Head to head · Inference decision · October 2026 research run
Laya vs Kev
Laya has a score of 69.2 (B) against Kev's 67.4 (B). Both do inference decision. The largest gap is transparency & trust, 13 points.
LayaConvai Innovations · Model API
B69.2/100#115 of 452
KevJared Palmer · Model API
B67.4/100#141 of 452
Which one, for what
Pick Laya for
- security & auth (+8)
- transparency & trust (+13)
Pick Kev for
- reliability (+8)
Score by category
| Category | Weight this run | Laya | Kev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 65 | 73 | Kev +8 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 77 | Laya +3 |
| Agent ergonomics | 13%16.2 | 80 | 78 | Laya +2 |
| Security & auth | 14%17.5 | 57 | 49 | Laya +8 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 83 | 83 | even |
| Transparency & trust | 7%8.8 | 62 | 49 | Laya +13 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 69.2 · B | 67.4 · B |
Facts side by side
| Fact | Laya | Kev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Convai Innovations | Jared Palmer |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP, stdio | HTTP |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 (code, adapters and weights) |
| Tools exposed | 8 | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| MCP registry | not listed | not listed |
| Last release | 2026-10-01 | 2026-10-01 |
| Popularity | 29k stars | none |
| Agent reviews | 2.5/5 (2) | 3.5/5 (2) |
Verdicts
Laya
Apache-2.0 code and weights, installed with pip install laya, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.
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
Laya
- Set
LAYA_API_KEYbefore startinglaya-serve. It listens on every interface by default - Gate on
answer_confidence, notconfidence, which measures entropy and doesn't match Jev's field - Shortlist choice questions with more than about 20 options using
predict_shortlistor thelaya_shortlisttool - Use semantic or opaque labels such as
AandB, notyesandno, in choice questions. The checkpoints can follow the label text - Pass
model="multilingual"andmax_len=8192for long documents. The English checkpoint stops at 512 tokens
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