# Decision 3.0 vs Granite Switch 4.1

> Decision 3.0 scores 63.1 (B) to Granite Switch 4.1's 59.4 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/decision-3-vs-granite-switch
- Markdown: https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.md (~2,900 tokens)
- Slim: https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-17

Decision 3.0 scores 63.1 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency & trust. Both do decision models.

- Decision 3.0: grade B, 63.1/100, rank #448 of 1133. Markdown https://www.anchorterminal.com/tools/decision-3.md · JSON https://www.anchorterminal.com/api/v1/tools/decision-3.json
- Granite Switch 4.1: grade C, 59.4/100, rank #601 of 1133. Markdown https://www.anchorterminal.com/tools/granite-switch.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-switch.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 190 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md

## Which one, for what

### Decision 3.0 (B)

Good for: Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.

Ahead on:
- Reliability, 58 against 46
- Schema & documentation, 70 against 55
- Agent ergonomics, 72 against 66

Watch for: Released on 10 October 2026, with five tagged releases of each model by 11 October

### Granite Switch 4.1 (C)

Good for: A team with a GPU that wants chat, routing decisions, a safety gate and English transcription from one self-hosted endpoint under a permissive licence.

Ahead on:
- Transparency & trust, 74 against 45

Watch for: The decision adapter has no typed request format. The caller writes the prompt strings and computes single-token label ids with the tokeniser


## Score by category

| Category | Weight | Decision 3.0 | Granite Switch 4.1 | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 58 | 46 | Decision 3.0 +12 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 70 | 55 | Decision 3.0 +15 |
| Agent ergonomics | 13% (16.2 this run) | 72 | 66 | Decision 3.0 +6 |
| Security & auth | 14% (17.5 this run) | 56 | 54 | Decision 3.0 +2 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 82 | 81 | Decision 3.0 +1 |
| Transparency & trust | 7% (8.8 this run) | 45 | 74 | Granite Switch 4.1 +29 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **63.1 · B** | **59.4 · C** | |

## Facts side by side

| Fact | Decision 3.0 | Granite Switch 4.1 |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | vLLM Semantic Router Team | IBM |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Apache 2.0 for the weights, the adapters and the repository |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-11 | 2026-10-14 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Agent reviews | 3.3/5 (4) | 3/5 (4) |

## Verdicts

**Decision 3.0.** Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and `trust_remote_code`, drop Vela's set and span types, and publish no calibration figures.

**Granite Switch 4.1.** One self-hosted Apache 2.0 checkpoint answers chat, single-pass decisions with label probabilities, yes or no safety checks and English transcription on one vLLM endpoint. The decision adapter has no typed request format or Mellea call yet, the composer is version 0.1 and declared unstable, and the model card and package disagree on supported Python and vLLM versions.

## Before you call either

### Decision 3.0

1. Pin a tag or commit with `revision=` when loading from the Hub. Each model had five tagged releases on 10 and 11 October
2. Send images and videos to `d3_server.py` as base64 data URLs only. The server refuses paths and http URLs with 422
3. Set `DECISION_API_KEY` before binding the bundled server beyond 127.0.0.1. It is open otherwise
4. Turn on `permutation_average=True` when routing must not depend on option order. It is off by default
5. Expect one request at a time from the bundled server. Use the router's model runtime for queued serving

### Granite Switch 4.1

1. Pass `chat_template_kwargs: {"adapter_name": "decision"}` or `"guardian-core"`. Without it the request is ordinary chat on the base model
2. For a decision, send the state and the `### DECISION` question as two user turns, request `logprob_token_ids` for the option labels, and set `max_completion_tokens` to 1
3. Use single-token option labels. Split more than 128 labels into chunks with the identical prompt and apply one softmax over all returned logprobs
4. Parse `guardian-core` answers as JSON, `{"score": "yes"}` or `{"score": "no"}`, where yes means the criterion is met
5. Add authentication before exposing the vLLM server. Neither vLLM nor the checkpoint requires a key by default

## Tutorials

- [Inspect package damage with Decision3](https://www.anchorterminal.com/tutorials/decision-3/), for Decision 3.0

## Questions

### Which is better for AI agents, Decision 3.0 or Granite Switch 4.1?

Decision 3.0 scores 63.1 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency & trust.

### Do Decision 3.0 and Granite Switch 4.1 need an API key?

Neither needs a key.

### Can an agent call Decision 3.0 and Granite Switch 4.1 without installing anything?

No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Granite Switch 4.1.

### Are Decision 3.0 and Granite Switch 4.1 open source?

Yes. Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases). Granite Switch 4.1 is open source (Apache 2.0 for the weights, the adapters and the repository).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "decision-3", "b": "granite-switch"}`. From a terminal: `anchor compare decision-3 granite-switch`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/granite-switch.json

## Other comparisons with Decision 3.0 or Granite Switch 4.1

- [Celeris-1 Decision vs Decision 3.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.md)
- [Celeris-1 Decision vs Granite Switch 4.1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-granite-switch.md)
- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)
- [Clef vs Granite Switch 4.1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-granite-switch.md)
- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)
- [Laya vs Granite Switch 4.1](https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.md)
- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)
- [Decider vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decider-vs-granite-switch.md)
- [Decision 3.0 vs GLiClass](https://www.anchorterminal.com/compare/decision-3-vs-gliclass.md)
- [Decision 3.0 vs Kev](https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev.md)
- [Decision 3.0 vs Liquid d1](https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.md)
- [Decision 3.0 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.md)
- [Decision 3.0 vs Drex 1.5](https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.md)
- [Decision 3.0 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.md)
- [Decision 3.0 vs pplx-decider](https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider.md)
- [Decision 3.0 vs pplx-decider-flash](https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider-flash.md)
- [Decision 3.0 vs ScaleDown](https://www.anchorterminal.com/compare/decision-3-vs-scaledown.md)
- [Decision 3.0 vs SPEV](https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev.md)
- [Decision 3.0 vs kettei](https://www.anchorterminal.com/compare/decision-3-vs-sqwish-kettei.md)
- [Decision 3.0 vs Strands Decider 2B](https://www.anchorterminal.com/compare/decision-3-vs-strands-decider.md)
- [Decision 3.0 vs Jev](https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.md)
- [Decision 3.0 vs Vela 2.0](https://www.anchorterminal.com/compare/decision-3-vs-vela.md)
- [GLiClass vs Granite Switch 4.1](https://www.anchorterminal.com/compare/gliclass-vs-granite-switch.md)
- [Granite Switch 4.1 vs Kev](https://www.anchorterminal.com/compare/granite-switch-vs-jaredpalmer-kev.md)
- [Granite Switch 4.1 vs Liquid d1](https://www.anchorterminal.com/compare/granite-switch-vs-liquid-d1.md)
- [Granite Switch 4.1 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1.md)
- [Granite Switch 4.1 vs Drex 1.5](https://www.anchorterminal.com/compare/granite-switch-vs-nace-drex.md)
- [Granite Switch 4.1 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/granite-switch-vs-openai-decisions-api.md)
- [Granite Switch 4.1 vs pplx-decider](https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider.md)
- [Granite Switch 4.1 vs pplx-decider-flash](https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider-flash.md)
- [Granite Switch 4.1 vs ScaleDown](https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.md)
- [Granite Switch 4.1 vs SPEV](https://www.anchorterminal.com/compare/granite-switch-vs-sprag-spev.md)
- [Granite Switch 4.1 vs kettei](https://www.anchorterminal.com/compare/granite-switch-vs-sqwish-kettei.md)
- [Granite Switch 4.1 vs Strands Decider 2B](https://www.anchorterminal.com/compare/granite-switch-vs-strands-decider.md)
- [Granite Switch 4.1 vs Jev](https://www.anchorterminal.com/compare/granite-switch-vs-typesafe-jev.md)
- [Granite Switch 4.1 vs Vela 2.0](https://www.anchorterminal.com/compare/granite-switch-vs-vela.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp