Head to head · Decision models · October 2026 research run
GLiClass vs Microsoft-Decision-1.1
GLiClass scores 55.5 (C) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in 5 of 7 scored categories. Microsoft-Decision-1.1 leads on reliability and security & auth. 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
GLiClass C
Best 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
- Schema & documentation, 49 against 43
- Agent ergonomics, 60 against 50
- Payments & pricing, 90 against 30
- Maintenance & community, 64 against 44
- Transparency & trust, 65 against 34
Also in its favour
- No key needed to call it
- Open source
Watch for
No calibration figures on the v3.0 cards, which report F1 only; the v4 2B and 27B repositories hold calibration report files we couldn't read
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.
Ahead on
- Reliability, 50 against 43
- Security & auth, 52 against 38
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 GLiClass +60
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. No payment protocol (0). Knowledgator's hosted platform and its plans were unreachable from our network on 8 October 2026 and are not graded here. 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 GLiClass +31
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). Self-hosted, so inputs stay on the owner's hardware, though no project page says so. The company's terms of use and privacy policy of 21 September 2023 (terms re-read on 4 November) covers its website and services, not the library (18 of 30). No deprecation policy. Older model generations stay on the Hub without a notice of which are current (2 of 20). We found no telemetry code in the package and no statement either way. Weights download from the Hugging Face Hub (10 of 20).
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 GLiClass +20
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 listed as models. The repository tagged v0.1.22 on 31 October 2026 (FP8 serving and a new process API), after v0.1.21 on 16 October (calibration and multimodal training), and the v4 checkpoints were last changed on 24 October (30). No deprecation policy or notice period. Each generation lives in its own Hub repository (v1.0, v2.0, v3.0, Instruct, Multilang, v4) and none has been removed or replaced in place; the v3.0 repositories last changed on 12 August 2025 (5 of 12, level with Decider's and Kev's 5). Four v4 models (edge, 2B, 9B and 27B) arrived from 13 to 24 October 2026 as new repositories, with the earlier ones untouched (5 of 8). 34 commits from v0.1.20 to v0.1.22 under six author names, six of them merges of pull requests (#48 to #53). Issue reply times weren't checked, and the open-issue count is per the 8 October check, not re-read on 4 November. A Discord server is linked (10 of 25). The Python package is current and runs on transformers 5. No other SDK (10 of 15). CI and a uv.lock exist, and PyPI publishing is automated on tags, but the Tests workflow was failing on main, per the 8 October check, not re-read on 4 November (4 of 10). 30+5+5+10+10+4 = 64.
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.
Security & auth Microsoft-Decision-1.1 +14
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 models listed as models. No account. The Ray Serve deployment checks no credential and has no option for one in 0.1.22, and the command line still binds to 0.0.0.0 by default (6 of 30). Self-hosted, so nothing reaches Knowledgator and no caller data can train a model, and the package has no telemetry code, but no project page says so, where Kev's cards and Vela 2.0's runtime reference state it for their 18 (15 of 20, level with Strands Decider and Granite Switch). The output is labels and scores, so no untrusted text comes back. The docs warn that the safety checkpoints can miss new or obfuscated attacks. Nothing documents how hostile text moves a score (10 of 15). The server logs start-up and label truncation and keeps request statistics, and the docs describe no per-call record (3 of 15). No SECURITY.md, no security.txt on knowledgator.com (404 per the 8 October check, not re-read on 4 November) and no bounty. Weights are safetensors, though the v4 2B repository also holds a pickled training_args.bin beside them. PyPI releases use trusted publishing. gliclass/config.py still loads an unknown encoder's configuration with trust_remote_code=True (4 of 20). 6+15+10+3+4 = 38.
Microsoft-Decision-1.1 52
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 (credential, training, retention, operator visibility, programme), as the Google Lyria and Soundverse listings read it; the 10 October note read the tool lines (20 + 10 + 5 + 5 + 12 = 52). The Foundry sample uses a Microsoft Entra bearer token for a fixed resource scope; role assignments and token lifetimes weren't read, and OpenRouter uses an API key (20 of 30). Microsoft's data page for Foundry Models sold by Azure (updated 5 June 2026, re-read 10 November) says prompts and completions aren't used to train foundation models without permission and the models are stateless, but it doesn't name this model (10 of 20). The same page says abuse monitoring can store prompts for human review, with no period stated and a modified-monitoring application for managed customers; whether it covers this model isn't stated (5 of 15). OpenRouter's Activity page shows token volume and requests, per the 10 October check; Foundry diagnostic logs weren't read (5 of 15). Microsoft's security.txt names its coordinated vulnerability disclosure policy, a bounty and a reporting form, and was renewed to expire on 27 October 2027; no certification naming this model was read (12 of 20). 20 + 10 + 5 + 5 + 12 = 52.
Agent ergonomics GLiClass +10
GLiClass 60
Read as an API an agent calls for a decision, as with the other decision models. The answer is a short list of labels and scores and no text is generated. Text and labels share one sequence, 1,024 tokens by default, with 25 labels by default (17 of 25). The caller sets a threshold, picks single-label or multi-label, and can ask for hierarchical output. The pipeline takes a batch of texts and a chunking pipeline handles long documents. The HTTP endpoint takes one text a request (15 of 20). Errors are {"error": "..."} with 400 or 404 and are undocumented. Truncation of long input is silent (7 of 20). Classification calls are stateless and safe to retry. The server has a request timeout and a queue capacity in its configuration. We found no Retry-After or retry guidance in the serve package or the docs (12 of 20). Loading takes a model, a tokeniser and a pipeline call, and a Python client ships with the server. Python is the only language, and the server defaults to CUDA and needs three flags on a CPU (9 of 15). The 0.1.22 /v1/process errors are actionable in the code (codes such as INPUT_TOO_LONG with a JSON path) but undocumented, so the error line holds.
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.
Reliability Microsoft-Decision-1.1 +7
GLiClass 43
Scored on the local-package checklist, since GLiClass is a library and weights the owner runs. pip install gliclass with Python 3.10 or newer stated. The repository tags v0.1.21 (16 October 2026) and v0.1.22 (31 October 2026), and its release workflow publishes every v* tag to PyPI; pypi.org didn't resolve from our shell on 4 November, so the PyPI pages weren't re-read. The README's source install still calls a requirements.txt the repository doesn't have, and the base v3.0 card still names transformers>=4.48.0 while the package requires 5.0 (17 of 20). A public Tests workflow runs pytest on Python 3.10 to 3.12 and a ruff job. Its last three runs on main, all on 24 September 2026, had failed, per the 8 October check, not re-read on 4 November (GitHub's pages refuse our reader), and later commits fix ruff errors (10 of 25). 15 issues and 1 pull request were open on 8 October, the oldest from 22 September 2024, among them #44 (models not loading with transformers v5), #35 (demo error) and #12 (every label scored 0.99), per the 8 October check, not re-read on 4 November (12 of 25). No changelog file, and 0.1.18 moved the dependency floor to transformers 5 in a patch version (4 of 15). Version 0.1.22, with no statement of stability (0). 17+10+12+4+0 = 43.
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 Azure status history page lists Foundry Models among its products, with post-incident reviews kept for five years, earning 20 of 20. It's a shared component, not a page for this model. In the 90 days from 12 August, re-read on 10 November 2026, the one review naming Foundry Models is 29 September 2026 in Sweden Central, 10:03 to 15:58 UTC, with intermittent request failures and latency. That is one region and a share of requests, so partial and minor, as the Azure OpenAI fine-tuning, Speech, Translator and Document Intelligence listings read it. The 30 September gateway review doesn't name Foundry Models, and nothing is posted after it (20 of 30, was 10). No rate limit, 429 guidance or SLA for this model was found (0, 0 and 0). The model is still in public preview per the Tech Community post, so there is no general availability award (0). Total 40. For 1.1: Foundry's model list marks Microsoft-Decision-1.1 generally available, and Microsoft calls it ready for enterprise production, so the GA line earns 10 where Decision-1 had 0 in preview. 40 + 10 = 50.
Score by category
| Category | Weight | GLiClass | Microsoft-Decision-1.1 | Edge |
|---|---|---|---|---|
| Reliability | 16% | 43 | 50 | Microsoft-Decision-1.1 +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 49 | 43 | GLiClass +6 |
| Agent ergonomics | 13% | 60 | 50 | GLiClass +10 |
| Security & auth | 14% | 38 | 52 | Microsoft-Decision-1.1 +14 |
| Payments & pricing | 10% | 90 | 30 | GLiClass +60 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 64 | 44 | GLiClass +20 |
| Transparency & trust | 7% | 65 | 34 | GLiClass +31 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 55.5/100 | E 44.8/100 |
Facts side by side
| Fact | GLiClass | Microsoft-Decision-1.1 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Knowledgator | 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 (library and the model weights we checked) | 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 | 2026-10-31 | 2026-11-17 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no date given |
| Popularity | 555 stars | none |
How the scores have moved
Microsoft-Decision-1.1
No score change since it was listed.
Verdicts
GLiClass
An Apache-2.0 classifier family that scores a whole label set in one pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes, and new v4 models from 0.4B to 27B parameters. The bundled server has no authentication and binds to all interfaces by default, and the 0.1.22 process API is undocumented.
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
GLiClass
- Pass
--host 127.0.0.1topython -m gliclass.serve, or put the port behind your own gateway. The server checks no credential - On a machine without a GPU add
--device cpu --dtype float32 --num-gpus-per-replica 0. The default configuration expects CUDA - Send one text a request to
POST /gliclass. An array intextsis cut to its first item without an error - Set
multi_labelto false for one label from a set. The default scores each label independently, so scores do not sum to 1 - Keep text plus labels under the pipeline's 1,024-token
max_length, or useZeroShotClassificationWithChunkingPipeline. Longer input is truncated silently - The
/v1/processinterface in 0.1.22 isn't documented. Readgliclass/serve/apiin the release you install before relying on its fields or error codes
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, GLiClass or Microsoft-Decision-1.1?
GLiClass scores 55.5 (C) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in 5 of 7 scored categories. Microsoft-Decision-1.1 leads on reliability and security & auth.
Which is cheaper for decision models, GLiClass or Microsoft-Decision-1.1?
GLiClass, at free against free for Microsoft-Decision-1.1. These are the vendors' published prices for the job.
Do GLiClass and Microsoft-Decision-1.1 need an API key?
GLiClass needs no key. Microsoft-Decision-1.1 takes an API key or an OAuth sign-in.
Can an agent call GLiClass and Microsoft-Decision-1.1 without installing anything?
No hosted endpoint is listed for GLiClass. No hosted endpoint is listed for Microsoft-Decision-1.1.
Are GLiClass and Microsoft-Decision-1.1 open source?
GLiClass is open source (Apache-2.0 (library and the model weights we checked)). No open-source release is listed for Microsoft-Decision-1.1.
Other comparisons with GLiClass or Microsoft-Decision-1.1
- Celeris-1 Decision vs GLiClass
- Celeris-1 Decision vs Microsoft-Decision-1.1
- Clef vs GLiClass
- Clef vs Microsoft-Decision-1.1
- Laya vs GLiClass
- Laya vs Microsoft-Decision-1.1
- Decider vs GLiClass
- Decider vs Microsoft-Decision-1.1
- Decision 3.0 vs GLiClass
- Decision 3.0 vs Microsoft-Decision-1.1
- Gemini Decision 1 vs GLiClass
- Gemini Decision 1 vs Microsoft-Decision-1.1
- GLiClass vs Granite Switch 4.1
- GLiClass vs Kev
- GLiClass vs Liquid d1
- GLiClass vs Microsoft-Decision-1
- GLiClass vs Drex 1.5
- GLiClass vs OpenAI Decisions API
- GLiClass vs pplx-decider
- GLiClass vs pplx-decider-flash
- GLiClass vs RightNow System Zero
- GLiClass vs ScaleDown
- GLiClass vs SPEV
- GLiClass vs kettei
- GLiClass vs Strands Decider 2B
- GLiClass vs Jev
- GLiClass vs Vela 2.0
- Granite Switch 4.1 vs Microsoft-Decision-1.1
- 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/gliclass-vs-microsoft-decision-1-1.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/gliclass.json·/api/v1/tools/microsoft-decision-1-1.json - From a terminal
anchor compare gliclass microsoft-decision-1-1(the CLI) - Over MCP
compare_tools {"a": "gliclass", "b": "microsoft-decision-1-1"}at/mcp, no key