OpenAI extends prompt caching in API to 12 hours
OpenAI extends prompt caching in API to 12 hours
OpenAI has expanded prompt caching in its API: caches can now persist for up to 12 hours, and indefinitely for authorized Codex and Work users.
OpenAI has expanded prompt caching capabilities in its API. Prompt caches can now persist for up to 12 hours, while authorized users of Codex and Work can keep cache entries indefinitely.
This means developers can return to an older task after several hours and continue work with a guaranteed cache hit.
In practice, this reduces repeated context processing and can help avoid wasting usage limits.
More updates like this would be welcome.
Why it matters
AnalysisLonger prompt caching lowers repeated context-processing costs and makes long-running AI workflows more predictable, especially for developers working with large prompts and multi-hour sessions.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
OpenAI expands caching in Codex, Work and API
OpenAI made caching persistent in Codex and Work and added a 12-hour cache retention option in the API at twice the cost of 30-minute caching.
MiniMax releases M3.1 Flash model
MiniMax has officially released M3.1 Flash, a model that generates over 200 tokens per second, outperforms several Chinese models on AI-agent benchmarks, and is significantly cheaper than M3.
Prompt Caching & KV Cache Reuse
A technology utilized by modern inference engines and cloud APIs (Anthropic, OpenAI, DeepSeek, vLLM) that stores precomputed attention matrices (KV Cache) of static prefixes, reducing processing costs by 80–90% and decreasing time to first token (TTFT) by 4–8 times.
Prompt Caching Architecture & Economics
A methodology for designing prompts focused on maximizing hardware cache hits for prefixes (Prefix Caching) in Anthropic, OpenAI, and DeepSeek, achieving a 90% cost reduction and 80% speedup.
Complete Guide to Higgsfield Cinema Studio 4.0: Scene Management, Soul 2.0, and API Automation
In-depth practical breakdown of the major Higgsfield update: Cinema Studio 4.0, consistent characters with Soul 2.0, API-based generation, and a ready-to-use UGC pipeline.
Part I. AI Agent Architecture: The Foundations
The eleven foundational building blocks of modern autonomous agents: model taxonomy, the agentic runtime loop, advanced prompting, distillation, skills architecture, memory systems, function calling, and FinOps.