Better prompt caching for GPT-6
Learn how GPT-6 improves prompt caching with higher cache hit rates, new diagnostics, explicit breakpoints, and controls that reduce latency and costs.
Get smart on it
GPT-6 includes an improved prompt caching system that reuses shared context across multiple API requests, reducing processing time and cutting costs by up to 90% on cached input tokens. OpenAI has introduced new tools including a dashboard to monitor cache performance and a diagnostics tool to identify why cached content is not being reused. Developers can now control caching more precisely through explicit cache breakpoints, adjust reasoning effort without losing cached context, and prewarm the cache before user requests arrive to reduce latency.
Related news
A Coding Guide to TypeSafe AI Jev: Typed Decisions, Calibrated Confidence, and Speculative Fan-Out with a System One Model
In this tutorial, we work with Jev, TypeSafe AI’s first System One model, which does not generate text at all: we send it a piece of program state and a set of typed questions, and it returns choices, scores, and yes/no probabilities that our code can branch on directly. We install the official Python SDK, make a first call that uses all three question primitives at once, and look at how the shape of the state changes what the model can know. We then recompute the published confidence sta
NVIDIA Releases Nemotron 3 Diarization: A 100M-Parameter Open-Weight Model That Tracks 8 Speakers in Real Time
NVIDIA has released Nemotron 3 Diarization, an open-weight speaker diarization model on Hugging Face. It answers one question about any conversation: who spoke when. The 100M-parameter model tracks up to 8 speakers, including when voices overlap. One checkpoint handles both offline recordings and real-time streaming. Is it deployable? Yes. The weights are released under the OpenMDW License 1.1, which permits commercial use. It runs on Linux through NVIDIA NeMo, using Ampere, Ada Lovelace, Ho
