Write a review

Head to head · Decision models · October 2026 research run

SPEV vs Vela 2.0

Vela 2.0 scores 66.5 (B) on agent readiness against SPEV's 51.1 (D), and leads in 5 of 7 scored categories. SPEV leads on transparency & trust. Both do decision models.

Best decision models for AI agents · All 136 decisions comparisons

SPEVSprag · Model API D51.1/100#819 of 1094 Vela 2.0vLLM Semantic Router project and KR Labs · Model API B66.5/100#310 of 1094

Which one, for what

SPEV D

Best for Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted.

Ahead on

  • Transparency & trust, 54 against 48

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

Published on 14 October 2026, with no service record, no status page and no API changelog

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

  • Reliability, 57 against 45
  • Security & auth, 60 against 33
  • Payments & pricing, 60 against 30
  • Maintenance & community, 84 against 49

Also in its favour

  • No key needed to call it
  • Open source

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 runSPEVVela 2.0Edge
Reliability16%204557Vela 2.0 +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28178SPEV +3
Agent ergonomics13%16.27679Vela 2.0 +3
Security & auth14%17.53360Vela 2.0 +27
Payments & pricing10%12.53060Vela 2.0 +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.84984Vela 2.0 +35
Transparency & trust7%8.85448SPEV +6
Negative events≤15-20
TotalD 51.1/100B 66.5/100

Facts side by side

FactSPEVVela 2.0
KindModel APIModel API
VendorSpragvLLM Semantic Router project and KR Labs
Hosted endpointhttps://api.sprag.ai/v1/decisionsno (local only)
TransportsHTTPHTTP
AuthAPI keyNone
PricingPay per useFree
x402nono
LicenceApache-2.0 (weights and inference code, following the Qwen3-Omni base). Training code and data aren't publishedApache-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.txtyesno
Last release2026-10-142026-10-06
Terms last updated2026-09-01no document linked
Privacy policy last updated2026-08-01no document linked
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularitynone6.1k stars

Verdicts

SPEV

SPEV answers typed questions over text, audio or an image in one call, with a public OpenAPI schema and Apache-2.0 weights on Hugging Face. It is a day old, has an 8,192-token context, no status page or changelog, and Sprag's terms let it train on API content unless the customer opts out by email.

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

SPEV

  1. Send model: "spev" to POST https://api.sprag.ai/v1/decisions with a bearer key. /v1/systemone returns 410
  2. Ask every question about one piece of evidence in one request. Answers come back in question order
  3. Send audio as base64 in input_audio with format, not as a data URL, and at most one image across all messages
  4. Keep evidence and questions under 8,192 tokens. Over the limit returns 400 model_limit_exceeded
  5. Back off on 429 and 503 for Retry-After seconds. Limits are 60 requests a minute per organisation by default
  6. Handle an answer of type refusal, which carries no probabilities

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, SPEV or Vela 2.0?

Vela 2.0 scores 66.5 (B) on agent readiness against SPEV's 51.1 (D), and leads in 5 of 7 scored categories. SPEV leads on transparency & trust.

Do SPEV and Vela 2.0 need an API key?

SPEV needs an API key. Vela 2.0 needs no key.

Can an agent call SPEV and Vela 2.0 without installing anything?

SPEV has a hosted endpoint at https://api.sprag.ai/v1/decisions. No hosted endpoint is listed for Vela 2.0.

Are SPEV and Vela 2.0 open source?

No open-source release is listed for SPEV. 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 SPEV 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