Decisions API (1 minute read)

TLDR AI Tools

Summary

OpenAI developers' thread-reader roundup highlighting developer updates around the Decisions API, alongside other announcements like GPT-Live-1, Codex skills, and the open-source Open Responses spec.

OpenAI's Decisions API, powered by GPT-6 Luna, is now available in limited preview. Users define questions and possible answers, and the model classifies content, routes requests, or chooses an agent's next action. Text and images can be used as context. Preview access is limited to selected API customers for testing. A broad release is planned in the coming days.
Original Article
View Cached Full Text

Cached at: 09/30/26, 02:53 PM

# Thread by @OpenAIDevs on Thread Reader App Source: [https://threadreaderapp.com/thread/2105003318917697873.html](https://threadreaderapp.com/thread/2105003318917697873.html) ## More from @OpenAIDevs [![OpenAI Developers Profile picture](https://pbs.twimg.com/profile_images/2022002720971096064/l3Kyt4qt_bigger.jpg)](https://threadreaderapp.com/user/OpenAIDevs) Sep 10 GPT\-Live\-1 is now available in the API\. Bring ChatGPT’s natural back\-and\-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose\. ![Video Poster](https://pbs.twimg.com/media/HR3yP3KaAAAHECk.jpg) GPT\-Live\-1 finally makes conversations fluid\. It distinguishes speech from background noise, so café chatter doesn’t have to stop the conversation ☕ You can even add a detail you just thought of or change direction mid\-conversation without waiting for the model to finish its speaking turn\. ![Video Poster](https://pbs.twimg.com/media/HR3yUB2acAA65LB.jpg) GPT\-Live\-1 handles listening and speaking in one model, cutting out extra handoffs so the conversation moves fasterrrrrrr 🏎️ And you can keep talking while your backend model handles reasoning and tool calls\. ![Video Poster](https://pbs.twimg.com/media/HR3yamMbsAAnIgZ.jpg) Read 5 tweets [![OpenAI Developers Profile picture](https://pbs.twimg.com/profile_images/2022002720971096064/l3Kyt4qt_bigger.jpg)](https://threadreaderapp.com/user/OpenAIDevs) May 16 We’re having way too much fun working through your feedback\. \(Please, keep it coming\.\) Keyboard shortcuts are now customizable\. Set Codex up around how you actually work, then tweak shortcuts from settings instead of adapting to our defaults\. ![Video Poster](https://pbs.twimg.com/media/HIdjX0DaYAALhYp.jpg) Git actions are easier to reach\. We moved key git controls back into the review flow, so common actions like commit, push, branch, PR creation, and PR status are closer to where you’re already working\. ![Video Poster](https://pbs.twimg.com/media/HIdjbwZagAAB9Yv.jpg) Improved thread panel\. Related context and controls now load and behave more cleanly from the thread header: summaries, local state, Git context, sources, and more\. ![Video Poster](https://pbs.twimg.com/media/HIdjg81bgAAYP6a.jpg) Read 5 tweets [![OpenAI Developers Profile picture](https://pbs.twimg.com/profile_images/2022002720971096064/l3Kyt4qt_bigger.jpg)](https://threadreaderapp.com/user/OpenAIDevs) Jan 15 Today we’re announcing Open Responses: an open\-source spec for building multi\-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API\. ✅ Multi\-provider by default ✅ Useful for real\-world workflows ✅ Extensible without fragmentation Build agentic systems without rewriting your stack for every model:[openresponses\.org](http://openresponses.org/) ![Video Poster](https://pbs.twimg.com/amplify_video_thumb/2011862892585623552/img/hctjghclCKQ8KAxt.jpg) Read 4 tweets [![OpenAI Developers Profile picture](https://pbs.twimg.com/profile_images/2022002720971096064/l3Kyt4qt_bigger.jpg)](https://threadreaderapp.com/user/OpenAIDevs) Dec 19, 2025 🆕 Codex now officially supports skills Skills are reusable bundles of instructions, scripts, and resources that help Codex complete specific tasks\. You can call a skill directly with $\.skill\-name, or let Codex choose the right one based on your prompt\. Following the[agentskills\.io](http://agentskills.io/)standard, a skill is just a folder:[SKILL\.md](http://skill.md/)for instructions \+ metadata, with optional scripts, references, and assets\. We’re looking forward to collaborating on the standard so it’s easy to share and use skill across different tools\.[![Screenshot of a folder tree layout for a skill](https://threadreaderapp.com/images/1px.png)](https://pbs.twimg.com/media/G8jULsYWUAAM6JA.jpg) You can install scripts for just yourself in \(~/\.codex/skills\), or for everyone working on a project in \(repo\_path/\.codex/skills\)\. We’ve also bundled a few handy system skills with Codex, such as plan, skill\-creator, and skill\-installer\. [developers\.openai\.com/codex/skills](https://developers.openai.com/codex/skills)[![Screenshot of the Codex CLI with the skill selector open](https://threadreaderapp.com/images/1px.png)](https://pbs.twimg.com/media/G8jUh_kWAAA89U9.jpg) Read 7 tweets [![OpenAI Developers Profile picture](https://pbs.twimg.com/profile_images/2022002720971096064/l3Kyt4qt_bigger.jpg)](https://threadreaderapp.com/user/OpenAIDevs) Nov 7, 2025 You can now get more Codex usage from your plan and credits with three updates today: 1️⃣ GPT\-5\-Codex\-Mini — a more compact and cost\-efficient version of GPT\-5\-Codex 2️⃣ 50% higher rate limits for ChatGPT Plus, Business, and Edu 3️⃣ Priority processing for ChatGPT Pro and Enterprise GPT\-5\-Codex\-Mini allows roughly 4x more usage than GPT\-5\-Codex, at a slight capability tradeoff due to the more compact model\. Available in the CLI and IDE extension when you sign in with ChatGPT, with API support coming soon\.[![Image](https://threadreaderapp.com/images/1px.png)](https://pbs.twimg.com/media/G5K8HGWWgAAKhQy.jpg) Select GPT\-5\-Codex\-Mini for easier tasks or to extend usage when you’re close to hitting rate limits\. Codex will also suggest switching to it when you reach 90% of your limits, so you can work longer without interruptions\.[![Image](https://threadreaderapp.com/images/1px.png)](https://pbs.twimg.com/media/G5K8eEqWMAAevck.jpg) Read 4 tweets

Similar Articles

Decisions API is now available in Public Beta (1 minute read)

TLDR AI

OpenAI 发布 Decisions API 公测版,宣称决策速度比 GPT-6 Luna 通过 Responses API 快最多 10 倍,支持文本与图像输入以及 predicates、choices、scores 三种输出,定价为每 100 万输入 token 0.10 美元且无缓存与输出 token 费用。

Decisions API is in public beta

Hacker News Top

OpenAI 的 Decisions API 进入公开测试版,可对文本、图像或两者进行评估并返回类型化答案,速度约为 Responses API 的 10 倍,目前仅支持 gpt-6-luna 模型,预计数周内正式发布。

llm-openai-decisions 0.1a0

Simon Willison's Blog

Simon Willison released llm-openai-decisions 0.1a0, an LLM plugin for OpenAI's new Decisions API, which supports predicate/choice/score question types and, via the gpt-6-luna model, image input alongside text.