Clef
Clef is a 27B parameter multimodal decision model that processes inputs like text, JSON, images, or video to produce structured classification outputs for automated decision-making. Hosted on Workers AI, Clef enables faster, more accurate classification than traditional LLMs. It is fully compatible with Jev APIs and open-sourced under Apache 2.0 license on Hugging Face. Additionally, Clef supports reinforcement learning fine-tuning with custom data, empowering developers to tailor models to specific use cases.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
Website checks
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 25, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 74 out of 100, Needs improvement
- Accessibility
- 95 out of 100, Good
- Best Practices
- 96 out of 100, Good
- SEO
- 100 out of 100, Good
Around the Web
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?
dalemooney · Imported from Product Hunt
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?
galdayan · Imported from Product Hunt