--- title: Cloudflare releases Clef, open-weight decision models,... description: Cloudflare has released Clef and Clef-flash, open-weight decision models hosted on Workers AI, designed for fast, deterministic structured classification used... canonical: https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Cloudflare releases Clef, open-weight decision models, and an RL fine-tuning service | daily.dev og:description: Cloudflare has released Clef and Clef-flash, open-weight decision models hosted on Workers AI, designed for fast, deterministic structured classification used... og:url: https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262 og:image: https://api.daily.dev/og/posts/Q5KWww262.png og:image:alt: Cloudflare releases Clef, open-weight decision models, and an RL fine-tuning service 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. # Cloudflare releases Clef, open-weight decision models, and an RL fine-tuning service **[Collections](https://daily.dev/sources/collections)** · 2 min read · 1 upvotes · 0 comments ## Summary Cloudflare has released Clef and Clef-flash, open-weight decision models hosted on Workers AI, designed for fast, deterministic structured classification used in routing and gating decisions within agentic workflows. Built on a Qwen backbone with a non-autoregressive, prefill-only scoring approach, Cloudflare claims the models beat Typesafe AI's Jev model and general-purpose LLMs like gpt-oss-120b on accuracy and latency, though these are self-reported benchmarks. The models are Jev-API compatible, Apache 2.0 licensed, and downloadable from Hugging Face. Cloudflare also launched a reinforcement learning fine-tuning service, starting with forward-deployed engineers before a self-serve platform arrives, built on AI Gateway, Containers, and a new Trainer component. LangChain's Harrison Chase praised the open-weight approach, arguing decision models should be as swappable as the main model in an agent harness. ## Content Cloudflare has released two decision models, Clef and Clef-flash, trained by its Workers AI team. Both are hosted on Workers AI, and the weights are on Hugging Face under Apache 2.0. ## What they do Decision models handle fast, deterministic structured classification, the kind of small routing and labeling steps that agentic workflows run constantly. Clef is built on a Qwen backbone. It doesn't generate text token by token. It uses a non-autoregressive, prefill-only scoring approach, which is where the speed comes from. Cloudflare says Clef beats Typesafe AI's Jev model and general-purpose LLMs like gpt-oss-120b on accuracy and latency across dozens of benchmarks. Those are Cloudflare's own numbers. The models are also Jev-API compatible, so existing Jev integrations should be easy to move over. ## Running it locally The open weights are already getting used. @lucataco, in a post that @kentcdodds reposted, ran clef-flash locally on an M5 Max and noted that it can handle images. Georgi Gerganov's llama.cpp v0.6.0 release lists Clef support for both text and vision, per a repost from @antirez. ## RL fine-tuning Cloudflare is also launching a reinforcement learning fine-tuning service. It starts with a hands-on team of forward-deployed engineers. A self-serve platform comes later, built on AI Gateway, Containers, and a new Trainer component that redeploys fine-tuned models on Workers AI. ## Reaction Developers jumped on it quickly. @jamesqquick said Clef landed the week after Jev, and that he plans to use it in his recipe app to map unstructured recipe data to structured ingredients. @steipete said he'd never seen an idea spread so fast. @hwchase17 called it "decision model season" and credited @ritakozlov and the Cloudflare team for the open weights. His view: a harness should be able to swap its decision model as easily as its main model. I think that's the right bar. InfoQ's Renato Losio also covered the release. ## Questions this post answers ### What is Cloudflare's Clef model and what is it used for? Clef and Clef-flash are open-weight decision models released by Cloudflare on Workers AI, built on a Qwen backbone using a non-autoregressive, prefill-only scoring approach instead of token-by-token generation. They are designed for fast, deterministic structured classification, such as the routing and gating decisions agentic workflows make constantly. They are Apache 2.0 licensed, Jev-API compatible, and downloadable from Hugging Face. _Developers wiring decision models into agent harnesses can follow releases like Clef on daily.dev._ ### Is Cloudflare's Clef model faster than gpt-oss-120b for classification tasks? Cloudflare claims Clef and Clef-flash deliver higher accuracy and lower latency than general-purpose LLMs such as gpt-oss-120b, as well as Typesafe AI's Jev model, across dozens of benchmarks. These figures come from Cloudflare's own testing rather than independent verification, so they should be treated as vendor-reported claims pending outside validation. _Anyone comparing decision models for routing calls can track independent benchmarks like this on daily.dev._ ### What is Cloudflare's new reinforcement learning fine-tuning service? Cloudflare launched an RL fine-tuning service that initially works through a hands-on team of forward-deployed engineers, with a self-serve platform planned for later. The self-serve version will be built on AI Gateway, Containers, and a new Trainer component that redeploys fine-tuned models directly onto Workers AI. _Teams planning to fine-tune their own agent models can follow services like this as they evolve on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 2 comments across x (as of 2026-10-08). **TL;DR:** The small sample of replies is enthusiastic and curious, with developers expressing interest in trying out Clef for their own tooling. **Sentiment:** 70% positive · 30% mixed · 0% skeptical **The case for** - People are eager to integrate Clef into existing projects, like an orchestrator CLI used with Claude and Codex. **By community** - x (positive): The few replies express excitement and interest in adopting the new models for personal projects. **Highlights** > @jamesqquick I've been wanting to try this out. I've been making an oss Jev orchestrator cli to use with Claude and Codex. But now I guess I'm going to have to branch out > — [PeteCapeCod on x](https://x.com/PeteCapeCod/status/2107943027323105509) > @jamesqquick Love this > — [fayazara on x](https://x.com/fayazara/status/2107916934381785279) **Source threads** - [x](https://x.com/jamesqquick/status/2107916182263316799) · 0 points · 2 comments ## Similar posts on daily.dev - [Cloudflare Open Sources Decision Models for AI Agents](https://daily.dev/posts/cloudflare-open-sources-decision-models-for-ai-agents-bgwofrpdu) · InfoQ · 4 upvotes · 1 comments - [Cloudflare’s AI Platform: an inference layer designed for agents](https://daily.dev/posts/cloudflare-s-ai-platform-an-inference-layer-designed-for-agents-70umlv07w) · Cloudflare · 1 upvotes · 0 comments - [Cloudflare Workers AI: run LLMs without API keys](https://daily.dev/posts/cloudflare-workers-ai-run-llms-without-api-keys-sxc7e3lma) · Flavio Copes · 1 upvotes · 0 comments --- Tags: [#open-source](https://daily.dev/tags/open-source), [#ai-agents](https://daily.dev/tags/ai-agents), [#cloudflare](https://daily.dev/tags/cloudflare), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning) [View this post on daily.dev](https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262) ```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":"Cloudflare releases Clef, open-weight decision models, and an RL fine-tuning service","url":"https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262"},"datePublished":"2026-10-01T17:38:02.596Z","dateModified":"2026-10-08T07:06:44.300Z","description":"Cloudflare has released Clef and Clef-flash, open-weight decision models hosted on Workers AI, designed for fast, deterministic structured classification used...","isAccessibleForFree":true,"articleSection":"Collections","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":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,ai-agents,cloudflare,reinforcement-learning","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Cloudflare releases Clef, open-weight decision models, and an RL fine-tuning service"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/cloudflare-releases-clef-open-weight-decision-models-and-an-rl-fine-tuning-service-q5kwww262#faq","mainEntity":[{"@type":"Question","name":"What is Cloudflare's Clef model and what is it used for?","acceptedAnswer":{"@type":"Answer","text":"Clef and Clef-flash are open-weight decision models released by Cloudflare on Workers AI, built on a Qwen backbone using a non-autoregressive, prefill-only scoring approach instead of token-by-token generation. They are designed for fast, deterministic structured classification, such as the routing and gating decisions agentic workflows make constantly. They are Apache 2.0 licensed, Jev-API compatible, and downloadable from Hugging Face. Developers wiring decision models into agent harnesses can follow releases like Clef on daily.dev."}},{"@type":"Question","name":"Is Cloudflare's Clef model faster than gpt-oss-120b for classification tasks?","acceptedAnswer":{"@type":"Answer","text":"Cloudflare claims Clef and Clef-flash deliver higher accuracy and lower latency than general-purpose LLMs such as gpt-oss-120b, as well as Typesafe AI's Jev model, across dozens of benchmarks. These figures come from Cloudflare's own testing rather than independent verification, so they should be treated as vendor-reported claims pending outside validation. Anyone comparing decision models for routing calls can track independent benchmarks like this on daily.dev."}},{"@type":"Question","name":"What is Cloudflare's new reinforcement learning fine-tuning service?","acceptedAnswer":{"@type":"Answer","text":"Cloudflare launched an RL fine-tuning service that initially works through a hands-on team of forward-deployed engineers, with a self-serve platform planned for later. The self-serve version will be built on AI Gateway, Containers, and a new Trainer component that redeploys fine-tuned models directly onto Workers AI. Teams planning to fine-tune their own agent models can follow services like this as they evolve on daily.dev."}}]} ```