Skip to content
Fri 20 Nov 2026 Toronto Sign in
AI & ML

The New AI Models Don’t Talk. They Decide.

Cloudflare, Perplexity and Amazon's Strands all shipped "decision models" on Oct. 1. They return probabilities instead of prose, and all of them benchmark against a startup's model called Jev.

A railway switch junction where tracks split in two directions
Illustration: prompt/power

Ask Cloudflare’s newest model whether a website is a phishing page and it won’t write you a paragraph. It will return numbers. In Cloudflare’s own example, the model “might classify a domain with a 95% chance it is a fashion website, 85% ecommerce, <1% phishing." That's the whole output.

Updated Oct. 19, 2026: OpenAI’s Decisions API documentation is now public: a beta running on gpt-6-luna at US$0.10 (about CA$0.14) per million input tokens. And Jev’s maker, TypeSafe, raised a reported US$870 million at a US$7.5 billion valuation on Oct. 9.

Cloudflare graphic announcing its Clef decision models
Cloudflare launched its Clef decision models on Oct. 1. Image: Cloudflare

On Oct. 1, three separate teams shipped models built to work this way. Cloudflare released Clef and Clef-flash. Perplexity put out a Decisions API. Strands Labs, which builds Amazon’s open-source agent framework, released Strands Decider 2B. All three call these “decision models,” and all three measured themselves against the same yardstick: a model called Jev that most people outside agent engineering had never heard of a month ago.

The model that started it

Jev comes from a company called TypeSafe. OpenRouter’s listing describes it as “a structured decision model from TypeSafe, and the first of its System One models.” The name is a nod to Daniel Kahneman, as developer Sébastien Dubois explains: fast, intuitive System 1, with ordinary chatbots playing the slow, deliberate System 2. Dubois dates the launch to Sept. 15; OpenRouter lists Sept. 18, likely the date it reached that platform.

The idea is narrow on purpose. You give the model some input and a bounded question, such as yes or no, pick one of these options, or score this on a scale, and it returns probabilities instead of prose. Dubois’s description is the best one going: “a semantic `if` you can afford to call thousands of times.” OpenRouter lists Jev at US$0.042 (CA$0.058) per million input tokens, with output free.

Cloudflare is candid about the debt. Its launch post opens by crediting Jev with introducing “a new decision model concept into the world of AI — a model that produces bounded structured outputs cheaply, quickly and consistently.”

Three answers in one day

Cloudflare’s Clef is two models hosted on Workers AI and open-sourced on Hugging Face under an Apache 2.0 licence. Cloudflare says it froze Qwen3.8-27B for Clef and Qwen3.5-9B for Clef-flash and trained a routing head on top. The speed comes from skipping text entirely: “The decision step is non-autoregressive, so there’s no intermediate text to generate token by token,” the company writes. Across 43 benchmarks it reports a median latency of 209.3 milliseconds for Clef against 524.1 for Jev, and 38.8 for Clef-flash. It claims a 64k context window, double Jev’s. It also describes Clef as fully API-compatible with Jev, which tells you who set the standard. The launch post doesn’t give a price.

Perplexity’s Decisions API runs on a model called pplx-decider-v1-27b. Its documentation supports three question types (yes/no, choice and score), up to 255 options per choice question, and text, JSON or images as input. Price: US$0.04 (CA$0.056) per million input tokens, and “Output tokens are free.” The docs are honest about speed, too: about 2 seconds for a few hundred tokens of input, rising to roughly 23 seconds near the 262,144-token limit. Fast is relative.

Strands Decider 2B is the small one. It’s a two-billion-parameter model meant to run on a laptop, and its announcement reports median latency of about 115 milliseconds on an Nvidia RTX 3090 and 153 on an M3 Mac. Strands released the weights along with “all the training data and scripts we used to build the model,” and says it placed third of 33 in its size class on JevBench.

Why build a model that can’t talk

Agents make a lot of small calls. Which tool next? Is this output acceptable? Should this ticket go to a human? Today many of those calls go to a full language model that writes out an answer, which software then has to parse. Strands lists the jobs it has in mind: model routing, tool selection, evaluations and guardrails.

Decision models attack three costs at once. The answer is a probability, so there’s nothing to parse. It’s cheap enough to call constantly. And because every choice comes with a confidence score, you can log it, set a threshold and send anything uncertain to a person. Our read is that the third one matters most. An agent whose every branch is a logged number is far easier to audit after something goes wrong than one that reasoned its way there in prose.

The trade-off is stated plainly by the people selling it. Strands says its model is “significantly worse at solving complex problems than reasoning models,” and that its inability to generate text “makes it unsuited for coding, chatbots, document summarization, and other common LLM tasks.” These are switches, not brains.

One vendor was missing at first. The Neuron reported that OpenAI also introduced a Decisions API as part of a new agent stack on Oct. 1. Its documentation has since become readable, and we cover it in the update below.

Everything above is vendor-reported, and every benchmark was chosen by the company that published it. The more telling number is the count of launches. Two weeks after a startup named a category, three companies with far bigger distribution shipped into it on the same Thursday, each one promising to answer Jev’s questions faster.

What’s happened since: OpenAI’s version, and Jev’s payday

The missing vendor has filled in its own blank. OpenAI’s Decisions API is in public beta on a single model, gpt-6-luna, behind a /v1/decisions endpoint. It takes three question types, which OpenAI calls predicate, choice and score. A predicate comes back as a probability between 0 and 1; a choice comes back with a probability for every option plus a confidence value. OpenAI says the API “returns typed answers about 10x faster than the Responses API,” without giving millisecond figures. The price is US$0.10 (about CA$0.14) per million input tokens, with no charge for output. That is two and a half times Perplexity’s rate. The page never mentions Jev.

TypeSafe, meanwhile, got paid for naming the category. On Oct. 9 it closed a US$870 million Series A at a US$7.5 billion valuation, led by Andreessen Horowitz with Sequoia Capital and existing investor DCVC, Tech Times reported, crediting SiliconANGLE. Tech Times puts the round 24 days after Jev’s launch, which came with a US$40 million seed at a US$200 million valuation. We could not open TypeSafe’s own announcement.

So the category’s inventor is now worth US$7.5 billion on paper, and the biggest lab in it charges a premium for a model that cannot write a sentence.

// How we reported this

Researched and drafted with AI tools, fact-checked against primary sources and approved by a human editor before publishing. Prices and dates are as of publication. Our standards →

Sources
  1. blog.cloudflare.com — Cloudflare's own example
  2. developers.openai.com — Decisions API documentation
  3. openrouter.ai — OpenRouter's listing
  4. dsebastien.net — explains
  5. docs.perplexity.ai — documentation
  6. strandsagents.com — announcement
Contributor, AI Explained Catherine Crowe

Catherine Crowe covers AI explained for prompt/power: the plain-English guides that break down how the technology works, what the jargon means and what it changes for everyday people. Originally from Canada, she writes from New Zealand.

All stories by Catherine →

Latest from prompt/power

  1. How to read an IPO prospectus in 10 minutes, using Anthropic’s as the exampleNov 20
  2. ChatGPT Pro, Claude Max or Google AI Ultra? What CA$140 a month buysNov 20
  3. Google’s Gemini health coach costs CA$12.99 a month, or nothing with AI Pro. What it does and doesn’t doNov 20
  4. Broadcom’s AI chip sales now outstrip its entire business from a year ago. What to watch on Dec. 9Nov 19
  5. Pay yearly or monthly? What you save on AI subscriptions in CanadaNov 19

Leave a Reply

Your email address will not be published. Required fields are marked *