Head to head · Decision models · October 2026 research run
Granite Switch 4.1 vs Microsoft-Decision-1.1
Granite Switch 4.1 scores 62.5 (B) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in 6 of 7 scored categories. Both do decision models. Microsoft-Decision-1.1 is cheaper for decision models, $0 against $0 per 1M tokens.
Best decision models for AI agents · All 263 decisions comparisons
Which one, for what
Best 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
- Schema & documentation, 57 against 43
- Agent ergonomics, 66 against 50
- Payments & pricing, 90 against 30
- Maintenance & community, 68 against 44
- Transparency & trust, 76 against 34
Also in its favour
- No key needed to call it
- Open source
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
Best 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.
Also in its favour
- Cheaper for decision models, $0 against $0 per 1M tokens
Watch for
No machine-readable contract or reference page with the request schema was found
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing Granite Switch 4.1 +60
Granite Switch 4.1 90
Self-hosted rule. Nothing to buy, and the Apache 2.0 licence allows commercial use at no charge (20). Free to run with no card (20). The weights are not gated, so an agent can fetch and run them with no sign-up (20). No payment protocol (0). IBM hosts no endpoint for Granite Switch that we found, and Hugging Face lists no inference provider for it. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.
Microsoft-Decision-1.1 30
Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. 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 announcement, the Foundry sample or OpenRouter's model page, earning 0 of 40. No free tier or trial without a card was found (0 of 20). The Foundry route needs an Azure subscription and deployment set up by a person, and OpenRouter's signup was not checked (0 of 20). Total 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30. For 1.1: Foundry prices now differ by deployment ($0.042, $0.046, $0.05), all published without a login; no change to the award.
Transparency & trust Granite Switch 4.1 +42
Granite Switch 4.1 76
Weights, adapters and code are Apache 2.0 with no gate, on an Apache 2.0 Granite 4.1 base. The decision adapter card adds that base-model use is also governed by the Granite model terms (28 of 30). Inputs stay on the owner's hardware, so no privacy statement applies. Neither the Switch cards nor the decision adapter card describe training data (18 of 30). No deprecation policy. Revision 4.1.1 replaced 4.1 on main on 27 October 2026 with a dated note and a Hub tag that keeps 4.1 loadable, while the 8B preview was overwritten in place on 3 May and 15 October 2026 (8 of 20, 5 on 17 October). No telemetry code found in the package source and no statement either way. Weights download through Hugging Face (10 of 20). 28 + 18 + 8 + 10 = 64.
Microsoft-Decision-1.1 34
Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. 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 check, and no Microsoft weights repository was found, so 0 of 30 for licence clarity. Microsoft's Foundry data page states no storage in the model, no training on prompts and processing within the geography or data zone, but abuse monitoring stores prompts for human review. The page does not say whether it covers this model, so 12 of 30. No dated deprecation policy was found, 0 of 20. The US and EU Datazone deployment types disclose where processing may happen, earning 10 of 20. No subprocessor list was read. Total 22.
Maintenance & community Granite Switch 4.1 +24
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 (recency 30, deprecation 12, churn 8, responsiveness 25, packages 15, health 10). The 17 October note used the tool lines. Revision 4.1.1 of the 8B and 30B checkpoints, with updated decision weights and speech input in seven languages, was published on 27 October 2026, 8 days before the check (30). No deprecation policy. 4.1.1 replaced 4.1 on main with a dated What's New note and a Hub tag that pins 4.1, while the preview repositories were rebuilt in place on 3 May and 15 October 2026 (5 of 12, level with Decider and Granite Guardian). Previews on 1 May, 4.1 on 14 October and 4.1.1 on 27 October, two replacements of main in 13 days with the earlier one still loadable by tag (4 of 8, level with Decider and Strands Decider). The clone's 200 newest commits come from 19 authors, with pull requests numbered to #154 and merged within days, and GitHub issue reply times couldn't be read. On the Hub, IBM merged its own pull requests and answered one of four questions (30B thread 5, six minutes after it was opened on 31 October), while the threads of 18 October (8B), 26 October (30B GGUF) and 2 November (30B) had no reply on 4 November, counted by author and date only (10 of 25). An official Python package with a vLLM plug-in, IBM's own GGUF builds of the 8B and 30B since 22 October (made from 4.1, before 4.1.1), and Mellea for the guardian adapter. The decision adapter still has no Mellea call, and whether llama.cpp runs the composed switch layer is unchecked (11 of 15). CI, a lock file and dependency ranges that track vLLM 0.26 to 0.30 (8 of 10). 30 + 5 + 4 + 10 + 11 + 8 = 68.
Microsoft-Decision-1.1 44
Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. Model reading of the checklist (recency, notice, churn, changelog, replies, SDKs, runtimes), as the Google Lyria and Soundverse listings read it; the 10 October note read the tool lines (30 + 0 + 0 + 10 + 0 = 40). The model was released on 9 October 2026, 32 days before this check, and no later dated change was found; the Command Line post was last modified on 10 October to add benchmarks (20 of 30, cause time). No deprecation policy or notice period for the model was found (0 of 12). No model or version has been removed, but OpenRouter says the weights are updated continually with no version names, per the 10 October check (4 of 8). No changelog (0 of 15). The one reader question under the Tech Community post, of 15 October, has no reply (0 of 10). OpenRouter's SDK lists the Decisions method in Python, TypeScript and Go as alpha, per the 10 October check; openrouter.ai isn't read in this run (10 of 15). No supported runtimes stated (0 of 10). 20 + 0 + 4 + 0 + 0 + 10 + 0 = 34. For 1.1: released 17 November 2026, the day before this check, so recency earns 30 where Decision-1 had 20. 34 + 10 = 44.
Agent ergonomics Granite Switch 4.1 +16
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 tokens, and the state turn can share vLLM's prefix cache with chat. Context is 131,072 tokens (21 of 25). The caller picks the adapter per request, the options and the label ids. More than 128 options need one request per 128 (13 of 20). Errors are vLLM's, with the 128-id limit and the audio prompt-length error documented. A guardian answer is JSON in text with no stated handling for a malformed reply (8 of 20). Requests are stateless and the examples set temperature 0, so a decision can be repeated safely (16 of 20). The OpenAI SDK works, and Mellea wraps the guardian adapter, but the decision adapter has no Mellea call yet, label ids need the tokeniser, and vLLM needs a GPU (8 of 15).
Microsoft-Decision-1.1 50
Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. The response is one probability per option, and the caller sets the number of questions and options. This earns 20 of 25 for context cost. No pagination, filtering or per-request limits were found for this model, earning 10 of 20. No documented error codes and recovery actions were found, earning 5 of 20. No idempotency or retry guidance was found, earning 5 of 20. Three required fields, a Python sample and OpenRouter's alpha SDK in three languages earn 10 of 15, since the SDK method is alpha. Total 50.
Schema & documentation Granite Switch 4.1 +14
Granite Switch 4.1 57
Read for a model the owner serves. The route is vLLM's OpenAI chat-completions API, and the adapter contract is the chat template, adapter_index.json and one io.yaml per adapter. There is no specification file of its own (10 of 25). We found no llms.txt. The model cards, BUILD.md, the adapter card and the repository docs are Markdown on Hugging Face and GitHub (5 of 10). The card says what each adapter does, that decision probabilities are a prior and not a certified classification outside trained domains, that the guardian adapter is no substitute for application testing, and the speech limits (16 of 20). A decision request is free-form prompt text with token ids the caller computes, and the guardian criterion is free text. The adapter card defines choice, noul and score types, but nothing on the endpoint enforces them (6 of 15). Python and curl examples for both adapters and audio, a chunking recipe for wide questions, and two documented HTTP 400 cases (11 of 15). Versioned model names, and since 27 October a dated What's New section in each card with a revision table and a Hub tag that pins 4.1 (granite-switch-4.1-8b, granite-switch-4.1-30b). The package changelog still has one entry, and the card names a granite-switch-4.1.1-8b tag that the Hub's tag list doesn't have (9 of 15, 7 on 17 October). 10 + 5 + 16 + 6 + 11 + 9 = 57.
Microsoft-Decision-1.1 43
Read 18 November 2026 for Microsoft-Decision-1.1. Where 1.1's own pages don't cover a line, the reading is the Microsoft-Decision-1 listing's of 10 November, the same platform and route. No machine-readable contract for the model was found (0 of 25). OpenRouter's llms.txt indexes its Decisions SDK pages as Markdown, earning 10 of 10 for the OpenRouter route. Microsoft's post states what the model is for and what it is not for, earning 15 of 20 without a reference page. The question fields (type, instructions and criteria) are typed in Microsoft's sample, earning 10 of 15, with no published schema read. The sample shows a request and handles an HTTP error, but no documented error responses were found, earning 8 of 15. No changelog was found, and OpenRouter says weights are updated continually while the API shape stays the same, so 0 of 15. Total 43. For 1.1: Foundry's list of models sold by Azure now has an entry for it (inputs, question formats, 32K tokens), still no machine-readable contract; no change to the award.
Score by category
| Category | Weight | Granite Switch 4.1 | Microsoft-Decision-1.1 | Edge |
|---|---|---|---|---|
| Reliability | 16% | 46 | 50 | Microsoft-Decision-1.1 +4 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 57 | 43 | Granite Switch 4.1 +14 |
| Agent ergonomics | 13% | 66 | 50 | Granite Switch 4.1 +16 |
| Security & auth | 14% | 54 | 52 | Granite Switch 4.1 +2 |
| Payments & pricing | 10% | 90 | 30 | Granite Switch 4.1 +60 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 68 | 44 | Granite Switch 4.1 +24 |
| Transparency & trust | 7% | 76 | 34 | Granite Switch 4.1 +42 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 62.5/100 | E 44.8/100 |
Facts side by side
| Fact | Granite Switch 4.1 | Microsoft-Decision-1.1 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | IBM | Microsoft |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Pay per use |
| Price for decision models | free | free |
| x402 | no | no |
| Licence | Apache 2.0 for the weights, the adapters and the repository | Not stated. Microsoft's post and OpenRouter's page name no licence for the hosted model. It's built on Gemma 4 26B A4B, and no Microsoft weights were released. |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-27 | 2026-11-17 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no date given |
| Agent reviews | 3/5 (4) | none |
How the scores have moved
Verdicts
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 transcription in seven languages on one vLLM endpoint. Revision 4.1.1 (27 October 2026) updated the decision weights, with a tag that pins 4.1. The decision adapter still has no typed request format or Mellea call, and the composer is version 0.1.
Microsoft-Decision-1.1
A generally available decision model that returns a calibrated probability per option, now from images as well as text, at $0.042 per million input tokens with output free on Foundry and OpenRouter. No published schema, changelog, licence or deprecation policy was found.
Before you call either
Granite Switch 4.1
- Pass
chat_template_kwargs: {"adapter_name": "decision"}or"guardian-core". Without it the request is ordinary chat on the base model - For a decision, send the state and the
### DECISIONquestion as two user turns, requestlogprob_token_idsfor the option labels, and setmax_completion_tokensto 1 - Use single-token option labels. Split more than 128 labels into chunks with the identical prompt and apply one softmax over all returned logprobs
- Pin
--revision granite-switch-4.1-8b(or-30b) to keep the 4.1 decision weights. main now serves 4.1.1 - Add authentication before exposing the vLLM server. Neither vLLM nor the checkpoint requires a key by default
Microsoft-Decision-1.1
- On Foundry, deploy Microsoft-Decision-1.1 in a Foundry resource and call it with a Microsoft Entra bearer token
- On OpenRouter, call microsoft/microsoft-decision-1.1 through the Decisions API, not chat completions
- Send fixed answer options and read the probabilities; it writes no explanation
- Set a confidence threshold and defer to a larger model below it
Questions
Which is better for AI agents, Granite Switch 4.1 or Microsoft-Decision-1.1?
Granite Switch 4.1 scores 62.5 (B) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in 6 of 7 scored categories.
Which is cheaper for decision models, Granite Switch 4.1 or Microsoft-Decision-1.1?
Granite Switch 4.1, at free against free for Microsoft-Decision-1.1. These are the vendors' published prices for the job.
Do Granite Switch 4.1 and Microsoft-Decision-1.1 need an API key?
Granite Switch 4.1 needs no key. Microsoft-Decision-1.1 takes an API key or an OAuth sign-in.
Can an agent call Granite Switch 4.1 and Microsoft-Decision-1.1 without installing anything?
No hosted endpoint is listed for Granite Switch 4.1. No hosted endpoint is listed for Microsoft-Decision-1.1.
Are Granite Switch 4.1 and Microsoft-Decision-1.1 open source?
Granite Switch 4.1 is open source (Apache 2.0 for the weights, the adapters and the repository). No open-source release is listed for Microsoft-Decision-1.1.
Other comparisons with Granite Switch 4.1 or Microsoft-Decision-1.1
- Celeris-1 Decision vs Granite Switch 4.1
- Celeris-1 Decision vs Microsoft-Decision-1.1
- Clef vs Granite Switch 4.1
- Clef vs Microsoft-Decision-1.1
- Laya vs Granite Switch 4.1
- Laya vs Microsoft-Decision-1.1
- Decider vs Granite Switch 4.1
- Decider vs Microsoft-Decision-1.1
- Decision 3.0 vs Granite Switch 4.1
- Decision 3.0 vs Microsoft-Decision-1.1
- Gemini Decision 1 vs Granite Switch 4.1
- Gemini Decision 1 vs Microsoft-Decision-1.1
- GLiClass vs Granite Switch 4.1
- GLiClass vs Microsoft-Decision-1.1
- Granite Switch 4.1 vs Kev
- Granite Switch 4.1 vs Liquid d1
- Granite Switch 4.1 vs Microsoft-Decision-1
- Granite Switch 4.1 vs Drex 1.5
- Granite Switch 4.1 vs OpenAI Decisions API
- Granite Switch 4.1 vs pplx-decider
- Granite Switch 4.1 vs pplx-decider-flash
- Granite Switch 4.1 vs RightNow System Zero
- Granite Switch 4.1 vs ScaleDown
- Granite Switch 4.1 vs SPEV
- Granite Switch 4.1 vs kettei
- Granite Switch 4.1 vs Strands Decider 2B
- Granite Switch 4.1 vs Jev
- Granite Switch 4.1 vs Vela 2.0
- Kev vs Microsoft-Decision-1.1
- Liquid d1 vs Microsoft-Decision-1.1
- Microsoft-Decision-1.1 vs Drex 1.5
- Microsoft-Decision-1.1 vs OpenAI Decisions API
- Microsoft-Decision-1.1 vs pplx-decider
- Microsoft-Decision-1.1 vs pplx-decider-flash
- Microsoft-Decision-1.1 vs RightNow System Zero
- Microsoft-Decision-1.1 vs ScaleDown
- Microsoft-Decision-1.1 vs SPEV
- Microsoft-Decision-1.1 vs kettei
- Microsoft-Decision-1.1 vs Strands Decider 2B
- Microsoft-Decision-1.1 vs Jev
- Microsoft-Decision-1.1 vs Vela 2.0
- Microsoft-Decision-1 vs Microsoft-Decision-1.1
Machine-readable
- This page as Markdown
/compare/granite-switch-vs-microsoft-decision-1-1.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-switch.json·/api/v1/tools/microsoft-decision-1-1.json - From a terminal
anchor compare granite-switch microsoft-decision-1-1(the CLI) - Over MCP
compare_tools {"a": "granite-switch", "b": "microsoft-decision-1-1"}at/mcp, no key