Write a review

Head to head · Decision models · October 2026 research run

Decision 3.0 vs ScaleDown

Decision 3.0 scores 63.1 (B) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on transparency & trust. Both do decision models.

Best decision models for AI agents · All 120 decisions comparisons

Best document parsing, OCR and extraction APIs for AI agents · All 124 documents comparisons

Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#435 of 1084 ScaleDownCarbon ScaleDown, Inc. · Model API D48.6/100#873 of 1084

Which one, for what

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

  • Reliability, 58 against 20
  • Security & auth, 56 against 48
  • Payments & pricing, 60 against 40
  • Maintenance & community, 82 against 56

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

ScaleDown D

Best for Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.

Ahead on

  • Transparency & trust, 54 against 45

Also in its favour

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

Watch for

No status page, no published rate limits and no SLA outside enterprise contracts

Score by category

CategoryWeight this runDecision 3.0ScaleDownEdge
Reliability16%205820Decision 3.0 +38
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27069Decision 3.0 +1
Agent ergonomics13%16.27276ScaleDown +4
Security & auth14%17.55648Decision 3.0 +8
Payments & pricing10%12.56040Decision 3.0 +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88256Decision 3.0 +26
Transparency & trust7%8.84554ScaleDown +9
Negative events≤150-2
TotalB 63.1/100D 48.6/100

Facts side by side

FactDecision 3.0ScaleDown
KindModel APIModel API
VendorvLLM Semantic Router TeamCarbon ScaleDown, Inc.
Hosted endpointno (local only)https://api.scaledown.xyz
TransportsHTTPHTTP
AuthNoneAPI key
PricingFreePay per use
x402nono
LicenceApache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 basesProprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-112026-10-14
Terms last updatedno document linkedcouldn't be read
Privacy policy last updatedno document linkedcouldn't be read
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Popularitynone0 stars

Verdicts

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.

ScaleDown

Classify answers Jev-shaped choice, noul and score questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.

Before you call either

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

ScaleDown

  1. Send several questions about one item in one /v1/scaledown call. Each becomes its own Classify call and the usage is summed
  2. Pin classify-1, extract-1 or summarize-1 once you've tuned thresholds on your own labelled cases
  3. Set context_chars to 0 and use top_n on Extract unless you need the 500 characters of context each side
  4. Set reasoning: false on /classify when you only need the label. The reasoning call bills its input at 2x
  5. Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects

Questions

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

Decision 3.0 scores 63.1 (B) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on transparency & trust.

Do Decision 3.0 and ScaleDown need an API key?

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

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

No hosted endpoint is listed for Decision 3.0. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.

Are Decision 3.0 and ScaleDown open source?

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). No open-source release is listed for ScaleDown.

Other comparisons with Decision 3.0 or ScaleDown

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