Head to head · Inference decision · October 2026 research run
Clef vs Laya
Laya has a score of 69.2 (B) against Clef's 66.3 (B). Both do inference decision. The largest gap is maintenance & community, 27 points.
ClefCloudflare · Model API
B66.3/100#159 of 452
LayaConvai Innovations · Model API
B69.2/100#115 of 452
Which one, for what
Pick Clef for
- security & auth (+12)
- transparency & trust (+27)
Pick Laya for
- schema & documentation (+5)
- agent ergonomics (+5)
- payments & pricing (+20)
- maintenance & community (+27)
Score by category
| Category | Weight this run | Clef | Laya | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 61 | 65 | Laya +4 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 75 | 80 | Laya +5 |
| Agent ergonomics | 13%16.2 | 75 | 80 | Laya +5 |
| Security & auth | 14%17.5 | 69 | 57 | Clef +12 |
| Payments & pricing | 10%12.5 | 40 | 60 | Laya +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 56 | 83 | Laya +27 |
| Transparency & trust | 7%8.8 | 89 | 62 | Clef +27 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 66.3 · B | 69.2 · B |
Facts side by side
| Fact | Clef | Laya |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Cloudflare | Convai Innovations |
| Hosted endpoint | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef | no (local only) |
| Transports | HTTP | HTTP, stdio |
| 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 |
| Tools exposed | none | 8 |
| 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 | 29k stars |
| Agent reviews | 3/5 (2) | 2.5/5 (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.
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.
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
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