Clef: Open-source decision models, and new RL fine-tuning platform

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.

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...

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."

Pricing is $0.24/million input tokens which is ~6x compared to Jev. Clef-flash is at $0.09 which is way more competitive.

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.

For smaller scale decision model that runs on CPU, check https://news.ycombinator.com/item?id=49923223

> This contrasts with the world of Large Language Models (LLMs), which are largely non-deterministic, but are open-ended enough to reason...

This seems misleading. Decision models do not produce deterministic output. Repeated calls can product different decisions just like an LLM with structured outputs.

I’ll go out on a limb and suggest that I don’t think a Jev-like model is particularly useful unless you can fine tune it. The Jev API has zero ability to pass in a prior [0], and, if you can neither pass in a prior nor fine tune for your system, you will get an output that may be almost meaningless.

I’d love to see someone build a model of this sort that can actually accept priors and do something intelligent with them.

[0] You can feed Jev a prior as text. I’ve tried it. It works poorly.

This is awesome.

I bet the competition will result in research into how to make these decision models several more orders of magnitude faster and cheaper.

Here's a challenge problem - look at a 1M context window and produce N decisions (different queries) from it in 50-100ms.

A question someone not trainined in AI/ML field, Is a decision model that easy to crete that there are floods of these JEV alternatives already?

Or are companies/people already building this based on say an arXiv docs? n

---

The pricing is ... hm more expensive but not at the point I won't give it a try due to the embeded vision encoding

2 years in stealth...

> This means that a human does not necessarily need to be in the loop for agentic decisions anymore — agents can programmatically gather context, make decisions, and take actions on tasks, or defer to a human when needed.

1. Humans are already not in the loop for lots of LLM agent actions. Isn't that just a function of how much you trust it and not some completely new paradigm? Am I missing something?

2. How can it gather context if it just outputs a single decision?

One guess: Maybe it's decision can be "gather more context and re-run me"? But an LLM can be much more expressive about what context it needs.

With all these new Jev-like models popping up, has anyone actually started building anything with them yet? It's odd how quickly they've multiplied despite being relatively niche in their use cases, as far as I can tell. I suppose they're simple and cheap enough to make that it's a sort of 'why not' thing for a lot of these companies.

Commodities get commoditized. Nothing to see here.

I found the paragraph about how much networking data they have weird. I mean, if you already have all that data why didn't you train your models already using that? Why did you need clef to begin with?

Is there a Jev-like model I can run on my Mac? Something like Ollama? Or what's the best way to play with it? Is there a cheap/free API service eg on OpenRouter?

Why give cloudflare your data ?

At0M: A 60M local Jev at 16 ms latency and 79% accuracy on Typed Decision

https://at0m.pienomial.com/ https://news.ycombinator.com/item?id=49920350

Related: an intelligence cache for decision model data: https://cachev.dev

I built this for my own needs, and thought others might find it useful too.

Oldy enough I tired this 2h ago as I was testing jev on cf and was like oh this should be a better replacement but it takes 3s which is useless to me

I wonder if a good usecase for this would be cloudflare's WAF rules. Give broader request context to the decider and let it pick type of challenge/block traffic directly.

Perhaps that may be too costly atm

it's great to see Cloudflare releasing consumer edge level models.

Can someone explain how so many folks managed to build decision models within days or weeks after Typesafe came out with Jev? Is this concept of decision models been in the works for a while? Is it easy to copy?

in a quick mini-bench here n=250 of clef vs jev, clef came out 5.2x more expensive, a lot slower (p50 of 350ms vs 1.9s) with only marginally better results (78.6% vs 79.8%)

Competition in this area is great and kudos for releasing something that we can try out today.

AMAZING, thanks, Cloudflare!

that's good. I believe decision focused models will explode in the next few months

It allows image input. Nice!

Would love to see benchmarks on visual tasks.

jev can ask jev if they should return investor money and shut down jev

brb while I build my entire cloud stack on Cloudflare

Now we just need some new NER models.

Just tested clef-flash vs jev:

- Jev/TypeSafe: 230 ms median, 254 ms mean

- Jev/OpenRouter: 237 ms median, 267 ms mean

- Clef Flash: 661 ms median, 806 ms mean

What gives?

Imagine making your whole company on one model and then being cucked by everyone within a week. I don't think I've ever seen anything like it.

No mention of calibration. Is it just another llm finetune?

I feel bad for the Jev guys. I wonder if they anticipated this much competition?

“Urgency” of “yes”?

[dead]

[dead]

I bet this's 100% slop.

Horrible name

Wow, Cloudflare is definitely buying some goodwill from me. Just consistently interesting new releases alongside and solid products at great prices. Seems nearly too good to be true.