Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing. The Clef API is fully compatible with Jev and SystemOne.
funny timing, I was just in a forum thread this morning about Jev, a yes/no decision model someone uses for email triage, and I see it's literally a comparison point on your benchmark chart. makes sense now why that category exists as its own thing instead of just using a full LLM for every classification call. for Clef specifically, what's the fallback when the model is genuinely unsure, does it return a low-confidence flag you can route to a human, or does it just give you its best guess either way?
I run most of my side projects on Workers and D1 so having these sat right next to them is handy, no extra API to wire up. Can a fine tuned model be pulled out and run somewhere else, seeing as it's open source, or does the trained version only live on Workers AI?
About Clef on Product Hunt
“Open-source decision models from Cloudflare”
Clef launched on Product Hunt on October 2nd, 2026 and earned 128 upvotes and 4 comments, placing #9 on the daily leaderboard. Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing. The Clef API is fully compatible with Jev and SystemOne.
Clef was featured in Open Source (68.9k followers) and Artificial Intelligence (481.3k followers) on Product Hunt. Together, these topics include over 146.7k products, making this a competitive space to launch in.
Who hunted Clef?
Clef was hunted by Chris Messina. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Clef stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Chris Messina
So many decision models... so little time...! Oh I know!
Let's build a "Which Decision Model Should I Use?" app! 🤓