Head to head · Decision models · October 2026 research run
Decision 3.0 vs Kev
Kev scores 67.4 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on security & auth. Both do decision models.
Best decision models for AI agents · All 105 decisions comparisons
Which one, for what
Best for Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.
Ahead on
- Security & auth, 56 against 49
Watch for
Released on 10 October 2026, with five tagged releases of each model by 11 October
Kev B
Best for Self-hosted classification, routing, triage and rubric scoring where a probability matters, especially for teams already calling Jev who want the same API on their own hardware.
Ahead on
- Reliability, 73 against 58
- Schema & documentation, 77 against 70
- Agent ergonomics, 78 against 72
Watch for
No package. pip install kev installs an unrelated 2021 ORM, so Kev runs from a Git clone with uv
Score by category
| Category | Weight this run | Decision 3.0 | Kev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 58 | 73 | Kev +15 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 70 | 77 | Kev +7 |
| Agent ergonomics | 13%16.2 | 72 | 78 | Kev +6 |
| Security & auth | 14%17.5 | 56 | 49 | Decision 3.0 +7 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 83 | Kev +1 |
| Transparency & trust | 7%8.8 | 45 | 49 | Kev +4 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 63.1/100 | B 67.4/100 |
Facts side by side
| Fact | Decision 3.0 | Kev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | vLLM Semantic Router Team | Jared Palmer |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Apache-2.0 (code, adapters and weights) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-11 | 2026-10-01 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no 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 | ||
| Agent reviews | none | 3.5/5 (2) |
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.
Kev
Apache-2.0 code, adapters and heads on Apache-2.0 Qwen bases, with release tarballs and SHA-256 checksums for the 0.8B, 4B and 9B models. No package. pip install kev installs an unrelated 2021 ORM, so Kev runs from a Git clone with uv.
Before you call either
Decision 3.0
- Pin a tag or commit with
revision=when loading from the Hub. Each model had five tagged releases on 10 and 11 October - Send images and videos to
d3_server.pyas base64 data URLs only. The server refuses paths and http URLs with 422 - Set
DECISION_API_KEYbefore binding the bundled server beyond 127.0.0.1. It is open otherwise - Turn on
permutation_average=Truewhen routing must not depend on option order. It is off by default - Expect one request at a time from the bundled server. Use the router's model runtime for queued serving
Kev
- Install from the repository. The
kevpackage on PyPI is an unrelated project - Pin a checkpoint with
@v1.0, as injaredpalmer/kev-4b@v1.0, so tuned thresholds keep their meaning - Keep states under 8,192 tokens on Kev-0.8B, 4B and 9B, or use Kev-27B for long documents
- Set
KEV_DATE_FACTS=1when a decision depends on the gap between two dates - Expect a 422 naming the token count when a state passes 65,536 tokens. The server refuses it instead of cutting it
Questions
Which is better for AI agents, Decision 3.0 or Kev?
Kev scores 67.4 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on security & auth.
Do Decision 3.0 and Kev need an API key?
Neither needs a key.
Can an agent call Decision 3.0 and Kev without installing anything?
No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Kev.
Are Decision 3.0 and Kev 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). Kev is open source (Apache-2.0 (code, adapters and weights)).
Other comparisons with Decision 3.0 or Kev
- Celeris-1 Decision vs Decision 3.0
- Celeris-1 Decision vs Kev
- Clef vs Decision 3.0
- Clef vs Kev
- Laya vs Decision 3.0
- Laya vs Kev
- Decider vs Decision 3.0
- Decider vs Kev
- Decision 3.0 vs GLiClass
- Decision 3.0 vs Liquid d1
- Decision 3.0 vs Microsoft-Decision-1
- Decision 3.0 vs Drex 1.5
- Decision 3.0 vs OpenAI Decisions API
- Decision 3.0 vs pplx-decider
- Decision 3.0 vs Strands Decider 2B
- Decision 3.0 vs Jev
- Decision 3.0 vs Vela 2.0
- GLiClass vs Kev
- Kev vs Liquid d1
- Kev vs Microsoft-Decision-1
- Kev vs Drex 1.5
- Kev vs OpenAI Decisions API
- Kev vs pplx-decider
- Kev vs Strands Decider 2B
- Kev vs Jev
- Kev vs Vela 2.0
Machine-readable
- This page as Markdown
/compare/decision-3-vs-jaredpalmer-kev.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/decision-3.json·/api/v1/tools/jaredpalmer-kev.json - From a terminal
anchor compare decision-3 jaredpalmer-kev(the CLI) - Over MCP
compare_tools {"a": "decision-3", "b": "jaredpalmer-kev"}at/mcp, no key