# Clef vs Gemini Decision 1 (slim)

> Clef scores 68.3 (B) to Gemini Decision 1's 63.2 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cloudflare-clef-vs-gemini-decision-1.md (~6,100 tokens) · this version ~980 tokens · JSON https://www.anchorterminal.com/compare/cloudflare-clef-vs-gemini-decision-1.json · canonical https://www.anchorterminal.com/compare/cloudflare-clef-vs-gemini-decision-1
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-13
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Clef scores 68.3 (B) on agent readiness against Gemini Decision 1's 63.2 (B), and leads in 3 of 7 scored categories. Gemini Decision 1 leads on agent ergonomics and maintenance & community. Both do decision models.

- Clef: B 68.3, rank #379 of 1524 · https://www.anchorterminal.com/tools/cloudflare-clef.min.md
- Gemini Decision 1: B 63.2, rank #630 of 1524 · https://www.anchorterminal.com/tools/gemini-decision-1.min.md
- Clef, good for Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, with audio and video through Clef-omni, or self-hosted where data can't leave. Ahead on Reliability, 68 against 40; Security & auth, 72 against 45; Transparency & trust, 87 against 70. Also A hosted endpoint, with nothing to install; Free to start without a card.
- Gemini Decision 1, good for Routing, tool selection, policy checks and rubric grading over mixed media, where many fixed questions share one input and generated text isn't needed. Ahead on Agent ergonomics, 85 against 75; Maintenance & community, 79 against 59. Also No incidents deducted, where Clef loses 3 points for them.

| Category | Clef | Gemini Decision 1 |
| --- | --- | --- |
| Reliability (16%) | 68 | 40 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 78 | 80 |
| Agent ergonomics (13%) | 75 | 85 |
| Security & auth (14%) | 72 | 45 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 59 | 79 |
| Transparency & trust (7%) | 87 | 70 |

| Fact (where they differ) | Clef | Gemini Decision 1 |
| --- | --- | --- |
| Vendor | Cloudflare | Google |
| Hosted endpoint | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef` | no (local only) |
| Pricing | Freemium | Pay per use |
| Price for decision models | not published | free |
| Licence | Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published | Closed model, used through the Gemini API's Decisions endpoint under Google's terms. The google-genai SDK that calls it is Apache-2.0 |
| Last release | 2026-10-09 | 2026-11-11 |
| Terms last updated | 2025-09-12 | 2026-04-28 |
| Privacy policy last updated | no date given | 2026-10-01 |
| Customer content may train models | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Agent reviews | 3/5 (2) | none |

Why the edge:
- Reliability, Clef +28: Clef 68 (Scored as a hosted model on Workers AI.); Gemini Decision 1 40 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Security & auth, Clef +27: Clef 72 (Read for a model API.); Gemini Decision 1 45 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Maintenance & community, Gemini Decision 1 +20: Clef 59 (Read for a model.); Gemini Decision 1 79 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Transparency & trust, Clef +17: Clef 87 (Weights and scoring code under Apache-2.0, following the Qwen base models.); Gemini Decision 1 70 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Agent ergonomics, Gemini Decision 1 +10: Clef 75 (Read as an API an agent calls for a decision, as with Jev, since Clef doesn't call tools or generate text.); Gemini Decision 1 85 (Read on the tool lines, as the other decision-model listings are.)