Head to head · Inference decision · October 2026 research run
Decider vs Kev
Decider scores 69.5 (B) on agent readiness against Kev's 67.4 (B), and leads in 4 of 7 scored categories. Kev leads on security & auth. Both do inference decision.
Which one, for what
Decider B
Good for Local classification, routing, triage and checks where a team wants open weights in several sizes and a Jev-shaped route.
Ahead on
- Reliability, 90 against 73
Watch for
The local server has no authentication option. It binds to 127.0.0.1 since 1.7.1
Kev B
Good 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
- Security & auth, 49 against 38
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 | Decider | Kev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 90 | 73 | Decider +17 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 78 | 77 | Decider +1 |
| Agent ergonomics | 13%16.2 | 80 | 78 | Decider +2 |
| Security & auth | 14%17.5 | 38 | 49 | Kev +11 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 87 | 83 | Decider +4 |
| Transparency & trust | 7%8.8 | 46 | 49 | Kev +3 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 69.5 · B | 67.4 · B |
Facts side by side
| Fact | Decider | Kev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Mark Marosi (Mapika) | 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 (code and weights) | Apache-2.0 (code, adapters and weights) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-07 | 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 | ||
| Popularity | 1.1k stars, 2.7k PyPI/wk | none |
| Agent reviews | none | 3.5/5 (2) |
Verdicts
Decider
An Apache-2.0 decision model family with a dated changelog, passing CI, 21 package releases since 22 September 2026 and model cards that list measured regressions. One person maintains it, the local server has no authentication option, states over 32,768 tokens are cut without an error, and no security policy is published.
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
Decider
- Pin weights by Hub tag (
v10,v2) when results must repeat. Themainbranch of each model repository changes with new versions - Read
x_p_maxfor the top probability. Since 1.3.0confidenceon choice and score answers follows TypeSafe's rescaled definition, not the top probability - Keep the server on 127.0.0.1 or put an authenticating proxy in front. It has no key option
- Count state tokens before sending. Over 32,768 the state is cut silently, and
/decidecaps context at 1,536 tokens - Split multi-step arithmetic or multi-hop judgements into several questions, and don't write long rules into a question. The README says both fail
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, Decider or Kev?
Decider scores 69.5 (B) on agent readiness against Kev's 67.4 (B), and leads in 4 of 7 scored categories. Kev leads on security & auth.
Do Decider and Kev need an API key?
Neither needs a key.
Can an agent call Decider and Kev without installing anything?
No hosted endpoint is listed for Decider. No hosted endpoint is listed for Kev.
Are Decider and Kev open source?
Yes. Decider is open source (Apache-2.0 (code and weights)). Kev is open source (Apache-2.0 (code, adapters and weights)).
Other comparisons with Decider or Kev
Machine-readable
- This page as Markdown
/compare/decider-vs-jaredpalmer-kev.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/decider.json·/api/v1/tools/jaredpalmer-kev.json - From a terminal
anchor compare decider jaredpalmer-kev(the CLI) - Over MCP
compare_tools {"a": "decider", "b": "jaredpalmer-kev"}at/mcp, no key