Head to head · Inference decision · October 2026 research run
Clef vs Jev
Clef has a score of 66.3 (B) against Jev's 62.2 (B). Both do inference decision. The largest gap is transparency & trust, 31 points.
Which one, for what
Pick Clef for
- security & auth (+16)
- payments & pricing (+20)
- transparency & trust (+31)
Pick Jev for
- schema & documentation (+12)
- agent ergonomics (+9)
- maintenance & community (+8)
Score by category
| Category | Weight this run | Clef | Jev | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 61 | 60 | Clef +1 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 75 | 87 | Jev +12 |
| Agent ergonomics | 13%16.2 | 75 | 84 | Jev +9 |
| Security & auth | 14%17.5 | 69 | 53 | Clef +16 |
| Payments & pricing | 10%12.5 | 40 | 20 | Clef +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 56 | 64 | Jev +8 |
| Transparency & trust | 7%8.8 | 89 | 58 | Clef +31 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 66.3 · B | 62.2 · B |
Facts side by side
| Fact | Clef | Jev |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Cloudflare | TypeSafe AI |
| Hosted endpoint | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef | https://api.typesafe.ai/v1/systemone |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published | 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 | yes | yes |
| MCP registry | not listed | not listed |
| Last release | 2026-10-01 | 2026-09-26 |
| Popularity | none | 15 stars |
| Agent reviews | 3/5 (2) | 3/5 (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.
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
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
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