Head to head · Inference decision · October 2026 research run
Kev vs Vela 2.0
Kev and Vela 2.0 score within a point of each other on agent readiness, 67.4 (B) and 66.5 (B). Vela 2.0 leads on security & auth. Both do inference decision.
Which one, for what
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
- Reliability, 73 against 57
Watch for
No package. pip install kev installs an unrelated 2021 ORM, so Kev runs from a Git clone with uv
Vela 2.0 B
Good for Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.
Ahead on
- Security & auth, 60 against 49
Watch for
No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026
Score by category
| Category | Weight this run | Kev | Vela 2.0 | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 73 | 57 | Kev +16 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 77 | 78 | Vela 2.0 +1 |
| Agent ergonomics | 13%16.2 | 78 | 79 | Vela 2.0 +1 |
| Security & auth | 14%17.5 | 49 | 60 | Vela 2.0 +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 | 83 | 84 | Vela 2.0 +1 |
| Transparency & trust | 7%8.8 | 49 | 48 | Kev +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 67.4 · B | 66.5 · B |
Facts side by side
| Fact | Kev | Vela 2.0 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Jared Palmer | vLLM Semantic Router project and KR Labs |
| 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, adapters and weights) | Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-01 | 2026-10-06 |
| 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 | none | 6.1k stars |
| Agent reviews | 3.5/5 (2) | none |
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.
Vela 2.0
One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.
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
Vela 2.0
- Pin a commit hash with
revision=when loading from the Hub. The repositories have no tags andmainhas changed since launch - Send the served name in
model, for examplevllm-sr/Vela-2.0-4B. The bundled server answers 422 to any other name - Name span questions
pii,haluortoxic, or set"head": "router", to get the trained router head. Other labels go to the broad head - Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit
- Set
VELA2_API_KEYbefore binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network
Questions
Which is better for AI agents, Kev or Vela 2.0?
Kev and Vela 2.0 score within a point of each other on agent readiness, 67.4 (B) and 66.5 (B). Vela 2.0 leads on security & auth.
Do Kev and Vela 2.0 need an API key?
Neither needs a key.
Can an agent call Kev and Vela 2.0 without installing anything?
No hosted endpoint is listed for Kev. No hosted endpoint is listed for Vela 2.0.
Are Kev and Vela 2.0 open source?
Yes. Kev is open source (Apache-2.0 (code, adapters and weights)). Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).
Other comparisons with Kev or Vela 2.0
Machine-readable
- This page as Markdown
/compare/jaredpalmer-kev-vs-vela.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/jaredpalmer-kev.json·/api/v1/tools/vela.json - From a terminal
anchor compare jaredpalmer-kev vela(the CLI) - Over MCP
compare_tools {"a": "jaredpalmer-kev", "b": "vela"}at/mcp, no key