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

> Gemini Decision 1 scores 63.2 (B) to Microsoft-Decision-1's 42.1 (E) for decision models. Gemini Decision 1 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/gemini-decision-1-vs-microsoft-decision-1.md (~6,000 tokens) · this version ~1,230 tokens · JSON https://www.anchorterminal.com/compare/gemini-decision-1-vs-microsoft-decision-1.json · canonical https://www.anchorterminal.com/compare/gemini-decision-1-vs-microsoft-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 Microsoft-Decision-1's 42.1 (E), and leads in 5 of 7 scored categories. Microsoft-Decision-1 leads on security & auth. Both do decision models. Gemini Decision 1 is cheaper for decision models, $0 against $0 per 1M tokens.

- Gemini Decision 1: B 63.2, rank #630 of 1524 · https://www.anchorterminal.com/tools/gemini-decision-1.min.md
- Microsoft-Decision-1: E 42.1, rank #1314 of 1524 · https://www.anchorterminal.com/tools/microsoft-decision-1.min.md
- 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 43; Agent ergonomics, 85 against 50; Payments & pricing, 60 against 30; Maintenance & community, 79 against 34; Transparency & trust, 70 against 36. Also Cheaper for decision models, $0 against $0 per 1M tokens.
- Microsoft-Decision-1, good for Routing, classification, prioritisation and rubric checks over text, where a fixed set of options and a low price per token matter more than generated text. Ahead on Security & auth, 52 against 45. Also Cheaper for decision models, $0 against $0 per 1M tokens.

| Category | Gemini Decision 1 | Microsoft-Decision-1 |
| --- | --- | --- |
| Reliability (16%) | 40 | 40 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 80 | 43 |
| Agent ergonomics (13%) | 85 | 50 |
| Security & auth (14%) | 45 | 52 |
| Payments & pricing (10%) | 60 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 79 | 34 |
| Transparency & trust (7%) | 70 | 36 |

| Fact (where they differ) | Gemini Decision 1 | Microsoft-Decision-1 |
| --- | --- | --- |
| Vendor | Google | Microsoft |
| Auth | API key | OAuth or key |
| Licence | 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 | Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found. |
| llms.txt | yes | no |
| Last release | 2026-11-11 | 2026-10-09 |
| Terms last updated | 2026-04-28 | no document linked |
| Privacy policy last updated | 2026-10-01 | not read yet |
| Customer content may train models | yes | not read yet |
| Terms restrict automated access | yes | not read yet |
| Terms restrict benchmarking | yes | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Maintenance & community, Gemini Decision 1 +45: Gemini Decision 1 79 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Microsoft-Decision-1 34 (Model reading of the checklist (recency, notice, churn, changelog, replies, SDKs, runtimes), as the Google Lyria and Soundverse listings read it; the 10 October…)
- Schema & documentation, Gemini Decision 1 +37: Gemini Decision 1 80 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Microsoft-Decision-1 43 (No machine-readable contract for the model was found (0 of 25).)
- Agent ergonomics, Gemini Decision 1 +35: Gemini Decision 1 85 (Read on the tool lines, as the other decision-model listings are.); Microsoft-Decision-1 50 (The response is one probability per option, and the caller sets the number of questions and options.)
- Transparency & trust, Gemini Decision 1 +34: Gemini Decision 1 70 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Microsoft-Decision-1 36 (No licence for the hosted model is stated in the announcement or the Tech Community post, re-read on 10 November, nor on OpenRouter's page per the 10 October ch…)
- Payments & pricing, Gemini Decision 1 +30: Gemini Decision 1 60 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Microsoft-Decision-1 30 (The price is published without a login at $0.042 per million input tokens, with output free, earning 20 of 20. No x402, MPP or L402 was found in the announcemen…)
- Security & auth, Microsoft-Decision-1 +7: Gemini Decision 1 45 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Microsoft-Decision-1 52 (Model reading of the checklist (credential, training, retention, operator visibility, programme), as the Google Lyria and Soundverse listings read it; the 10 Oc…)