Jev vs Cloudflare Clef

What Cloudflare announced

From the Cloudflare blog and Workers AI model docs:

• Models: @cf/cloudflare/clef and clef-flash
• Question types: noul, choice, score (System One-shaped)
• Input: multimodal — text, JSON, images, video
• Batch: up to 64 questions per call
• Context: 65,536 tokens
• Pricing: $0.24 per million input tokens (Workers AI pricing page, as of early October 2026)
• Open weights: Apache 2.0 license on Hugging Face
• API compatibility: Jev-API compatible (Cloudflare blog claims vendor evaluation tables)

Sources: Workers AI Clef docs, Cloudflare blog post

What Jev is

TypeSafe's Jev is a decision model (System One), not a chat model that happens to pick a label. Launched September 15, 2026.

• Question types: Choice, Score, Noul (mixable in one call)
• Returns: per-option probabilities and confidence
• Input: text only (string, JSON object, or array of strings)
• API: documented POST /v1/systemone with Python and JavaScript SDKs
• Pricing: $0.042 per million input tokens, output free
• Batch: ~60 questions cost about the same as one
• Limits: 64k tokens per request; 32k for state plus longest question

Source: TypeSafe models

Side by side

Facts only. Where either product has not published a detail, that is what the table says.

What builders should do

1. If you need vision (screenshots, UI state, video frames): Clef documents it. Jev is text-only; preprocess images with OCR or vision models if using Jev.
2. If you need self-hosted open weights: Clef publishes Apache 2.0 on Hugging Face. Jev: closed. Or see open-source alternatives (Laya, Julia 1, kev).
3. If you are already on Cloudflare Workers: Clef is native; no external API wiring needed.
4. If you want lowest per-token cost: Jev $0.042/M vs Clef $0.24/M (as of early October 2026 docs). Text-only routing and classification favor Jev's pricing.
5. If you want proof builds: Jev has madewithjev catalog with published cost/latency figures. Clef: vendor benchmarks only as of early October 2026.

How to talk about timing

Jev mid-September, Clef late September, Perplexity Decisions and OpenAI Decisions in the same window. Frame it as category validation: the industry agrees that constrained typed decisions at speed beat generative prose for classify/route/act workflows. No vendor has stated they copied another.

Builds that show the job

Routing, classification, and agent next action — with the cost and latency each builder published.

Duncan

@ephraimduncan

Built a model router with Jev by @typesafeai. Jev decides what model fits your request best and the request is sent to that model.

X·Routing and model choice

A model router on Jev

Gregor Zunic

@gregpr07

Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓

X·Search

Pick

Flight search with Browser Use

Run time

~7 s

Cost

~$0.004

tamara

@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

X·Context and memory

Pick

Instant compaction for Claude

Hassan

@nutlope

I used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on http://1kpapers.com The summaries cost $3.99 on @togethercompute. The classifications cost $0.08 on @typesafeai. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the Jev classifications before replacing the current ones, but the site is already live: http://1kpapers.com

Live site·Documents and OCR

1kpapers

Documents

1,018 papers

Total cost

$0.08

Median latency

256 ms

More on Jev use cases.

Try it today

Next steps

• Cloudflare Clef alternatives — who should use Jev instead, and when Clef still wins
• How to use Jev — your first call, SDKs, and gateways
• Jev pricing — what a decision costs across real builds
• Open-source Jev — local models that answer typed questions
• Agent prompts — wire Jev into Claude Code, Cursor, Codex

Common questions

What is Cloudflare Clef?

A System One decision model on Cloudflare Workers AI. Handles Choice/Score/Noul question types, multimodal (text/JSON/images/video), up to 64 questions per call, Apache 2.0 open weights on Hugging Face. Announced as Jev-API compatible.

How is Jev different from Cloudflare Clef?

Jev is text-only, GA via TypeSafe API ($0.042/M input, output free), closed weights, madewithjev proof builds. Clef is multimodal, on Workers AI ($0.24/M input per docs as of early October 2026), Apache 2.0 open weights, can self-host.

Which is cheaper, Jev or Clef?

Per Workers AI docs as of early October 2026: Jev $0.042/M input (output free), Clef $0.24/M input. Verify current pricing before hard-coding; both APIs evolve.

Can I self-host Jev like Clef?

No: TypeSafe has not released Jev weights. Clef publishes Apache 2.0 weights on Hugging Face for self-hosting. For local alternatives to both, see open-source decision models (Laya, Julia 1, kev).

Does Clef support images like OpenAI Decisions?

Yes. Clef accepts text, JSON, images and video per Cloudflare docs. Jev is text-only. OpenAI Decisions (limited preview) also supports images.

Which should I use for agent routing?

If you need vision (screenshots, UI state): Clef or preprocess to text for Jev. If text-only and want lowest per-token cost: Jev. If already on Workers AI: Clef is native. If want proof builds: Jev has madewithjev catalog.