--- title: OpenAI answers TypeSafe’s Jev with a Decision API built... description: OpenAI announced a Decisions API at its DevDay conference, seemingly in response to the sudden popularity of TypeSafe's Jev decision model. Built on OpenAI's... canonical: https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenAI answers TypeSafe’s Jev with a Decision API built on Luna | daily.dev og:description: OpenAI announced a Decisions API at its DevDay conference, seemingly in response to the sudden popularity of TypeSafe's Jev decision model. Built on OpenAI's... og:url: https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk og:image: https://api.daily.dev/og/posts/STTLgbzXk.png og:image:alt: OpenAI answers TypeSafe’s Jev with a Decision API built on Luna og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI answers TypeSafe’s Jev with a Decision API built on Luna **[The New Stack](https://daily.dev/sources/newstack)** · 3 min read · 0 upvotes · 0 comments ## Summary OpenAI announced a Decisions API at its DevDay conference, seemingly in response to the sudden popularity of TypeSafe's Jev decision model. Built on OpenAI's small Luna model, the API returns predefined answers with confidence scores rather than chat-style prose, aiming at use cases like content classification, request routing, and agent action selection. OpenAI claims a 150ms response time versus 1.6 seconds for GPT-6 Luna, but details like pricing, candidate limits, and fine-tuning options remain undisclosed. The API is in limited preview with broad rollout planned soon. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is OpenAI's new Decisions API and how is it different from a chat model? The Decisions API is a new OpenAI offering, built on the small Luna model, that returns predefined answers with confidence scores instead of chat-style prose. It is designed for classifying content, routing requests, or picking an agent's next action from a limited set of choices, returning results in about 150 milliseconds compared to 1.6 seconds for GPT-6 Luna. It launched in limited preview at OpenAI's DevDay conference, with broad rollout planned soon and pricing not yet disclosed. _Developers weighing decision models over prompt-based classifiers can track rollout details for this API on daily.dev._ ### How fast is OpenAI's Decisions API compared to using GPT-6 Luna for classification? OpenAI's Decisions API returns results in 150 milliseconds, versus 1.6 seconds for GPT-6 Luna performing a similar classification task through a prompt. This speed comes from using a purpose-built decision model rather than a general chat model, making it suited for latency-sensitive tasks like request routing or agent action selection. _Teams optimizing latency in classification pipelines can follow benchmarks like this on daily.dev._ ### What is TypeSafe's Jev and why did it prompt OpenAI to build a competing product? TypeSafe's Jev is a decision model that saw a sudden surge in popularity, prompting OpenAI to quickly announce its own competing Decisions API at its DevDay conference. OpenAI reportedly rushed the announcement ahead of schedule in response, though full details on pricing and capabilities are still being withheld until broad rollout. _Anyone comparing decision-model options like Jev and OpenAI's new API can follow the competitive landscape on daily.dev._ --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#openai](https://daily.dev/tags/openai) [View this post on daily.dev](https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI answers TypeSafe’s Jev with a Decision API built on Luna","url":"https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk"},"datePublished":"2026-09-29T17:18:26.696Z","dateModified":"2026-09-30T22:29:03.912Z","description":"OpenAI announced a Decisions API at its DevDay conference, seemingly in response to the sudden popularity of TypeSafe's Jev decision model. Built on OpenAI's...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/39d11ea726b3cb684d129a5b61af9a21?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/39d11ea726b3cb684d129a5b61af9a21?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,openai","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"OpenAI answers TypeSafe’s Jev with a Decision API built on Luna"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/openai-answers-typesafe-s-jev-with-a-decision-api-built-on-luna-sttlgbzxk#faq","mainEntity":[{"@type":"Question","name":"What is OpenAI's new Decisions API and how is it different from a chat model?","acceptedAnswer":{"@type":"Answer","text":"The Decisions API is a new OpenAI offering, built on the small Luna model, that returns predefined answers with confidence scores instead of chat-style prose. It is designed for classifying content, routing requests, or picking an agent's next action from a limited set of choices, returning results in about 150 milliseconds compared to 1.6 seconds for GPT-6 Luna. It launched in limited preview at OpenAI's DevDay conference, with broad rollout planned soon and pricing not yet disclosed. Developers weighing decision models over prompt-based classifiers can track rollout details for this API on daily.dev."}},{"@type":"Question","name":"How fast is OpenAI's Decisions API compared to using GPT-6 Luna for classification?","acceptedAnswer":{"@type":"Answer","text":"OpenAI's Decisions API returns results in 150 milliseconds, versus 1.6 seconds for GPT-6 Luna performing a similar classification task through a prompt. This speed comes from using a purpose-built decision model rather than a general chat model, making it suited for latency-sensitive tasks like request routing or agent action selection. Teams optimizing latency in classification pipelines can follow benchmarks like this on daily.dev."}},{"@type":"Question","name":"What is TypeSafe's Jev and why did it prompt OpenAI to build a competing product?","acceptedAnswer":{"@type":"Answer","text":"TypeSafe's Jev is a decision model that saw a sudden surge in popularity, prompting OpenAI to quickly announce its own competing Decisions API at its DevDay conference. OpenAI reportedly rushed the announcement ahead of schedule in response, though full details on pricing and capabilities are still being withheld until broad rollout. Anyone comparing decision-model options like Jev and OpenAI's new API can follow the competitive landscape on daily.dev."}}]} ```