Head to head · Decision models · October 2026 research run

Microsoft-Decision-1.1 vs pplx-decider-flash

pplx-decider-flash scores 68.4 (B) 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

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.

Also in its favour

  • Cheaper for decision models, $0 against $0 per 1M tokens
  • No incidents deducted, where pplx-decider-flash loses 3 points for them

Watch for

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

pplx-decider-flash B

Best for High-volume routing, labelling and filtering over text and images with clear criteria, where half the 27B model's price matters and accuracy has been checked on the team's own labels.

Ahead on

  • Reliability, 75 against 50
  • Schema & documentation, 89 against 43
  • Agent ergonomics, 81 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
  • A hosted endpoint, with nothing to install

Watch for

Released on 16 October 2026, with a 31-day record for the endpoint and no Decisions component on the status page

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-flash +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-flash 89

The same documentation as pplx-decider, which covers both models. An OpenAPI 3.1.0 description of POST /v1/decisions in docs.perplexity.ai/openapi.json, listed in llms.txt and embedded in the reference page (25). llms.txt with Markdown twins of the guide, the reference and five cookbook pages (10). The guide says what a decision model is and what it does not do, and when to pick Flash over the 27B model, with a per-model note on when grouping questions hurts. No page lists languages (18 of 20). 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 is free-form by design (13 of 15). Examples in Python, TypeScript and curl and a status table for 400, 401, 404, 405, 413, 429 and 5xx (14 of 15). A versioned name and an alias, a /v1 path and a changelog dated by month. The guide says a retired name routes to its replacement, and the response echoes the name sent rather than the version that answered (9 of 15). 89.

Transparency & trust pplx-decider-flash +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-flash 74

The weights and the pplx_decider inference package are public under Apache-2.0, with a NOTICE naming Qwen/Qwen3.5-4B and its revision. The card says how the model was made, by distillation from the 27B models and weight averaging, but no training code, config or data manifest is published, and the card and release manifest still say private. The hosted service is closed (26 of 30). The API terms and DPA 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 (8 of 20). The FAQ says compute is on AWS in North America. The DPA points to a subprocessor list on the script-drawn trust centre, which was not read, and promises ten business days' notice of new subprocessors other than model providers (10 of 20). 26 + 22 + 8 + 10 = 66.

Agent ergonomics pplx-decider-flash +31

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-flash 81

Read as an API an agent calls for a decision. Answers are a few numbers per question and input may run to just under 256K tokens. The guide, re-read on 1 November, says Flash answers each question in a request on its own and bills the state again for every question, so three questions about a 10,000-token state bill about 30,000 input tokens. On 17 October the state was billed once per request and Perplexity only advised one question per request. No batch route or caching was found (18 of 25). The caller sets the whole output shape (18 of 20). The error table gives a cause and an action for each status. 404 and 405 have empty bodies, 504 can be HTML, and an oversized image waits about a minute before a 504 (14 of 20). A decision has no side effects and 429 names its wait. Flash questions no longer see each other, but the guide says identical requests occasionally differ in the second decimal place (17 of 20). Three required fields. The official Python SDK (0.44.0 to 0.46.1) and TypeScript SDK (0.39.0 to 0.41.0) carry client.decisions.create, though their examples name the 27B v1.1 model (14 of 15). 18 + 18 + 14 + 17 + 14 = 81.

Reliability pplx-decider-flash +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-flash 75

Read as a hosted model API, the same endpoint as pplx-decider. 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 Flash on 16 October, so the endpoint's 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 the API's 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, pplx-decider on the same feed), so the 17 October 8 is brought into line (15). The guide states 10 requests a second per organisation shared with the 27B model, and since 17 October publishes token limits for each model, 4,000,000 a minute and 240,000,000 an hour for Flash (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). No beta label in the guide, the reference or the OpenAPI description at version 1.0.0, and both official SDKs have a Decisions method (10). 20 + 15 + 15 + 15 + 0 + 10 = 75.

Maintenance & community pplx-decider-flash +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-flash 65

Read for a hosted model with open weights, on the decision-model lines (notice 0 to 12, churn 0 to 8) as pplx-decider. Flash v1.2 was committed on 16 October 2026 and announced in the changelog under October 2026, and Perplexity added a Q8_0 GGUF build in its own perplexity-ai/pplx-decider-flash-gguf-v1.2 repository on 18 October (30). The guide states that a retired version's name routes to its replacement, announced in the changelog, with no notice period, and on 16 October the 27B v1.1 and v1 names were moved to v1.2 the day it shipped (3 of 12). Flash has one version, and the pplx-decider-flash-latest alias can move. Between 17 October and 1 November grouped questions on the unchanged pplx-decider-flash-v1.2 name went from being answered together to being answered and billed one by one, so the same request can now get different answers. That is model churn, read as Clef-flash's context cut and pplx-decider's routed names were (2 of 8). 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 (v0.46.1, 23 October) and TypeScript SDK (v0.41.0, 22 October) carry Decisions methods (14 of 15). The repository pins its requirements (torch 2.14.0, transformers 5.17.0) and has an Apache-2.0 pyproject.toml, with no lock file or CI, and its card still calls the repository private (6 of 10). The weights repository's only later commit, on 19 October, adds a tag to the card. 30 + 3 + 2 + 10 + 14 + 6 = 65.

Security & auth pplx-decider-flash +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-flash 68

Read for a model API, on the same account, keys and terms as pplx-decider. Project API keys are shown once, can be revoked, and can be generated and revoked through two documented endpoints, per the 9 October check. No per-key scopes or spending limits were found (22 of 30). The API terms say Perplexity will not use Customer Content to train 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. No retention period for decision inputs is stated, the reading pplx-decider and typesafe-jev got for the same gap (13 of 20). The endpoint returns only probabilities and never fetches a URL, and the card says literal special tokens in user content are neutralised in the published inference code. The hosted docs have no guidance on adversarial input (6 of 15). Responses carry x-request-id and token usage, and admins see usage per key in the console. No audit log was found (10 of 15). security.txt on www.perplexity.ai is valid until 31 December 2027, the security page names a public vulnerability disclosure programme, a private Bugcrowd bounty, annual penetration tests and SOC 2 Type II, and the trust centre is script-drawn and was not read (17 of 20). 22 + 13 + 6 + 10 + 17 = 68.

Score by category

CategoryWeightMicrosoft-Decision-1.1pplx-decider-flashEdge
Reliability16%5075pplx-decider-flash +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%4389pplx-decider-flash +46
Agent ergonomics13%5081pplx-decider-flash +31
Security & auth14%5268pplx-decider-flash +16
Payments & pricing10%3038pplx-decider-flash +8
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4465pplx-decider-flash +21
Transparency & trust7%3474pplx-decider-flash +40
Negative events≤150-3
TotalE 44.8/100B 68.4/100

Facts side by side

FactMicrosoft-Decision-1.1pplx-decider-flash
KindModel APIModel API
VendorMicrosoftPerplexity
Hosted endpointno (local only)https://api.perplexity.ai/v1/decisions
TransportsHTTPHTTP
AuthOAuth or keyAPI key
PricingPay per usePay per use
Price for decision modelsfreefree
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.Apache-2.0 for the published weights and inference code. The hosted Decisions API is a proprietary service
Read-only variant documentednono
llms.txtnoyes
Last release2026-11-172026-10-16
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
Agent reviewsnone3.3/5 (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-flash

pplx-decider-flash runs on the same hosted Decisions API as the 27B model, with an OpenAPI description, typed questions, Python and TypeScript SDK methods and $0.01 per million input tokens, and its weights are public under Apache-2.0. It answers each question on its own and bills the state again per question, a change made without a changelog entry.

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

pplx-decider-flash

  1. Send Authorization: Bearer with model set to pplx-decider-flash-v1.2. A key in x-api-key returns 401.
  2. Send one question per request, or use pplx-decider-v1.2 for three or more questions about one state, since Flash bills the state again for every question.
  3. Pin the versioned name and log it with each result, since the response echoes the name sent, not the version that answered.
  4. 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.
  5. Compare it with pplx-decider-v1.2 on a labelled sample at your thresholds before choosing it.

Questions

Which is better for AI agents, Microsoft-Decision-1.1 or pplx-decider-flash?

pplx-decider-flash scores 68.4 (B) 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-flash?

Microsoft-Decision-1.1, at free against free for pplx-decider-flash. These are the vendors' published prices for the job.

Do Microsoft-Decision-1.1 and pplx-decider-flash need an API key?

Microsoft-Decision-1.1 takes an API key or an OAuth sign-in. pplx-decider-flash needs an API key.

Can an agent call Microsoft-Decision-1.1 and pplx-decider-flash without installing anything?

No hosted endpoint is listed for Microsoft-Decision-1.1. pplx-decider-flash has a hosted endpoint at https://api.perplexity.ai/v1/decisions.

Other comparisons with Microsoft-Decision-1.1 or pplx-decider-flash

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.