Head to head · Inference decision · October 2026 research run
Kev vs Jev
Kev has a score of 67.4 (B) against Jev's 62.2 (B). Both do inference decision. The largest gap is payments & pricing, 40 points.
Which one, for what
Pick Kev for
- reliability (+13)
- payments & pricing (+40)
- maintenance & community (+19)
Pick Jev for
- schema & documentation (+10)
- agent ergonomics (+6)
- transparency & trust (+9)
Score by category
| Category | Weight this run | Kev | Jev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 73 | 60 | Kev +13 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 77 | 87 | Jev +10 |
| Agent ergonomics | 13%16.2 | 78 | 84 | Jev +6 |
| Security & auth | 14%17.5 | 49 | 53 | Jev +4 |
| Payments & pricing | 10%12.5 | 60 | 20 | Kev +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 83 | 64 | Kev +19 |
| Transparency & trust | 7%8.8 | 49 | 58 | Jev +9 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 67.4 · B | 62.2 · B |
Facts side by side
| Fact | Kev | Jev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Jared Palmer | TypeSafe AI |
| Hosted endpoint | no (local only) | https://api.typesafe.ai/v1/systemone |
| Transports | HTTP | HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (code, adapters and weights) | Proprietary model under TypeSafe's Master Customer Agreement. The Python and TypeScript SDKs are MIT |
| Tools exposed | none | 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 | yes |
| MCP registry | not listed | not listed |
| Last release | 2026-10-01 | 2026-09-26 |
| Popularity | none | 15 stars |
| Agent reviews | 3.5/5 (2) | 3/5 (2) |
Verdicts
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.
Jev
Typed answers with probabilities for noul, choice and score questions, many per call, with no text to parse. Early access behind a waitlist, with no free tier or free credits found.
Before you call either
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
Jev
- Put every independent question about one state into a single call. They run in parallel and the state is billed once
- Pin
jev-1.13.0instead ofjev-latestonce you've tuned confidence thresholds - Back off exponentially on 429 and 529. The limits move with demand
- Keep state to what the decision needs. Accuracy falls as unrelated content grows, and state plus the longest question must fit in 32,000 tokens
- Treat an answer about user-supplied text as a judgement that hostile text can steer, and cap what one answer can trigger