# Gemini Decision 1 vs Granite Switch 4.1 (slim)

> Gemini Decision 1 and Granite Switch 4.1 score within a point of each other for decision models, 63.2 and 62.5 out of 100. 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-granite-switch.md (~6,650 tokens) · this version ~1,180 tokens · JSON https://www.anchorterminal.com/compare/gemini-decision-1-vs-granite-switch.json · canonical https://www.anchorterminal.com/compare/gemini-decision-1-vs-granite-switch
- 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 and Granite Switch 4.1 score within a point of each other on agent readiness, 63.2 (B) and 62.5 (B). Granite Switch 4.1 leads on reliability, security & auth, payments & pricing and transparency & trust. 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
- Granite Switch 4.1: B 62.5, rank #660 of 1524 · https://www.anchorterminal.com/tools/granite-switch.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 57; Agent ergonomics, 85 against 66; Maintenance & community, 79 against 68. Also Cheaper for decision models, $0 against $0 per 1M tokens.
- Granite Switch 4.1, good for A team with a GPU that wants chat, routing decisions, a safety gate and transcription in seven languages from one self-hosted endpoint under a permissive licence. Ahead on Reliability, 46 against 40; Security & auth, 54 against 45; Payments & pricing, 90 against 60; Transparency & trust, 76 against 70. Also No key needed to call it; Open source.

| Category | Gemini Decision 1 | Granite Switch 4.1 |
| --- | --- | --- |
| Reliability (16%) | 40 | 46 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 80 | 57 |
| Agent ergonomics (13%) | 85 | 66 |
| Security & auth (14%) | 45 | 54 |
| Payments & pricing (10%) | 60 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 79 | 68 |
| Transparency & trust (7%) | 70 | 76 |

| Fact (where they differ) | Gemini Decision 1 | Granite Switch 4.1 |
| --- | --- | --- |
| Vendor | Google | IBM |
| 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 for the weights, the adapters and the repository |
| llms.txt | yes | no |
| Last release | 2026-11-11 | 2026-10-27 |
| 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 |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Payments & pricing, Granite Switch 4.1 +30: Gemini Decision 1 60 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Granite Switch 4.1 90 (Self-hosted rule.)
- Schema & documentation, Gemini Decision 1 +23: Gemini Decision 1 80 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Granite Switch 4.1 57 (Read for a model the owner serves.)
- Agent ergonomics, Gemini Decision 1 +19: Gemini Decision 1 85 (Read on the tool lines, as the other decision-model listings are.); Granite Switch 4.1 66 (Read as an endpoint an agent calls for a decision, as with Vela and Decision 3.0. A decision returns one token and its label logprobs, a guardian check up to 16…)
- Maintenance & community, Gemini Decision 1 +11: Gemini Decision 1 79 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Granite Switch 4.1 68 (Read as a model, for deprecation notice and model churn rather than release counts, on the lines used for Granite Guardian, Decider, Kev and Strands Decider (re…)
- Security & auth, Granite Switch 4.1 +9: Gemini Decision 1 45 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Granite Switch 4.1 54 (Read as a model the owner runs, on the model lines as Granite Guardian is, with retention and training in place of the read-only line.)
- Reliability, Granite Switch 4.1 +6: Gemini Decision 1 40 (Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.); Granite Switch 4.1 46 (Scored on the local-software lines, since the owner serves the checkpoint with vLLM.)