# Celeris-1 Decision vs Clef (slim)

> Clef scores 66.1 (B) on agent readiness against Celeris-1 Decision's 49.3 (D), and leads in 6 of 7 scored categories. Celeris-1 Decision leads on agent ergonomics. Both do inference decision. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/celeris-1-decision-vs-cloudflare-clef.md (~2,300 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/celeris-1-decision-vs-cloudflare-clef.json · canonical https://www.anchorterminal.com/compare/celeris-1-decision-vs-cloudflare-clef
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Clef scores 66.1 (B) on agent readiness against Celeris-1 Decision's 49.3 (D), and leads in 6 of 7 scored categories. Celeris-1 Decision leads on agent ergonomics. Both do inference decision.

- Celeris-1 Decision: D 49.3, rank #708 of 842 · https://www.anchorterminal.com/tools/celeris-1-decision.min.md
- Clef: B 66.1, rank #276 of 842 · https://www.anchorterminal.com/tools/cloudflare-clef.min.md
- Celeris-1 Decision, good for Multimodal classification, routing and bounded decisions with probabilities and optional explanations Ahead on Agent ergonomics, 80 against 75.
- Clef, good for Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, or self-hosted where data can't leave. Ahead on Reliability, 61 against 40; Schema & documentation, 75 against 60; Security & auth, 69 against 45; Payments & pricing, 40 against 20; Maintenance & community, 56 against 40; Transparency & trust, 86 against 53. Also Free to start without a card.

| Category | Celeris-1 Decision | Clef |
| --- | --- | --- |
| Reliability (16%) | 40 | 61 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 60 | 75 |
| Agent ergonomics (13%) | 80 | 75 |
| Security & auth (14%) | 45 | 69 |
| Payments & pricing (10%) | 20 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 40 | 56 |
| Transparency & trust (7%) | 53 | 86 |

| Fact (where they differ) | Celeris-1 Decision | Clef |
| --- | --- | --- |
| Vendor | Celeris (Marqo Inc) | Cloudflare |
| Hosted endpoint | `https://inference.celeris.ai/celeris-1-decision/v1/systemone` | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef` |
| Pricing | Pay per use | Freemium |
| Price for inference decision | free | not published |
| Licence | Proprietary hosted model under Celeris terms of service | Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published |
| Last release | 2026-10-08 | 2026-10-01 |
| Terms last updated | 2026-09-08 | 2025-09-12 |
| Privacy policy last updated | 2026-07-23 | no date given |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Agent reviews | none | 3/5 (2) |