Write a review

Head to head · Decision models · October 2026 research run

Decision 3.0 vs SPEV

Decision 3.0 scores 63.1 (B) on agent readiness against SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema & documentation and transparency & trust. Both do decision models.

Best decision models for AI agents · All 136 decisions comparisons

Decision 3.0vLLM Semantic Router Team · Model API B63.1/100#438 of 1094 SPEVSprag · Model API D51.1/100#819 of 1094

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 45
  • Security & auth, 56 against 33
  • Payments & pricing, 60 against 30
  • Maintenance & community, 82 against 49

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

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

  • Schema & documentation, 81 against 70
  • Transparency & trust, 54 against 45

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

Score by category

CategoryWeight this runDecision 3.0SPEVEdge
Reliability16%205845Decision 3.0 +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27081SPEV +11
Agent ergonomics13%16.27276SPEV +4
Security & auth14%17.55633Decision 3.0 +23
Payments & pricing10%12.56030Decision 3.0 +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88249Decision 3.0 +33
Transparency & trust7%8.84554SPEV +9
Negative events≤150-2
TotalB 63.1/100D 51.1/100

Facts side by side

FactDecision 3.0SPEV
KindModel APIModel API
VendorvLLM Semantic Router TeamSprag
Hosted endpointno (local only)https://api.sprag.ai/v1/decisions
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 basesApache-2.0 (weights and inference code, following the Qwen3-Omni base). Training code and data aren't published
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-112026-10-14
Terms last updatedno document linked2026-09-01
Privacy policy last updatedno document linked2026-08-01
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

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.

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.

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

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

Questions

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

Decision 3.0 scores 63.1 (B) on agent readiness against SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema & documentation and transparency & trust.

Do Decision 3.0 and SPEV need an API key?

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

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

No hosted endpoint is listed for Decision 3.0. SPEV has a hosted endpoint at https://api.sprag.ai/v1/decisions.

Are Decision 3.0 and SPEV 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 SPEV.

Other comparisons with Decision 3.0 or SPEV

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