# Gemini Decision 1 vs GLiClass (slim)

> Gemini Decision 1 scores 63.2 (B) to GLiClass's 55.5 (C) 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-gliclass.md (~6,200 tokens) · this version ~1,130 tokens · JSON https://www.anchorterminal.com/compare/gemini-decision-1-vs-gliclass.json · canonical https://www.anchorterminal.com/compare/gemini-decision-1-vs-gliclass
- 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 GLiClass's 55.5 (C), and leads in 5 of 7 scored categories. GLiClass leads on payments & pricing. 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
- GLiClass: C 55.5, rank #959 of 1524 · https://www.anchorterminal.com/tools/gliclass.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 49; Agent ergonomics, 85 against 60; Security & auth, 45 against 38; Maintenance & community, 79 against 64; Transparency & trust, 70 against 65. Also Cheaper for decision models, $0 against $0 per 1M tokens.
- GLiClass, good for Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once. Ahead on Payments & pricing, 90 against 60. Also No key needed to call it; Open source.

| Category | Gemini Decision 1 | GLiClass |
| --- | --- | --- |
| Reliability (16%) | 40 | 43 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 80 | 49 |
| Agent ergonomics (13%) | 85 | 60 |
| Security & auth (14%) | 45 | 38 |
| Payments & pricing (10%) | 60 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 79 | 64 |
| Transparency & trust (7%) | 70 | 65 |

| Fact (where they differ) | Gemini Decision 1 | GLiClass |
| --- | --- | --- |
| Vendor | Google | Knowledgator |
| Auth | API key | None |
| Pricing | Pay per use | Free |
| 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 (library and the model weights we checked) |
| llms.txt | yes | no |
| Last release | 2026-11-11 | 2026-10-31 |
| Terms last updated | 2026-04-28 | no document linked |
| Privacy policy last updated | 2026-10-01 | no document linked |
| 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 |
| Popularity | none | 555 stars |

Why the edge:
- Schema & documentation, Gemini Decision 1 +31: Gemini Decision 1 80 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); GLiClass 49 (Read for a model the owner serves.)
- Payments & pricing, GLiClass +30: Gemini Decision 1 60 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); GLiClass 90 (Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up under the self-hosted rule.)
- Agent ergonomics, Gemini Decision 1 +25: Gemini Decision 1 85 (Read on the tool lines, as the other decision-model listings are.); GLiClass 60 (Read as an API an agent calls for a decision, as with the other decision models.)
- Maintenance & community, Gemini Decision 1 +15: Gemini Decision 1 79 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); GLiClass 64 (Read as a model, for deprecation notice and model churn rather than release counts, on the lines used for Kev, Vela 2.0, Decider and the other decision models l…)
- Security & auth, Gemini Decision 1 +7: Gemini Decision 1 45 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); GLiClass 38 (Read as a model, for retention, training and zero-retention options in place of read-only modes, on the lines used for Kev, Vela 2.0 and the other decision mode…)
- Transparency & trust, Gemini Decision 1 +5: Gemini Decision 1 70 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); GLiClass 65 (Apache-2.0 for the library and the weights, with `train.py`, the training datasets named on the card and an arXiv paper (30).)