Get an audit

Head to head · Decision models · October 2026 research run

Decision 3.0 vs Vela 2.0

Vela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Both do decision models.

Best decision models for AI agents · All 105 decisions comparisons

Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#413 of 965 Vela 2.0vLLM Semantic Router project and KR Labs · Model API B66.5/100#294 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.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

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

Vela 2.0 B

Best for Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.

Ahead on

  • Schema & documentation, 78 against 70
  • Agent ergonomics, 79 against 72

Watch for

No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026

Score by category

CategoryWeight this runDecision 3.0Vela 2.0Edge
Reliability16%205857Decision 3.0 +1
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27078Vela 2.0 +8
Agent ergonomics13%16.27279Vela 2.0 +7
Security & auth14%17.55660Vela 2.0 +4
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88284Vela 2.0 +2
Transparency & trust7%8.84548Vela 2.0 +3
Negative events≤1500
TotalB 63.1/100B 66.5/100

Facts side by side

FactDecision 3.0Vela 2.0
KindModel APIModel API
VendorvLLM Semantic Router TeamvLLM Semantic Router project and KR Labs
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 basesApache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences
Read-only variant documentednono
llms.txtnono
Last release2026-10-112026-10-06
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularitynone6.1k 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.

Vela 2.0

One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.

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

Vela 2.0

  1. Pin a commit hash with revision= when loading from the Hub. The repositories have no tags and main has changed since launch
  2. Send the served name in model, for example vllm-sr/Vela-2.0-4B. The bundled server answers 422 to any other name
  3. Name span questions pii, halu or toxic, or set "head": "router", to get the trained router head. Other labels go to the broad head
  4. Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit
  5. Set VELA2_API_KEY before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network

Questions

Which is better for AI agents, Decision 3.0 or Vela 2.0?

Vela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories.

Do Decision 3.0 and Vela 2.0 need an API key?

Neither needs a key.

Can an agent call Decision 3.0 and Vela 2.0 without installing anything?

No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Vela 2.0.

Are Decision 3.0 and Vela 2.0 open source?

Yes. 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). Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).

Other comparisons with Decision 3.0 or Vela 2.0

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