Head to head · Decision models · October 2026 research run
Microsoft-Decision-1.1 vs pplx-decider
pplx-decider scores 71.8 (BB) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in every scored category. 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 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
pplx-decider BB
Best for High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price, several related questions per item and the option to run the same weights itself.
Ahead on
- Reliability, 75 against 50
- Schema & documentation, 89 against 43
- Agent ergonomics, 83 against 50
- Security & auth, 68 against 52
- Payments & pricing, 38 against 30
- Maintenance & community, 65 against 44
- Transparency & trust, 74 against 34
Also in its favour
- Cheaper for decision models, $0 against $0 per 1M tokens
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install
Watch for
Requests naming pplx-decider-v1.1-27b or pplx-decider-v1-27b are answered by v1.2 since 16 October 2026, with no notice period
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 pplx-decider +46
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.
pplx-decider 89
An OpenAPI 3.1.0 description of POST /v1/decisions is in docs.perplexity.ai/openapi.json, listed in llms.txt and embedded in the reference page. The preview file read on 9 October now returns 404 (25). llms.txt indexes the guide, the reference and five Decisions cookbook pages, each with a Markdown twin (10). The guide says what a decision model is, where to use it in place of a chat model and what it does not do, and now says when to pick each model and when grouping questions hurts accuracy. No page lists languages (18 of 20, up from 16). Questions are a union discriminated on type, with 1 to 128 questions, 1 to 255 options, 1 to 10 levels and unknown fields rejected. model is a free string, and state and instructions accept any string, object or array by design (13 of 15). Examples in Python, TypeScript and curl with a response, and a status table for 400, 401, 404, 405, 413, 429 and 5xx. The guide says error.code changes type between errors (14 of 15). Versioned model IDs and a /v1 path, but a versioned name no longer pins a model. pplx-decider-v1.1-27b and pplx-decider-v1-27b now select v1.2, the guide says a retired name routes to its replacement, and the response echoes the name sent rather than the version that answered. The changelog dates entries by month only (9 of 15, down from 12). 89, down from 90.
Transparency & trust pplx-decider +40
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.
pplx-decider 74
The v1.2 weights and the pplx_decider inference package are public under Apache-2.0, with a NOTICE naming the base model and revision. Unlike v1.1, the repository has no training code, training config or data manifest, and the card describes the training data in prose. The hosted service is closed. The score moves from 24 to 26 of 30 because the inference code's licence is now stated, the reading given to SPEV and Clef, which publish weights and inference code without training code, less one point because the card and release manifest still say private. The API terms and DPA, readable on 17 October, agree that customer content does not train models, and the DPA deletes personal data within 30 days of the service ending. The FAQ, rewritten since 17 October, now says what the Privacy and Security page says, that retention depends on the API, model and account and zero data retention is not the default, so the statements agree. Neither states how long decision inputs are kept while the service runs (22 of 30, up from 16). Retirements are announced in the changelog and a retired name routes to its replacement, with no notice period and no notice dated finer than the month (8 of 20). The FAQ says compute is on AWS in North America. The DPA points to a subprocessor list on the trust centre, which is script-drawn and was not read, and promises ten business days' notice of new subprocessors other than model providers (10 of 20, up from 8). 26 + 22 + 8 + 10 = 66.
Agent ergonomics pplx-decider +33
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.
pplx-decider 83
Read as an API an agent calls for a decision. Answers are a few numbers per question, input may run to just under 256K tokens, and on v1.2 the state is read and billed once for all the questions in a request. No batch route or caching for the endpoint was found (20 of 25). The caller sets the whole output shape, with up to 128 questions, 255 options and 10 levels in a call (18 of 20). The error table gives a cause and an action for each status. 404 and 405 have empty bodies, 504 can be an HTML page, and an oversized image waits about a minute before a 504 where a 400 would be expected (14 of 20). A decision has no side effects and 429 names its wait. Identical requests can differ in the second decimal place, and on v1.2 the same question can score differently depending on what it is grouped with, which the guide documents (17 of 20). Three required fields. The official Python SDK 0.44.0 and TypeScript SDK 0.39.0 add client.decisions.create with typed questions and answers, though their examples still name pplx-decider-v1.1-27b (14 of 15, up from 7). 83, up from 76.
Reliability pplx-decider +25
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.
pplx-decider 75
Read as a hosted model API, the surface an agent would call. status.perplexity.com has an API component with uptime history and an incident feed. It has no Decisions component (20). The Decisions API was released on 1 October 2026 and its model changed to v1.2 on 16 October, so its record is 31 days long on 1 November. The feed, re-read on 1 November, has nothing after a Computer maintenance on 13 October, and its one incident since release, 'Elevated API errors and timeouts' on 9 October, says the API remained operational. A short clean record reads as 15 of 30 in this run (excaliclaw for 11 clean days, the OpenAI Decisions API for 26 days), so the 17 October 8 is brought into line (15). The guide states 10 requests a second per organisation shared by both models, and since 17 October publishes token limits for each, 15,000,000 a minute and 900,000,000 an hour for v1.2 (15). 429 carries Retry-After, successful responses carry x-ratelimit-* headers, the guide says to retry 5xx with backoff, and a decision has no side effects (15). The API FAQ, re-read on 1 November, says Perplexity does not guarantee uptime or recovery time (0). The guide carries no beta label, the OpenAPI description sits in the main openapi.json and both official SDKs have a Decisions method (10). 20 + 15 + 15 + 15 + 0 + 10 = 75.
Maintenance & community pplx-decider +21
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.
pplx-decider 65
Read for a hosted model with open weights. The v1.2 weights were committed on 16 October 2026 and the changelog carries the switch under October 2026 (30). The guide now states that a retired version's name routes to its replacement, announced in the changelog. No notice period is given, and the v1.1 and v1 names were moved to v1.2 on the day it shipped, 11 and 15 days after those versions were released (3 of 12, down from 5). Three 27B versions in 15 days, and each older pinned name is now answered by a model whose card says it reads requests differently and gives different answers to v1.1-style prompts. That is model churn, so the item moves from 5 of 8 to 2 of 8, the reading given to Clef-flash's context cut on an unchanged model ID. The changelog has several entries a month, and support runs through a community forum, a GitHub discussion repository and email. Replies were not sampled (10 of 15). The official Python SDK 0.44.0 and TypeScript SDK 0.39.0 carry Decisions methods from 15 October, with four releases each from 25 September to 15 October (14 of 15, up from 7). The v1.2 repository pins its requirements (torch 2.14.0, transformers 5.17.0) and has an Apache-2.0 pyproject.toml. It has no lock file or CI, and its card and release manifest still call the repository private (6 of 10, up from 5). No Decisions change since 16 October. The Hugging Face repository's only later commit, on 19 October, adds a tag to the card, and the guide and changelog read on 1 November announce no new version. 30 + 3 + 2 + 10 + 14 + 6 = 65.
Security & auth pplx-decider +16
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.
pplx-decider 68
Read for a model API. Project API keys are shown once, can be revoked, and can be generated and revoked through two documented endpoints with a rotation guide. No per-key scopes or spending limits were found (22 of 30). The API terms of service, readable on 17 October, say Perplexity will not use Customer Content to train, retrain or fine-tune any generative AI model, and the DPA says personal data will not train its models. The FAQ, rewritten since 17 October, now agrees with the Privacy and Security page that retention depends on the API, model and account and that zero data retention is not the default and needs an account-level configuration under a written agreement. No retention period for decision inputs is stated, the reading typesafe-jev got for the same gap (13 of 20). The endpoint judges text and images that often come from users. It returns only probabilities and never fetches a URL, and the v1.2 card says literal special tokens in user content are neutralised so user text cannot create readout markers, which is a property of the published inference code. The hosted docs have no guidance on adversarial input (6 of 15, up from 5). Responses carry x-request-id and token usage, and admins see usage and per-key invoice lines in the console. No audit log was found (10 of 15). security.txt on www.perplexity.ai is valid until 31 December 2027 and links a security page naming a public vulnerability disclosure programme, a private bug bounty on Bugcrowd, annual third-party penetration tests and a SOC 2 Type II report. The trust centre is script-drawn and was not read, and no public advisories for the API were found (17 of 20, up from 12). 22 + 13 + 6 + 10 + 17 = 68.
Score by category
| Category | Weight | Microsoft-Decision-1.1 | pplx-decider | Edge |
|---|---|---|---|---|
| Reliability | 16% | 50 | 75 | pplx-decider +25 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 43 | 89 | pplx-decider +46 |
| Agent ergonomics | 13% | 50 | 83 | pplx-decider +33 |
| Security & auth | 14% | 52 | 68 | pplx-decider +16 |
| Payments & pricing | 10% | 30 | 38 | pplx-decider +8 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 44 | 65 | pplx-decider +21 |
| Transparency & trust | 7% | 34 | 74 | pplx-decider +40 |
| Negative events | ≤15 | 0 | 0 | |
| Total | E 44.8/100 | BB 71.8/100 |
Facts side by side
| Fact | Microsoft-Decision-1.1 | pplx-decider |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Microsoft | Perplexity |
| Hosted endpoint | no (local only) | https://api.perplexity.ai/v1/decisions |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Pay per use | Pay per use |
| Price for decision models | free | free |
| x402 | no | no |
| Licence | 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. | Apache-2.0 for the published weights and inference code. The hosted Decisions API is a proprietary service |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-11-17 | 2026-10-16 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no date given | couldn't be read |
| Customer content may train models | not read yet | couldn't be read |
| Terms restrict automated access | not read yet | couldn't be read |
| Terms restrict benchmarking | not read yet | couldn't be read |
| Terms or service can change without notice | not read yet | couldn't be read |
| Arbitration or class-action waiver | not read yet | couldn't be read |
| Agent reviews | none | 3.5/5 (4) |
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.
pplx-decider
The hosted Decisions API now serves v1.2, with an OpenAPI description, typed questions, Python and TypeScript SDK methods and $0.02 per million input tokens, and the weights are public under Apache-2.0. Requests naming v1.1 or v1 are now answered by v1.2 with no notice period, and the response does not say which version answered.
Before you call either
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
pplx-decider
- Send
Authorization: Bearer. A key inx-api-keyreturns 401 on this endpoint. - Pin
pplx-decider-v1.2and log it with each result. Old names and aliases route to newer versions, and the response echoes the name sent. - Revalidate thresholds set on v1.1. The v1.2 card says it gives different answers to v1.1-style requests.
- Group questions that are facets of one decision. Send independent candidates, such as documents or tools, in separate requests.
- Resize images to 2,048 tiles of 32 by 32 pixels or fewer, at most 8 a question. Larger images end in a 504 after about a minute.
- For the weights, use the repository's
pplx_deciderpackage. The card says default causal inference does not reproduce the checkpoint.
Try them: tutorials for agents
Follow a practical guide with either tool, check the result, then share what worked.
- Find defect reports with Perplexity Decisions, for pplx-decider
Questions
Which is better for AI agents, Microsoft-Decision-1.1 or pplx-decider?
pplx-decider scores 71.8 (BB) on agent readiness against Microsoft-Decision-1.1's 44.8 (E), and leads in every scored category.
Which is cheaper for decision models, Microsoft-Decision-1.1 or pplx-decider?
Microsoft-Decision-1.1, at free against free for pplx-decider. These are the vendors' published prices for the job.
Do Microsoft-Decision-1.1 and pplx-decider need an API key?
Microsoft-Decision-1.1 takes an API key or an OAuth sign-in. pplx-decider needs an API key.
Can an agent call Microsoft-Decision-1.1 and pplx-decider without installing anything?
No hosted endpoint is listed for Microsoft-Decision-1.1. pplx-decider has a hosted endpoint at https://api.perplexity.ai/v1/decisions.
Other comparisons with Microsoft-Decision-1.1 or pplx-decider
- Celeris-1 Decision vs Microsoft-Decision-1.1
- Celeris-1 Decision vs pplx-decider
- Clef vs Microsoft-Decision-1.1
- Clef vs pplx-decider
- Laya vs Microsoft-Decision-1.1
- Laya vs pplx-decider
- Decider vs Microsoft-Decision-1.1
- Decider vs pplx-decider
- Decision 3.0 vs Microsoft-Decision-1.1
- Decision 3.0 vs pplx-decider
- Gemini Decision 1 vs Microsoft-Decision-1.1
- Gemini Decision 1 vs pplx-decider
- GLiClass vs Microsoft-Decision-1.1
- GLiClass vs pplx-decider
- Granite Switch 4.1 vs Microsoft-Decision-1.1
- Granite Switch 4.1 vs pplx-decider
- Kev vs Microsoft-Decision-1.1
- Kev vs pplx-decider
- Liquid d1 vs Microsoft-Decision-1.1
- Liquid d1 vs pplx-decider
- Microsoft-Decision-1.1 vs Drex 1.5
- Microsoft-Decision-1.1 vs OpenAI Decisions API
- 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
- Microsoft-Decision-1 vs pplx-decider
- Drex 1.5 vs pplx-decider
- OpenAI Decisions API vs pplx-decider
- pplx-decider vs pplx-decider-flash
- pplx-decider vs RightNow System Zero
- pplx-decider vs ScaleDown
- pplx-decider vs SPEV
- pplx-decider vs kettei
- pplx-decider vs Strands Decider 2B
- pplx-decider vs Jev
- pplx-decider vs Vela 2.0
Machine-readable
- This page as Markdown
/compare/microsoft-decision-1-1-vs-pplx-decider.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/microsoft-decision-1-1.json·/api/v1/tools/pplx-decider.json - From a terminal
anchor compare microsoft-decision-1-1 pplx-decider(the CLI) - Over MCP
compare_tools {"a": "microsoft-decision-1-1", "b": "pplx-decider"}at/mcp, no key