Skip to content

Project

Workers AI

Cloudflare's inference service, which runs open models on GPUs in its network and is callable from Workers as a binding.

Known aliases

  • AI binding
  • Cloudflare Workers AI
  • Workers AI

Current stories

buildConfirmed2 publishers

Cloudflare's Clef-omni scores audio and video against a decision schema in one call

Cloudflare's Clef-omni takes audio and video alongside text and images and returns schema-bound decisions in one API call. Runtimewire reported that the same release cut hosted Clef-flash's context window from 64,000 to 24,000 tokens, so longer prompts now go to Clef or to self-hosted weights.

Perspective Coverage

3 publishers
Builder
Builder 63%
Operator
Operator 25%
Investor
Investor 12%

Reality

Evidence55
Adoption12
Hype gap+30
Incentives70
Confidence60
buildOne report1 publisher

TypeSafe's Jev, Cloudflare's Clef and AWS's Strands Decider 2B bring small models to agent decisions

Cloudflare and AWS have followed TypeSafe's Jev with Clef and Strands Decider 2B, small models built to pick an agent's next tool or step. The pitch is a smaller token bill, though the practitioners dev.to cites say calibration and the cost of a wrong pick decide whether any saving survives.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+25
Incentives
Not scored
Confidence35
buildConfirmed4 publishers

Post-training alone took GLM-5.3 from 4.6 to 28.3 on Terminal-Bench 3.0

Z.ai says the base model did not change between GLM-5.2 and GLM-5.3, so the coding jump and the doubled exploitation score come out of the same post-training run. Security teams inherit the second half.

Perspective Coverage

4 publishers
Builder
Builder 49%
Operator
Operator 32%
Investor
Investor 19%

Reality

Evidence50
Adoption30
Hype gap+30
Incentives70
Confidence60
buildConfirmed4 publishers

Typesafe's Jev API gains an open-weight rival in Cloudflare's Clef decision models

Cloudflare released two Jev-API-compatible decision models, Clef and Clef-flash, on Workers AI and as Apache 2.0 weights on Hugging Face. Typed classification steps in agent code can now move between providers or onto owned hardware, as long as they stay inside the text-only, 32k-context features Jev supports.

Publishers:blog.cloudflare.com dev.to developers.cloudflare.com the-decoder.com

Perspective Coverage

4 publishers
Builder
Builder 53%
Operator
Operator 30%
Investor
Investor 17%

Reality

Evidence55
Adoption18
Hype gap+30
Incentives75
Confidence60
buildOne report1 publisher

Cloudflare brings publicly built EuroLLM and Switzerland's Apertus to Workers AI

Cloudflare is adding EuroLLM, which covers all 24 official EU languages, and Switzerland's fully open Apertus model to Workers AI. Both come from public universities and research institutions, so teams with sovereignty requirements now have hosted models built outside the frontier labs.

Reality

Evidence40
Adoption12
Hype gap+25
Incentives80
Confidence45
buildOne report1 publisher

Cloudflare AI Search goes GA with pixel-level image search and a November 1 billing start

Cloudflare made AI Search generally available with native image embeddings and PDF OCR, and will start billing for it on November 1, 2026. Which embedding model an instance runs now decides whether an image query searches pixels or a caption.

Reality

Evidence35
Adoption
Not scored
Hype gap+10
Incentives85
Confidence45
buildOne report1 publisher

Cloudflare's Auto Router moves model selection from the user into AI Gateway

Cloudflare's Auto Router, now in public beta, picks a model per AI Gateway request and cut costs by up to 30% in the company's own OpenCode use. How much of that transfers depends on how much of a team's traffic never needed a frontier model.

Reality

Evidence35
Adoption15
Hype gap+15
Incentives80
Confidence40
buildOne report1 publisher

A Lnkr payload sat in URLScan for nearly two and a half years marked "No classification"

Cloudflare says its graph model flagged eight malicious scripts running on live storefronts. A retrospective check put seven of the eight outside VirusTotal entirely. URLScan flagged none of the eight as malicious.

Reality

Evidence45
Adoption40
Hype gap+30
Incentives85
Confidence50
buildOne report1 publisher

A $5-a-month monitoring SaaS on Workers, Turso and R2 is a cost datapoint, not a blueprint

A solo founder says their Cloudflare-native stack runs a multi-tenant monitoring product for about $5 a month across its first hundred customers. The bill is the finding. The 60-second cron is the caveat.

Publishers:dev.to

Reality

Evidence42
Adoption9
Hype gap+38
Incentives68
Confidence46