Compare · Last verified 2026-10-15

OpenAI Decisions vs Microsoft-Decision-1: pricing, limits, and which to use

Verdict

As of 2026-10-15, Microsoft-Decision-1 is cheaper ($0.042 vs $0.10 per 1M input tokens) and publishes a 32,768-token context on OpenRouter, while the OpenAI Decisions API publishes no context or rate limits. OpenAI accepts images and has ZDR/HIPAA options; Microsoft accepts text or JSON state and runs in Azure Foundry. Neither publishes an SLA on the pages we checked.

  • Pick OpenAI Decisions for: Image-plus-text decisions and teams standardized on the OpenAI platform.
  • Pick Microsoft-Decision-1 for: Lower cost, JSON state, and Azure/Entra-governed deployments.

Side-by-side

OpenAI Decisions APIMicrosoft-Decision-1
VendorOpenAIMicrosoft (Foundry)
CategoryDecision modelDecision model
Price

$0.10 per 1M input tokens; no output, cache-read, or cache-write charges. [Verified 2026-10-15 against official page]

Regional processing premiums and long-context input multipliers apply (amounts not stated on the guide). [Verified 2026-10-15 against official page]

$0.042 per 1M input tokens; output $0 (OpenRouter listing, provider Azure). [Verified 2026-10-15 on OpenRouter; Foundry/Azure price page not checked]

Limits

Context window and rate limits are not stated on the Decisions guide. [Unverified — not published on the page checked]

32,768-token context window (OpenRouter). [Verified 2026-10-15 on OpenRouter]

Rate limits are per deployment quota (429 on exceed); specific numbers not published on the how-to page. [Verified 2026-10-15 against official page]

Status

Public beta; OpenAI says it expects GA "in the coming weeks". [Verified 2026-10-15 against official page]

Data controls: ZDR and HIPAA for eligible customers; data residency/regional processing in the US and Europe (EEA + Switzerland). [Verified 2026-10-15 against official page]

No published SLA, dated model snapshot, or deprecation schedule found for /v1/decisions. [Absence noted 2026-10-14/15; not confirmed against enterprise terms]

Released Oct 9, 2026 (OpenRouter). OpenRouter reported 99.99% availability over 3 days on 2026-10-15. [Verified 2026-10-15 on OpenRouter]

OpenRouter: "Weights are updated continually while the API shape stays the same." Microsoft docs list model version 1. [Verified 2026-10-15; whether Foundry pins weights per version is unclear]

Preview label and any SLA. [Unverified — not confirmed on a Microsoft page]

Fit notes
  • Good fit: classification, routing, prioritization, and review queues with app-owned thresholds set from your own labeled examples.
  • Only the alias gpt-6-luna is documented — behavior can change under you. Run a canary eval and log the model string on every call.
  • No rationale is returned; if users need an explanation, pair it with a generative model and human review.
  • OpenAI Usage Policies restrict automating high-stakes decisions in sensitive areas (e.g. critical infrastructure, product safety components, medical) without human review. Keep it advisory; never the sole authority.
  • Good fit: gates, routing, ranking, grading, and agent/tool selection inside a fixed allowlist.
  • Microsoft lists known risks: bias, wording/order sensitivity, calibration strongest on familiar tasks, no explanations, may miss harmful content.
  • Microsoft: for consequential decisions about people (credit, employment, housing, healthcare, legal) use it for decision support with meaningful human review, not as the sole decision-maker.
  • Recommended: include a "cannot tell" option, randomize option order, and set thresholds from labeled data.

FAQ

Which is cheaper?

Microsoft-Decision-1 at $0.042 per 1M input tokens (OpenRouter, provider Azure) vs $0.10 for the OpenAI Decisions API, as of 2026-10-15.

Is either generally available?

OpenAI Decisions is in public beta. Microsoft-Decision-1 was released Oct 9, 2026; a preview/GA label was not confirmed on a Microsoft page.

Do they return explanations?

No. Both return typed probabilities/choices/scores without a rationale.

Methodology

Every fact in the table is copied from the vendor's official page (or OpenRouter where noted) and labeled with the date it was last verified. Items we could not confirm are marked unverified. Prices are list prices per 1M input tokens before regional or volume adjustments. See our methodology.

Sources (checked 2026-10-15)

More comparisons