--- title: Baseten’s joey-1 makes AI decisions for a penny per... description: Baseten released joey-1, a 2B parameter open-weights 'decision model' that returns an answer and a probability instead of writing text. It costs $0.01 per... canonical: https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Baseten’s joey-1 makes AI decisions for a penny per million tokens | daily.dev og:description: Baseten released joey-1, a 2B parameter open-weights 'decision model' that returns an answer and a probability instead of writing text. It costs $0.01 per... og:url: https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq og:image: https://api.daily.dev/og/posts/YmLfXGroQ.png og:image:alt: Baseten’s joey-1 makes AI decisions for a penny per million tokens 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. # Baseten’s joey-1 makes AI decisions for a penny per million tokens **[The Next Web](https://daily.dev/sources/tnw)** · 2 min read · 1 upvotes · 0 comments ## Summary Baseten released joey-1, a 2B parameter open-weights 'decision model' that returns an answer and a probability instead of writing text. It costs $0.01 per million tokens and answers a typical 2,000-token request in about 20 milliseconds, roughly 2.5 times faster than elephant-1. Sorting 10 million support tickets a month would cost about $50, versus $500 on mammoth-1. Joey-1 is built on Alibaba's Qwen3.5-2B, trained on 6.21 million decision examples, and its weights are free on Hugging Face under the MIT license. Its model card ranks joey-1 37th of 230 models on the Jev Decision Index, the top score for models under 4B parameters, though the company has not published the tests behind its claim that it is the strongest decision model with 3B or fewer parameters. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much does Baseten's joey-1 decision model cost per million tokens? Joey-1 costs $0.01 per million tokens. It is a 2B parameter open-weights model built on Alibaba's Qwen3.5-2B that returns an answer with a probability score instead of generated text, answering a typical 2,000-token request in about 20 milliseconds. Its weights are free on Hugging Face under the MIT license. _Comparing costs across decision models like this is easier when tracking AI pricing news on daily.dev._ ### What is a decision model in AI and how is it different from a regular LLM? A decision model answers yes-or-no or multiple-choice questions with a probability score instead of generating free-form text, making it cheaper and faster for tasks like routing support tickets, spotting spam, or blocking harmful prompts. Baseten's joey-1 handles a 2,000-token request in about 20 milliseconds, roughly 2.5 times faster than its larger elephant-1 model. _Developers weighing decision models against general LLMs can follow these comparisons on daily.dev._ ### How does Baseten's joey-1 compare to Microsoft's decision model on cost? Joey-1 costs $0.01 per million tokens, while Microsoft's own decision model, also built on Qwen, is priced at $0.042 per million tokens. Joey-1 ranks 37th of 230 models on the Jev Decision Index, the top score among models under 4B parameters. _Picking between competing low-cost AI models gets easier by following pricing updates on daily.dev._ ## Similar posts on daily.dev - [Companies rein in AI spending as running costs mount](https://daily.dev/posts/companies-rein-in-ai-spending-as-running-costs-mount-1dwposyjf) · TechCentral · 0 upvotes · 0 comments - [MiniMax M2.5: low costs, high performance, relaunches the Chinese AI geopolitical challenge](https://daily.dev/posts/minimax-m2-5-low-costs-high-performance-relaunches-the-chinese-ai-geopolitical-challenge-mhwdnr3ic) · Codemotion · 4 upvotes · 0 comments - [Microsoft separates decision-making from generative AI with a new model](https://daily.dev/posts/microsoft-separates-decision-making-from-generative-ai-with-a-new-model-z7lrvkhp8) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#open-source](https://daily.dev/tags/open-source), [#qwen](https://daily.dev/tags/qwen) [View this post on daily.dev](https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq) ```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":"Baseten’s joey-1 makes AI decisions for a penny per million tokens","url":"https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq"},"datePublished":"2026-10-29T18:58:51.618Z","dateModified":"2026-10-31T13:30:30.606Z","description":"Baseten released joey-1, a 2B parameter open-weights 'decision model' that returns an answer and a probability instead of writing text. It costs $0.01 per...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6d61a1b31fcb5f43661235ff6c2a8b35?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6d61a1b31fcb5f43661235ff6c2a8b35?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Next Web","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 Next Web","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tnw","url":"https://daily.dev/sources/tnw"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,qwen","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Next Web","item":"https://daily.dev/sources/tnw"},{"@type":"ListItem","position":3,"name":"Baseten’s joey-1 makes AI decisions for a penny per million tokens"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/baseten-s-joey-1-makes-ai-decisions-for-a-penny-per-million-tokens-ymlfxgroq#faq","mainEntity":[{"@type":"Question","name":"How much does Baseten's joey-1 decision model cost per million tokens?","acceptedAnswer":{"@type":"Answer","text":"Joey-1 costs $0.01 per million tokens. It is a 2B parameter open-weights model built on Alibaba's Qwen3.5-2B that returns an answer with a probability score instead of generated text, answering a typical 2,000-token request in about 20 milliseconds. Its weights are free on Hugging Face under the MIT license. Comparing costs across decision models like this is easier when tracking AI pricing news on daily.dev."}},{"@type":"Question","name":"What is a decision model in AI and how is it different from a regular LLM?","acceptedAnswer":{"@type":"Answer","text":"A decision model answers yes-or-no or multiple-choice questions with a probability score instead of generating free-form text, making it cheaper and faster for tasks like routing support tickets, spotting spam, or blocking harmful prompts. Baseten's joey-1 handles a 2,000-token request in about 20 milliseconds, roughly 2.5 times faster than its larger elephant-1 model. Developers weighing decision models against general LLMs can follow these comparisons on daily.dev."}},{"@type":"Question","name":"How does Baseten's joey-1 compare to Microsoft's decision model on cost?","acceptedAnswer":{"@type":"Answer","text":"Joey-1 costs $0.01 per million tokens, while Microsoft's own decision model, also built on Qwen, is priced at $0.042 per million tokens. Joey-1 ranks 37th of 230 models on the Jev Decision Index, the top score among models under 4B parameters. Picking between competing low-cost AI models gets easier by following pricing updates on daily.dev."}}]} ```