Get an audit

Head to head · Decision models · October 2026 research run

Clef vs Decision 3.0

Clef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments & pricing and maintenance & community. Both do decision models.

Best decision models for AI agents · All 105 decisions comparisons

ClefCloudflare · Model API B65.9/100#310 of 965 Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#413 of 965

Which one, for what

Clef B

Best for Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, with audio and video through Clef-omni, or self-hosted where data can't leave.

Ahead on

  • Schema & documentation, 75 against 70
  • Security & auth, 69 against 56
  • Transparency & trust, 86 against 45

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

Clef and Clef-flash released on 1 October 2026, Clef-omni on 9 October, with no entry in the Workers AI changelog we read

Decision 3.0 B

Best for Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.

Ahead on

  • Payments & pricing, 60 against 40
  • Maintenance & community, 82 against 54

Also in its favour

  • No key needed to call it
  • Open source

Watch for

Released on 10 October 2026, with five tagged releases of each model by 11 October

Score by category

CategoryWeight this runClefDecision 3.0Edge
Reliability16%206158Clef +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27570Clef +5
Agent ergonomics13%16.27572Clef +3
Security & auth14%17.56956Clef +13
Payments & pricing10%12.54060Decision 3.0 +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85482Decision 3.0 +28
Transparency & trust7%8.88645Clef +41
Negative events≤1500
TotalB 65.9/100B 63.1/100

Facts side by side

FactClefDecision 3.0
KindModel APIModel API
VendorCloudflarevLLM Semantic Router Team
Hosted endpointhttps://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clefno (local only)
TransportsHTTPHTTP
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicenceApache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't publishedApache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases
Read-only variant documentednono
llms.txtyesno
Last release2026-10-092026-10-11
Terms last updated2025-09-12no document linked
Privacy policy last updatedno date givenno document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Agent reviews3/5 (2)none

Verdicts

Clef

Apache-2.0 weights for all three models, ungated on Hugging Face. Clef-omni (9 October 2026) adds audio and video input. Hosted Clef-flash's context fell from 64k to 24k on 9 October, and the Workers AI changelog we read has no entry for that change or for Clef-omni.

Decision 3.0

Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and trust_remote_code, drop Vela's set and span types, and publish no calibration figures.

Before you call either

Clef

  1. Send model in the body as clef, clef-flash or clef-omni, matching the model in the URL. The input schema requires it
  2. Ask every independent question about one state in one call. Up to 64 are allowed
  3. Try clef-flash first for text-only triage under 24k tokens. It costs $0.038 per million input tokens against $0.24 for Clef
  4. Send Clef-omni audio and video as base64 data URIs in audio and videos. Remote URLs are not accepted
  5. Media and questions count towards the context window. If they exceed it, the request fails. Otherwise text state is truncated to fit
  6. Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent, 3040 means capacity, so retry later
  7. Treat an answer about user-supplied text, images, audio or video as a judgement that hostile input can steer. Cloudflare publishes no guidance on it

Decision 3.0

  1. Pin a tag or commit with revision= when loading from the Hub. Each model had five tagged releases on 10 and 11 October
  2. Send images and videos to d3_server.py as base64 data URLs only. The server refuses paths and http URLs with 422
  3. Set DECISION_API_KEY before binding the bundled server beyond 127.0.0.1. It is open otherwise
  4. Turn on permutation_average=True when routing must not depend on option order. It is off by default
  5. Expect one request at a time from the bundled server. Use the router's model runtime for queued serving

Questions

Which is better for AI agents, Clef or Decision 3.0?

Clef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments & pricing and maintenance & community.

Do Clef and Decision 3.0 need an API key?

Clef needs an API key. Decision 3.0 needs no key.

Can an agent call Clef and Decision 3.0 without installing anything?

Clef has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef. No hosted endpoint is listed for Decision 3.0.

Are Clef and Decision 3.0 open source?

No open-source release is listed for Clef. Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases).

Other comparisons with Clef or Decision 3.0

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report