Head to head · Inference decision · October 2026 research run
GLiClass vs Kev
Kev scores 67.4 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust. Both do inference decision.
Which one, for what
GLiClass D
Good for Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once.
Ahead on
- Transparency & trust, 64 against 49
Watch for
No calibration evidence. The cards report F1 only, and the docs tell users to calibrate thresholds on their own traffic
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 43
- Schema & documentation, 77 against 49
- Agent ergonomics, 78 against 60
- Security & auth, 49 against 38
- Maintenance & community, 83 against 44
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 | GLiClass | Kev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 43 | 73 | Kev +30 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 49 | 77 | Kev +28 |
| Agent ergonomics | 13%16.2 | 60 | 78 | Kev +18 |
| 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 | 44 | 83 | Kev +39 |
| Transparency & trust | 7%8.8 | 64 | 49 | GLiClass +15 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 49.9 · D | 67.4 · B |
Facts side by side
| Fact | GLiClass | Kev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Knowledgator | 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 (library and the model weights we checked) | Apache-2.0 (code, adapters and weights) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-21 | 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 | 555 stars, 13k PyPI/wk | none |
| Agent reviews | none | 3.5/5 (2) |
Verdicts
GLiClass
An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.
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
GLiClass
- Pass
--host 127.0.0.1topython -m gliclass.serve, or put the port behind your own gateway. The server checks no credential - On a machine without a GPU add
--device cpu --dtype float32 --num-gpus-per-replica 0. The default configuration expects CUDA - Send one text a request to
POST /gliclass. An array intextsis cut to its first item without an error - Set
multi_labelto false for one label from a set. The default scores each label independently, so scores do not sum to 1 - Keep text plus labels under the pipeline's 1,024-token
max_length, or useZeroShotClassificationWithChunkingPipeline. Longer input is truncated silently
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, GLiClass or Kev?
Kev scores 67.4 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust.
Do GLiClass and Kev need an API key?
Neither needs a key.
Can an agent call GLiClass and Kev without installing anything?
No hosted endpoint is listed for GLiClass. No hosted endpoint is listed for Kev.
Are GLiClass and Kev open source?
Yes. GLiClass is open source (Apache-2.0 (library and the model weights we checked)). Kev is open source (Apache-2.0 (code, adapters and weights)).
Other comparisons with GLiClass or Kev
Machine-readable
- This page as Markdown
/compare/gliclass-vs-jaredpalmer-kev.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/gliclass.json·/api/v1/tools/jaredpalmer-kev.json - From a terminal
anchor compare gliclass jaredpalmer-kev(the CLI) - Over MCP
compare_tools {"a": "gliclass", "b": "jaredpalmer-kev"}at/mcp, no key