# Gemini Decision 1 vs SPEV (slim)

> Gemini Decision 1 scores 63.2 (B) to SPEV's 50.9 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/gemini-decision-1-vs-sprag-spev.md (~5,100 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/gemini-decision-1-vs-sprag-spev.json · canonical https://www.anchorterminal.com/compare/gemini-decision-1-vs-sprag-spev
- 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 SPEV's 50.9 (D), and leads in 5 of 7 scored categories. Both do decision models.

- Gemini Decision 1: B 63.2, rank #630 of 1524 · https://www.anchorterminal.com/tools/gemini-decision-1.min.md
- SPEV: D 50.9, rank #1115 of 1524 · https://www.anchorterminal.com/tools/sprag-spev.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 Agent ergonomics, 85 against 76; Security & auth, 45 against 33; Payments & pricing, 60 against 30; Maintenance & community, 79 against 49; Transparency & trust, 70 against 59.
- SPEV, good for Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted. Also A hosted endpoint, with nothing to install.

| Category | Gemini Decision 1 | SPEV |
| --- | --- | --- |
| Reliability (16%) | 40 | 42 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 80 | 81 |
| Agent ergonomics (13%) | 85 | 76 |
| Security & auth (14%) | 45 | 33 |
| Payments & pricing (10%) | 60 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 79 | 49 |
| Transparency & trust (7%) | 70 | 59 |

| Fact (where they differ) | Gemini Decision 1 | SPEV |
| --- | --- | --- |
| Vendor | Google | Sprag |
| Hosted endpoint | no (local only) | `https://api.sprag.ai/v1/decisions` |
| Price for decision models | free | not published |
| 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 | Apache-2.0 (weights and inference code, following the Qwen3-Omni base). Training code and data aren't published |
| Last release | 2026-11-11 | 2026-10-21 |
| Terms last updated | 2026-04-28 | 2026-09-01 |
| Privacy policy last updated | 2026-10-01 | 2026-08-01 |
| Customer content may train models | yes | yes, with an opt-out |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |

Why the edge:
- Payments & pricing, Gemini Decision 1 +30: Gemini Decision 1 60 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); SPEV 30 (No x402, MPP or L402 (0).)
- Maintenance & community, Gemini Decision 1 +30: Gemini Decision 1 79 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); SPEV 49 (Read for a model.)
- Security & auth, Gemini Decision 1 +12: Gemini Decision 1 45 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); SPEV 33 (Read for a model API.)
- Transparency & trust, Gemini Decision 1 +11: Gemini Decision 1 70 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); SPEV 59 (Weights and inference code under Apache-2.0 with third-party notices for the Qwen base and the AMI corpus.)
- Agent ergonomics, Gemini Decision 1 +9: Gemini Decision 1 85 (Read on the tool lines, as the other decision-model listings are.); SPEV 76 (Read as an API an agent calls for a decision.)