AITOPAI热报
ProductsOfficialSelected

OpenAI adds 12-hour prompt caching to its API

官方一手@OpenAIDevs@OpenAIDevs
Post· 11 sources
View the post
Why we picked it

Longer cache windows change the economics of always-on agents, since hourly or daily recurring calls can now hit cached-input pricing instead of full-price tokens. Teams building background assistants or scheduled workflows on the OpenAI API should re-check their token spend, as cost drops apply to any workload with repeated shared context.

OpenAI announced a 12-hour prompt caching option for its API, up from the previous shorter cache window. Developers running persistent agents can keep shared instructions, tools and context cached for longer and pay the lower cached-input rate even when requests are hours apart. The announcement cites agents like dots, which reuse context throughout the day, as a primary beneficiary.

Original · @OpenAIDevs

You can now choose 12-hour prompt caching in the API. Persistent agents, like dots, reuse context throughout the day. You can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart. 💬 41 🔄 13 ❤️ 344 👀 16605 📊 76 ⚡

#OpenAI#prompt caching#agents

Keep reading

Recent stories with the same tag or section
ModelsUS vs ChinaMulti-sourceSelected10:07
Anthropic models lead completeness but trail OpenAI on medical benchmarks

Verbose medical answers earn completeness points but introduce more claims that can contradict the record, so length itself becomes an accuracy liability. Teams building clinical documentation or decision-support tools should weight length-adjusted scores over raw ones, since the top model changes depending on that choice. Against alternatives like GPT-6 Astra, Claude models suit use cases where covering every rubric point matters more than brevity.

#Claude Opus 5.5#Claude Sonnet 5.5#GPT-6 Astra#HealthBench
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource
ModelsUS vs ChinaMulti-sourceSelected01:00
GPT-6 Astra lifts low-resource coding languages on MultiLangBench

Legacy COBOL systems still run banking and government payroll worldwide, and a 97.9 percent migration accuracy claim suggests AI-assisted mainframe modernization is becoming practical rather than experimental. Teams maintaining COBOL or Fortran codebases should evaluate GPT-6.1 Sol against Anthropic's Claude and other coding assistants on their own migration test suites. The MultiLangBench scores also give enterprises a benchmark for comparing models beyond mainstream languages like Python.

#GPT-6#OpenAI#COBOL#coding assistants
Event
官方账号Decoder@Matthias Bastian11 sourcesSource
IndustryUS vs ChinaMulti-sourceSelected00:31
Intelligence Index thresholds now far cheaper per task, Artificial Analysis finds

The price of intelligence is collapsing at every fixed quality level while top-end capability prices keep climbing, so buyers face a widening spread between commodity and frontier performance. Teams benchmarking models should match their task's required score to the cheapest threshold model instead of defaulting to the highest scorer. The data also names concrete price leaders at each level, such as Claude Haiku 5.5 (xhigh) at US$0.12/task for a score of 41.

#Artificial Analysis#OpenAI#Anthropic#GPT-6
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource
IndustryBuildersMulti-sourceSelected23:46
Latent.space Retrospective of 2026 Technical AI Themes

The month-by-month structure makes it a compact index of which model releases, acquisitions and infrastructure shifts actually dominated 2026, useful for spotting what faded versus what compounded. Builders can mine it for tooling trends like MCP Apps and agent dispatch patterns. Chinese labs appear repeatedly through DeepSeek, Kimi and GLM releases, giving a side-by-side view against US lab moves.

#latent.space#OpenAI#Anthropic#DeepSeek
Event
Latent.Space@latentspacepod11 sourcesSource
How-toBuildersMulti-sourceSelected09:11
Space Bunny Max sets integer multiplication record on OpenAI benchmark

The free model's win suggests cheaper open or free models can contribute meaningfully to frontier auto-research when paired with verification from a paid model like Claude Opus 5.5. The jump in research-referencing PRs shows that a shared prompt file can coordinate an army of agents better than brute-force exploration. Practitioners running multi-agent research workflows can test the context-engineering tricks cited here, such as forking and context flushing, to escape local minima.

#Space Bunny Max#opencode#OpenAI#Claude Opus 5.5
Event
Jerry Liu@jerryjliu011 sourcesSource
How-toBuildersOfficialSelected13:36
OpenAI shows how to shape GPT-Live-1 voices via prompts

Voice personality is now a promptable parameter, meaning developers can differentiate voice apps without recording custom audio or training anything. The international preset voices lower the barrier for teams localising realtime voice apps for multilingual markets. Developers can experiment with prompt-written personas and pick presets that match their app's audience.

#GPT-Live-1#OpenAI#voice#prompt engineering
Event
官方一手@OpenAIDevs@OpenAIDevs7 sourcesSource