Head to head · Decision models · October 2026 research run

Microsoft-Decision-1.1 vs RightNow System Zero

RightNow System Zero scores 69.3 (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.

Best decision models for AI agents · All 263 decisions 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.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

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

RightNow System Zero B

Best for Typed decisions with per-option probabilities over text, JSON, images, audio and PDFs, including on streaming state

Ahead on

  • Schema & documentation, 83 against 43
  • Agent ergonomics, 86 against 50
  • Security & auth, 70 against 52
  • Payments & pricing, 60 against 30
  • Maintenance & community, 68 against 44
  • Transparency & trust, 70 against 34

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

Standard context is 38,000 tokens. The 64k, 128k and 1M bands are held, and video is a preview

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.

Schema & documentation RightNow System Zero +40

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.

RightNow System Zero 83

An OpenAPI 3.1.0 file in the official SDK repository covers decide, the model list and the stream, with typed questions and attachments and an apiKey scheme. The docs don't link it and cite an 'API spec 0.4.3', while the file's version is 1 (22 of 25). llms.txt, llms-full.txt, a Markdown copy of each docs page and a SKILL.md for coding agents (10). The docs say what each question type is for, and the terms say not to use an answer as the only basis for a decision with legal or similar effects on a person. The launch post contradicts the docs on audio formats and option counts (12 of 20). Questions are a typed union, choice takes 1 to 255 options and score 2 to 10 levels, names are pattern-checked and extra fields are refused. State is free-form JSON by design (13 of 15). TypeScript, Python and curl examples on every page, and an error catalogue of about 70 codes with status, type, meaning and whether to retry (15). A pinned model ID, system-zero-2.0.0, beside the system-zero alias, dated release notes (15 and 27 October) and an SDK changelog. The release notes date neither streaming nor image, PDF and video input, and the vendor's benchmark names a RightNow 3.0.0 the model list doesn't have (11 of 15).

Agent ergonomics RightNow System Zero +36

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.

RightNow System Zero 86

Read as an API an agent calls for a decision, as with the other decision models. Answers are a probability per option with no generated text and no output charge. Standard context is 38,000 state tokens, and an over-long state is refused with 413 state_too_large rather than truncated. Text caching is automatic, with an optional prompt_cache_key. The 64k, 128k and 1M bands are held (18 of 25). Up to 1,024 named questions a call of three types, and a WebSocket stream that decides on each change or on request, tagging each decision with the state_version it covers (17 of 20). Errors carry code, type, param, retryable and details, and an HTTP 200 can hold a refusal for one question while the others are answered. About half the catalogue is codes for held capabilities, with repeated text (18 of 20). An Idempotency-Key replays a stored answer for up to 24 hours, with separate codes for work still running, a changed body and an unavailable replay. Replay isn't guaranteed (19 of 20). Official TypeScript and Python SDKs at 0.4.2 retry with an idempotency key by default, and a call needs three fields. The docs say 0.4.2's request contract predates the served API spec for long context (14 of 15).

Transparency & trust RightNow System Zero +36

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.

RightNow System Zero 70

Closed weights under terms of use from RightNow AI, Inc. (Delaware), with the SDKs under Apache-2.0 (15). The privacy policy, terms and docs agree on no training, no content logging and 24-hour keyed replays, with retention stated for sign-in records (90 days) and product analytics (up to 7 years). Service receipts and crash records, which hold no content, aren't deleted automatically yet (24 of 30). Pinned model IDs have a retirement notice policy with no stated period, and material changes to the terms get 30 days' notice (6 of 20). Recipients are listed by category with processing countries, and the named provider list is available only on request. Model hosting can run in any region of the cloud host (10 of 20).

Payments & pricing RightNow System Zero +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.

RightNow System Zero 60

No x402, MPP or L402. HTTP 402 means the workspace's prepaid balance is too low (0). Per-unit prices are published without a login on price card G of 27 October 2026, USD 0.19 per million uncached text tokens, USD 0.00013 per answered question and a USD 0.000055 call fee, with file rates (20). New accounts get USD 5 of starting credit per verified email after a human check and eligibility checks, with no card asked for (20). Sign-in is through Google, GitHub or email in a browser with a human check, so an agent can't get a key on its own (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Maintenance & community RightNow System Zero +24

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.

RightNow System Zero 68

Read for a model. Launched on 15 October 2026, with price card G and SDK 0.4.2 on 27 October and the models and rate-limit pages updated on 31 October (30). Six SDK releases on npm and PyPI from 20 to 27 October and two dated release-note entries. Pinned model IDs are said to have a retirement notice policy, but no notice period is stated (12 of 20). Public release notes, Discord and a contact form, and the SDK's SECURITY.md aims to acknowledge reports within five business days. We didn't read Discord or the GitHub issues (7 of 15). Official TypeScript and Python SDKs under Apache-2.0 at 0.4.2. The docs say 0.4.2's request contract predates the served API spec for long context (13 of 15). npm versions from 0.1.0 were published by GitHub Actions and the Python package bounds its dependencies. GitHub's API wasn't reachable from this session, so CI results went unread (6 of 10).

Security & auth RightNow System Zero +18

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.

RightNow System Zero 70

Read for a model API. Workspace API keys are named, shown once and revocable by their creator or an admin, with a leaked-key procedure. They have no scopes, and the stream refuses credentials in the URL (20 of 30). The privacy policy and terms say content and answers are never used to train any model and request content isn't logged. Answers are kept for up to 24 hours only when a request sends an Idempotency-Key (18 of 20). Requests whose content reads as instructions to the model are refused with 422 injection_suspected, the terms warn that hidden instructions in documents or images can change answers, and the Danger zone page says the guard isn't qualified for every input size (12 of 15). The console lists recent requests by ID, status and error code without content, and usage separates answered, replayed and failed calls. We found no exportable audit log (12 of 15). security.txt is valid until 20 September 2027, and the SDK repository's SECURITY.md takes private reports. trust.rightnowai.co shows SOC 2 Type 2 as compliant with no public documents, and the blog and contact footers label it 'RunInfra: SOC 2 Type 2'. No report was reviewed and no bug bounty was found (8 of 20).

Score by category

CategoryWeightMicrosoft-Decision-1.1RightNow System ZeroEdge
Reliability16%5050even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%4383RightNow System Zero +40
Agent ergonomics13%5086RightNow System Zero +36
Security & auth14%5270RightNow System Zero +18
Payments & pricing10%3060RightNow System Zero +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4468RightNow System Zero +24
Transparency & trust7%3470RightNow System Zero +36
Negative events≤1500
TotalE 44.8/100B 69.3/100

Facts side by side

FactMicrosoft-Decision-1.1RightNow System Zero
KindModel APIModel API
VendorMicrosoftRightNow AI, Inc.
Hosted endpointno (local only)https://api.rightnowai.co/v1/system-zero/decide
TransportsHTTPHTTP, websocket
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 model under RightNow AI terms of use; the SDKs are Apache-2.0
Read-only variant documentednono
llms.txtnoyes
Last release2026-11-172026-10-27
Terms last updatedno document linkedno date given
Privacy policy last updatedno date givenno date given
Customer content may train modelsnot read yetyes
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text

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.

RightNow System Zero

A well-documented decision API with an OpenAPI file, idempotent retries, a detailed error catalogue, streaming over WebSocket and published per-unit prices with USD 5 of starting credit. Standard context is 38,000 tokens; the 64k, 128k and 1M bands are held and video is a preview. The latency and benchmark figures are RightNow's own, and several of its pages disagree.

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

RightNow System Zero

  1. Send audio only as inline 16,000 Hz WAV. The FLAC, MP3, OGG and MP4 audio named on the blog are refused with media_unsupported.
  2. Keep state under 38,000 tokens. Long-context requests return 404 long_context_not_available, which never succeeds on retry.
  3. Reuse the same Idempotency-Key and body on retries, and stop when error.retryable or x-should-retry is false.
  4. Check every entry in answers even on HTTP 200, since one question can be refused while the others are answered.
  5. Treat probabilities as uncalibrated while calibrated is false, and pin system-zero-2.0.0 when answers must not move with the alias.

Questions

Which is better for AI agents, Microsoft-Decision-1.1 or RightNow System Zero?

RightNow System Zero scores 69.3 (B) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in 6 of 7 scored categories.

Do Microsoft-Decision-1.1 and RightNow System Zero need an API key?

Microsoft-Decision-1.1 takes an API key or an OAuth sign-in. RightNow System Zero needs an API key.

Can an agent call Microsoft-Decision-1.1 and RightNow System Zero without installing anything?

No hosted endpoint is listed for Microsoft-Decision-1.1. RightNow System Zero has a hosted endpoint at https://api.rightnowai.co/v1/system-zero/decide.

Other comparisons with Microsoft-Decision-1.1 or RightNow System Zero

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.