Get an audit

Head to head · Decision models · October 2026 research run

Decision 3.0 vs pplx-decider

Decision 3.0 and pplx-decider score within a point of each other on agent readiness, 63.1 (B) and 62.9 (B). pplx-decider leads on schema & documentation, security & auth and transparency & trust. Both do decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens.

Best decision models for AI agents · All 105 decisions comparisons

Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#413 of 965 pplx-deciderPerplexity · Model API B62.9/100#423 of 965

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

  • Payments & pricing, 60 against 25
  • Maintenance & community, 82 against 62

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

pplx-decider B

Best for High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.

Ahead on

  • Schema & documentation, 90 against 70
  • Security & auth, 61 against 56
  • Transparency & trust, 52 against 45

Also in its favour

  • Cheaper for decision models, $0 against $0 per 1M tokens
  • A hosted endpoint, with nothing to install

Watch for

The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee

Score by category

CategoryWeight this runDecision 3.0pplx-deciderEdge
Reliability16%205861pplx-decider +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27090pplx-decider +20
Agent ergonomics13%16.27276pplx-decider +4
Security & auth14%17.55661pplx-decider +5
Payments & pricing10%12.56025Decision 3.0 +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88262Decision 3.0 +20
Transparency & trust7%8.84552pplx-decider +7
Negative events≤1500
TotalB 63.1/100B 62.9/100

Facts side by side

FactDecision 3.0pplx-decider
KindModel APIModel API
VendorvLLM Semantic Router TeamPerplexity
Hosted endpointno (local only)https://api.perplexity.ai/v1/decisions
TransportsHTTPHTTP
AuthNoneAPI key
PricingFreePay per use
Price for decision modelsfreefree
x402nono
LicenceApache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 basesApache-2.0 for the published weights. The hosted Decisions API is a proprietary service
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-112026-10-05
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

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.

pplx-decider

The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.

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

pplx-decider

  1. Send Authorization: Bearer. A key in x-api-key returns 401 on this endpoint.
  2. Set model on every request. A missing or unknown model returns 400, and the guide shows a -latest name rejected.
  3. Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.
  4. Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and error.code changes type.
  5. For the weights, use the repository's autojev code. The card says default causal inference does not reproduce the evaluated setup.

Questions

Which is better for AI agents, Decision 3.0 or pplx-decider?

Decision 3.0 and pplx-decider score within a point of each other on agent readiness, 63.1 (B) and 62.9 (B). pplx-decider leads on schema & documentation, security & auth and transparency & trust.

Which is cheaper for decision models, Decision 3.0 or pplx-decider?

Decision 3.0, at free against free for pplx-decider. These are the vendors' published prices for the job.

Do Decision 3.0 and pplx-decider need an API key?

Decision 3.0 needs no key. pplx-decider needs an API key.

Can an agent call Decision 3.0 and pplx-decider without installing anything?

No hosted endpoint is listed for Decision 3.0. pplx-decider has a hosted endpoint at https://api.perplexity.ai/v1/decisions.

Are Decision 3.0 and pplx-decider 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 pplx-decider.

Other comparisons with Decision 3.0 or pplx-decider

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