# Celeris-1 Decision vs Gemini Decision 1 (slim)

> Gemini Decision 1 scores 63.2 (B) to Celeris-1 Decision's 51 (D) for decision models. Celeris-1 Decision is cheaper for decision models, $0 against $0 per 1M tokens. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gemini-decision-1.md (~5,600 tokens) · this version ~1,130 tokens · JSON https://www.anchorterminal.com/compare/celeris-1-decision-vs-gemini-decision-1.json · canonical https://www.anchorterminal.com/compare/celeris-1-decision-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)

Gemini Decision 1 scores 63.2 (B) on agent readiness against Celeris-1 Decision's 51 (D), and leads in 5 of 7 scored categories. Celeris-1 Decision leads on reliability. Both do decision models. Celeris-1 Decision is cheaper for decision models, $0 against $0 per 1M tokens.

- Celeris-1 Decision: D 51, rank #1111 of 1524 · https://www.anchorterminal.com/tools/celeris-1-decision.min.md
- Gemini Decision 1: B 63.2, rank #630 of 1524 · https://www.anchorterminal.com/tools/gemini-decision-1.min.md
- Celeris-1 Decision, good for Multimodal classification, routing and bounded decisions with probabilities and optional explanations Ahead on Reliability, 50 against 40. Also Cheaper for decision models, $0 against $0 per 1M tokens; A hosted endpoint, with nothing to install.
- 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 Schema & documentation, 80 against 60; Agent ergonomics, 85 against 80; Payments & pricing, 60 against 30; Maintenance & community, 79 against 44; Transparency & trust, 70 against 55. Also Cheaper for decision models, $0 against $0 per 1M tokens.

| Category | Celeris-1 Decision | Gemini Decision 1 |
| --- | --- | --- |
| Reliability (16%) | 50 | 40 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 60 | 80 |
| Agent ergonomics (13%) | 80 | 85 |
| Security & auth (14%) | 45 | 45 |
| Payments & pricing (10%) | 30 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 44 | 79 |
| Transparency & trust (7%) | 55 | 70 |

| Fact (where they differ) | Celeris-1 Decision | Gemini Decision 1 |
| --- | --- | --- |
| Vendor | Celeris (Marqo Inc) | Google |
| Hosted endpoint | `https://inference.celeris.ai/celeris-1-decision/v1/systemone` | no (local only) |
| Licence | Proprietary hosted model under Celeris terms of service | 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 | 2026-10-08 | 2026-11-11 |
| Terms last updated | 2026-09-08 | 2026-04-28 |
| Privacy policy last updated | 2026-07-23 | 2026-10-01 |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | yes |

Why the edge:
- Maintenance & community, Gemini Decision 1 +35: Celeris-1 Decision 44 (Read for a model, on the decision-model split used for Jev, OpenAI Decisions, pplx-decider and Liquid d1 (notice 0 to 12 and churn 0 to 8 in place of the 20-poi…); Gemini Decision 1 79 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Payments & pricing, Gemini Decision 1 +30: Celeris-1 Decision 30 (Public per-token prices earn 20. No machine-payment protocol found (0).); Gemini Decision 1 60 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Schema & documentation, Gemini Decision 1 +20: Celeris-1 Decision 60 (No public machine-readable decision contract found (0).); Gemini Decision 1 80 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Transparency & trust, Gemini Decision 1 +15: Celeris-1 Decision 55 (Closed model with service terms earns 15. Privacy and security statements explain processing and 90-day usage records, but not prompt retention or a training ex…); Gemini Decision 1 70 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Reliability, Celeris-1 Decision +10: Celeris-1 Decision 50 (Read as a hosted model API.); Gemini Decision 1 40 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.)
- Agent ergonomics, Gemini Decision 1 +5: Celeris-1 Decision 80 (Compact probability answers earn 25. Multiple questions, bounded options and image controls earn 15 of 20; the docs now state a 131,072-token window but no outp…); Gemini Decision 1 85 (Read on the tool lines, as the other decision-model listings are.)