Head to head · Decision models · October 2026 research run

Microsoft-Decision-1.1 vs ScaleDown

Microsoft-Decision-1.1 scores 44.8 (E) on agent readiness against ScaleDown's 39.6 (E), and leads in 4 of 7 scored categories. ScaleDown leads on schema & documentation, agent ergonomics and maintenance & community. Both do decision models.

Best decision models for AI agents · All 263 decisions comparisons

Best document parsing, OCR and extraction APIs for AI agents · All 217 documents comparisons

Which one, for what

Microsoft-Decision-1.1 E

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 20
  • Security & auth, 52 against 27
  • Payments & pricing, 30 against 0
  • Transparency & trust, 34 against 28

Watch for

No machine-readable contract or reference page with the request schema was found

ScaleDown E

Best for Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.

Ahead on

  • Schema & documentation, 69 against 43
  • Agent ergonomics, 76 against 50
  • Maintenance & community, 56 against 44

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page, no published rate limits and no SLA in the docs

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.

Reliability Microsoft-Decision-1.1 +30

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.

ScaleDown 20

Read as a hosted model API. No status page found. status.scaledown.ai and status.scaledown.xyz didn't resolve per the 14 October check, and the docs link none (0). No readable incident history (5). The docs, re-read on 4 November, publish no rate limit with numbers (0). Only the Compress reference lists 429, with 'Back off and retry'. Classify and Decisions list 422, 402, 502 and 504 without retry guidance. A call has no side effects, so a retry is safe, and the earlier partial is kept (5 of 15). No SLA found in the docs (0). The models carry no beta or preview label in the docs (10). 0 + 5 + 0 + 5 + 0 + 10 = 20.

Payments & pricing Microsoft-Decision-1.1 +30

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.

ScaleDown 0

No x402, MPP or L402 in the docs or the OpenAPI document (0). The only price on the docs host is on the OpenAI-compatibility page ('the base rate of $0.05 per 1M input tokens'). The docs repository removed that page from the navigation on 12 October 2026, before the price was added on 13 October, and neither llms.txt nor any docs page links it. An unlinked file isn't read as published, as for unlinked OpenAPI files (synthflow, jambonz), and the docs introduction says to contact sales for a key (0). The 50 million free tokens and the no-card statement came from scaledown.ai's homepage, which robots.txt now closes to us, so no free tier is established (0). A person contacts sales or signs up in a browser, and no key API was found (0). 0 + 0 + 0 + 0 = 0. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 0 is 0.

Schema & documentation ScaleDown +26

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.

ScaleDown 69

An OpenAPI 3.1 document (ScaleDown API 1.0.0), linked from the docs' llms.txt under OpenAPI Specs, covers /compress/raw/, /classify and /v1/scaledown. Its /classify schema has only text and labels, without chunks, document, multi_label or the label caps, and Extract and Summarize on /v1/chat/completions aren't in it (15 of 25). llms.txt indexes 28 pages, each with a Markdown twin (10). Overviews say when to use each model and how to write rubrics, and a table says when to choose /classify over Decisions. No known-limitations page (14 of 20). Typed question kinds behind a type field, with 20 labels, 16 in multi-label mode, 50 chunks and 2 to 10 score levels stated in prose, and Extract driven by a JSON schema with $ref refused (11 of 15). curl, Python and TypeScript examples with sample responses, and an error table per endpoint (422, 402, 502, 504 and others), though 429 appears only for Compress and no error body is shown (12 of 15). Pinned model IDs (classify-1, extract-1, summarize-1). No public changelog, but the docs source on GitHub has dated commits, the newest on 14 October 2026 (7 of 15). 15 + 10 + 14 + 11 + 12 + 7 = 69.

Agent ergonomics ScaleDown +26

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.

ScaleDown 76

Read as an API an agent calls for a decision, the reading used for Jev. Decisions answers are a few numbers per question, and the reference's sample answers a three-way choice from 62 input tokens with 1 output token. Extract adds 500 characters of context on each side of every value by default, which context_chars can turn off, and the OpenAI-compatibility page gives each model a 1,000,000-token context window (20 of 25). threshold, top_n, context_chars, multi-label mode, the reasoning switch and up to 50 chunks a request sized against one billed label set (17 of 20). Error tables per endpoint, with 402 for insufficient credit. Error bodies aren't documented (13 of 20). Calls have no side effects. No retry guidance outside Compress, and the langchain-scaledown client doesn't retry (14 of 20). No SDK of ScaleDown's own. OpenAI SDKs work against /v1/chat/completions with only the base URL changed, a Jev client works against /v1/scaledown, and langchain-scaledown covers Python callers. model is optional on Decisions (12 of 15). 20 + 17 + 13 + 14 + 12 = 76.

Security & auth Microsoft-Decision-1.1 +25

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.

ScaleDown 27

Read for a model API, on the lines used for Jev. A plain API key in x-api-key, or as a bearer token on chat completions. The docs document no scopes, expiry or rotation, and revocation wasn't checked, since the dashboard is disallowed in robots.txt and we made no account (18 of 30). scaledown.ai's robots.txt, read on 4 November, disallows Claude-Web and anthropic-ai on every path, so the 14 October readings of the terms, DPA, privacy notice, site FAQ and site llms.txt are struck. The docs say nothing on training or retention (0 of 20). Classify and Extract judge text that often comes from users. The docs carry no warning or mitigation for injected instructions (3 of 15). Each Decisions response reports tokens and cost, and the earlier partial is kept (6 of 15). The security.txt, certification and breach-notice readings came from scaledown.ai and are struck. docs.scaledown.ai had no security.txt per the 14 October check, and no disclosure route was found in the docs (0 of 20). 18 + 0 + 3 + 6 + 0 = 27.

Maintenance & community ScaleDown +12

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.

ScaleDown 56

Read for a closed model, on the decision-model split used for Jev (notice 0 to 12, churn 0 to 8). The newest dated change is the docs commit of 14 October 2026 that set Extract's scalar entity cap to 30 per type, 21 days before this check (30). Pinned -1 model IDs are documented, with no deprecation policy or notice period in the docs. The terms' notice promise is struck with the rest of scaledown.ai (5 of 12). One version of each model so far, and the docs dropped the native /extract and /summarization/abstractive endpoints from the reference on 13 October 2026 (2 of 8). No public changelog. Dated commits in the docs repository and a Discord bot repository, and issue replies weren't sampled. The earlier partial is kept (6 of 15). No SDK of ScaleDown's own. langchain-scaledown 0.2.0 (MIT, 12 October 2026) from the scaledown-team organisation is still the newest version in its repository, and OpenAI SDK compatibility covers other languages (8 of 15). langchain-scaledown ships GitHub workflows with unit and integration tests (5 of 10). 30 + 5 + 2 + 6 + 8 + 5 = 56.

Score by category

CategoryWeightMicrosoft-Decision-1.1ScaleDownEdge
Reliability16%5020Microsoft-Decision-1.1 +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%4369ScaleDown +26
Agent ergonomics13%5076ScaleDown +26
Security & auth14%5227Microsoft-Decision-1.1 +25
Payments & pricing10%300Microsoft-Decision-1.1 +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4456ScaleDown +12
Transparency & trust7%3428Microsoft-Decision-1.1 +6
Negative events≤1500
TotalE 44.8/100E 39.6/100

Facts side by side

FactMicrosoft-Decision-1.1ScaleDown
KindModel APIModel API
VendorMicrosoftCarbon ScaleDown, Inc.
Hosted endpointno (local only)https://api.scaledown.xyz
TransportsHTTPHTTP
AuthOAuth or keyAPI key
PricingPay per usePay per use
Price for decision modelsfreenot published
x402nono
LicenceNot 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.Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT
Read-only variant documentednono
llms.txtnoyes
Last release2026-11-172026-10-14
Terms last updatedno document linkedcouldn't be read
Privacy policy last updatedno date givencouldn't be read
Customer content may train modelsnot read yetcouldn't be read
Terms restrict automated accessnot read yetcouldn't be read
Terms restrict benchmarkingnot read yetcouldn't be read
Terms or service can change without noticenot read yetcouldn't be read
Arbitration or class-action waivernot read yetcouldn't be read
Popularitynone0 stars

How the scores have moved

Verdicts

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.

ScaleDown

Classify answers Jev-shaped choice, noul and score questions with probabilities, and Extract returns values with confidences and character offsets. There is no status page, no published rate limit or changelog, the only price sits on a docs page no longer linked, and the terms, privacy notice and DPA couldn't be read.

Before you call either

Microsoft-Decision-1.1

  1. On Foundry, deploy Microsoft-Decision-1.1 in a Foundry resource and call it with a Microsoft Entra bearer token
  2. On OpenRouter, call microsoft/microsoft-decision-1.1 through the Decisions API, not chat completions
  3. Send fixed answer options and read the probabilities; it writes no explanation
  4. Set a confidence threshold and defer to a larger model below it

ScaleDown

  1. Send several questions about one item in one /v1/scaledown call. Each becomes its own Classify call and the usage is summed
  2. Pin classify-1, extract-1 or summarize-1 once you've tuned thresholds on your own labelled cases
  3. Set context_chars to 0 and use top_n on Extract unless you need the 500 characters of context each side
  4. Set reasoning: false on /classify when you only need the label. The reasoning call bills its input at 2x
  5. Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects

Questions

Which is better for AI agents, Microsoft-Decision-1.1 or ScaleDown?

Microsoft-Decision-1.1 scores 44.8 (E) on agent readiness against ScaleDown's 39.6 (E), and leads in 4 of 7 scored categories. ScaleDown leads on schema & documentation, agent ergonomics and maintenance & community.

Do Microsoft-Decision-1.1 and ScaleDown need an API key?

Microsoft-Decision-1.1 takes an API key or an OAuth sign-in. ScaleDown needs an API key.

Can an agent call Microsoft-Decision-1.1 and ScaleDown without installing anything?

No hosted endpoint is listed for Microsoft-Decision-1.1. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.

Other comparisons with Microsoft-Decision-1.1 or ScaleDown

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.