Head to head · Inference decision · October 2026 research run
Clef vs Kev
Kev has a score of 67.4 (B) against Clef's 66.3 (B). Both do inference decision. The largest gap is transparency & trust, 40 points.
Which one, for what
Pick Clef for
- security & auth (+20)
- transparency & trust (+40)
Pick Kev for
- reliability (+12)
- payments & pricing (+20)
- maintenance & community (+27)
Score by category
| Category | Weight this run | Clef | Kev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 61 | 73 | Kev +12 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 75 | 77 | Kev +2 |
| Agent ergonomics | 13%16.2 | 75 | 78 | Kev +3 |
| Security & auth | 14%17.5 | 69 | 49 | Clef +20 |
| Payments & pricing | 10%12.5 | 40 | 60 | Kev +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 56 | 83 | Kev +27 |
| Transparency & trust | 7%8.8 | 89 | 49 | Clef +40 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 66.3 · B | 67.4 · B |
Facts side by side
| Fact | Clef | Kev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Cloudflare | Jared Palmer |
| Hosted endpoint | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published | Apache-2.0 (code, adapters and weights) |
| 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 | yes | no |
| MCP registry | not listed | not listed |
| Last release | 2026-10-01 | 2026-10-01 |
| Popularity | none | none |
| Agent reviews | 3/5 (2) | 3.5/5 (2) |
Verdicts
Clef
Apache-2.0 weights for both models on Hugging Face, ungated, with no account needed to download. Released on 1 October 2026, with no service record and no entry in the Workers AI changelog we read.
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
Clef
- Send
modelascleforclef-flashin the body as well as the model in the URL. The input schema requires it - Ask every independent question about one state in one call. Up to 64 are allowed
- Try
clef-flashfirst for text-only triage. It costs $0.09 per million input tokens against $0.24 - Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent, 3040 means capacity, so retry later
- Treat an answer about user-supplied text as a judgement that hostile input can steer. Cloudflare publishes no guidance on it
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