained its four-layer misalignment monitoring. Tool-using Responses API traffic is watched too, with auto-pause and webhooks.
Mistral's stateless /v1/responses endpoint returns the answer, reasoning and tool calls as separate items, for its hosted chat models including Large 4.
Xint got raw GPT-5.6 Sol reasoning out via the /responses/compact step, bypassing August's fix. Xint says OpenAI fixed it server-side on 23 October.
Since 20 October, GPT-5.6 and later can hold a cached prefix for at least 12 hours in the Responses API. Writes cost 2.5x input; read prices are unchanged.
A chat can carry its own history or ask the API to keep the thread. The choice changes what your application stores, sends, and checks on every turn.
