Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • Clef is based on Qwen3.8-27B and Clef-flash is based on Qwen3.8-9B (edit: actually Qwen3.5-9B). So, similar in spirit to Kev by my understanding, but based on a newer model.
    by bityard
  • Since it supports vision, I tested it (an 8 bit quant) against one of my pet problems of coin classification (US coins, but not beauty shots of them, just lots of cell phone images on a piece of paper). It did .. horribly. About 41% accuracy. My local gemma4:27b gets 53% and runs 4x faster. Not too surprising but seemed worth poking at it.
    by dgacmu
  • Pricing is $0.24/million input tokens which is ~6x compared to Jev. Clef-flash is at $0.09 which is way more competitive.
    by ssiddharth
  • I'm a big fan of Cloudflare products. I recently stuck Jev in front of a Cloudflare-hosted Ollama model for chat/username moderation, so I was excited to test out Clef. The setup is user send a message -> Jev does first pass to see if it's toxic/hate speech/profane, if Jev is unsure then Ollama on Workers AI takes a deeper look.

    Clef was 2-3x slower and worse (it caught less hate speech) than Jev. Overall disappointing.

    by agrippanux
  • Unrelated to the subject matter, but something that I never fail to appreciate is just how well-written the majority of Cloudflare's posts are. (There was an article on Merkle Tree Certificates which was phenomenal.) There is real skill in creating an informative work which condenses complex technical subject matter into something that a technically-inclined non-expert can understand.
    by djray
  • Jev = $0.042/m input, output free Clef = $0.24/m input, no output price listed

    At 300 tokens per call, you'd get:

    One million decisions on Jev cost about $12.60. One million decisions on Clef cost about $72.

    Would probably make sense to self-host Clef, if you have the capability/resources. If not...

    by vulture916
  • Open weights, not open source.

    The weights have permissive licensing, but the data and training pipeline are not published to reproduce them from their proprietary Qwen starting points. Weights are not "source."

    by buildbuildbuild
  • Am I hearing this right, that they made a decision model based on Typesafe's new paradigm, and actually made a model better than Jev based on Typesafe's own ranking?

    And it's only been a few weeks.

    by manlymuppet

Explore Birbla archives