THE WORLD IS NOT STANDING STILL.RSS
BIG CHANGE.
BIG CHANGE, one tap away
BIG CHANGE, one tap away

Make room for the big picture.

Add BIG CHANGE to your home screen or desktop. It opens in its own window, with the latest stories when you’re online.

iPhone & iPad
Open bigchange.ai in Safari. Tap Share, then Add to Home Screen. Turn on Open as Web App if shown, then tap Add.
Android
Open bigchange.ai in Chrome. In the browser menu, choose Install app or Add to Home screen.
Desktop
In Chrome or Edge, use the install icon in the address bar or the browser’s app menu. In Safari on Mac, choose File → Add to Dock.

Markdown edition

# OpenAI Decisions API is generally available: answers, pricing and limits

> OpenAI’s Decisions API is generally available with JSON inputs, question images and caching. Its typed answers, prices and limits define what builders can evaluate now.

By BIGCHANGE.AI Editorial

Published: 2026-10-24T20:50:39.659Z
Updated: 2026-10-24T20:50:39.659Z
Canonical: https://bigchange.ai/blog/openai-decisions-api-ga-contract-pricing-limits

![Conceptual illustration of two developers at one desktop workstation reviewing an image, text context and three unlabeled possible choices on a generic screen.](https://bigchange.ai/api/media/file/openai-decisions-developer-routing-hero-v2.png)
AI-generated by OpenAI; BIG CHANGE conceptual editorial illustration.

OpenAI made its Decisions API generally available on October 22, moving a tool for small, bounded AI judgments beyond its October public beta. The [current developer guide](https://developers.openai.com/api/docs/guides/decisions) now spells out the request, answer types and pricing. For a developer deciding whether to put a model in an application’s routing path, the useful distinction is precise: Decisions supplies an answer to a question the application defines; the application still decides what to do with it.

The [October 22 launch](https://openai.com/index/decisions-api/) names additions since beta: native JSON input, images inside individual question instructions, prompt caching, native GPT-Live integration and up to 400 questions in one request, up from 200. OpenAI also says it added capacity in several Asian regions. Its [API changelog](https://developers.openai.com/api/docs/changelog) records the beta release on October 6 and the GA update on October 22. Our [earlier preview account](https://bigchange.ai/blog/openai-decisions-api-preview-developer-guide) described a product whose public contract and price were still unsettled; the published guide and reference now give builders a specific interface to assess.

## What the API returns

The documented call is `POST /v1/decisions` with `model`, shared `input` and a `questions` array. The only currently supported model is `gpt-6-luna`. Shared input can be text or an ordered history of supported messages and tool calls. Each named question specifies its type and instructions, plus allowed choices or rubric levels where needed. The response’s `answers` array follows question order and echoes names so the application can match results to questions. These are descriptions of [OpenAI’s guide](https://developers.openai.com/api/docs/guides/decisions) and [API reference](https://developers.openai.com/api/reference/resources/decisions), not a BIG CHANGE integration test.

A `predicate` returns an estimated probability from zero to one for a stated condition. A `choice` selects one developer supplied string or Boolean value and returns probabilities and a confidence field. A `score` applies ordered rubric levels and returns a probability weighted average of their numeric indices, which may fall between levels. A question can instead receive a refusal while other questions in the same request receive answers. That [reference behavior](https://developers.openai.com/api/reference/resources/decisions) matters to code that expects every answer to contain a choice or score.

OpenAI distinguishes these typed judgments from generating an arbitrary JSON object with Structured Outputs or asking a model to call a tool. The [guide](https://developers.openai.com/api/docs/guides/decisions) says tool calls and their outputs may be supplied as evidence, but the consuming application executes any selected action. A returned `choice` therefore does not grant permission to perform that action. Authorization, side effects and a fallback for refusals belong in the surrounding application.

## What changed for inputs and control

The GA guide accepts `input_json` in a user message, so structured evidence need not first be turned into prose. Images can be shared evidence or included in a particular question’s instructions. Public HTTP or HTTPS image URLs and inline base64 data URLs are documented; file IDs are not. The [reference](https://developers.openai.com/api/reference/resources/decisions) limits a JSON content part to 256 KiB of compact UTF-8, 10,000 values and 32 container levels. Files, audio and item references are outside the documented Decisions input. GPT-Live is a separate native integration that can trigger Decisions from transcript events or delegate to it during a live session; it does not make raw audio a Decisions request input.

The 400-question ceiling is a batching limit, not a 400-step workflow. OpenAI says to group independent questions against the same input, and to send a later request when one decision depends on an earlier answer. Its [guide](https://developers.openai.com/api/docs/guides/decisions) recommends distinct choices, observable criteria and clearly separated rubric levels. That is also a useful test of fit: if a decision needs a free-form explanation or an open-ended tool plan, the three bounded answer types cannot express it directly.

## Price, access and evidence to check

For Decisions using `gpt-6-luna`, OpenAI lists **$0.10 per million uncached input tokens**, **$0.01 per million cached input tokens**, and no output-token charge. The [pricing guide](https://developers.openai.com/api/docs/pricing) lists **$0.125 per million tokens for 30-minute cache writes** and **$0.25 for 12-hour writes** at the standard rate. The Decisions guide says regional processing premiums and long-context input multipliers apply. A cache hit requires a matching shared-input prefix of at least 1,024 tokens; question content does not count toward that threshold. These are token rates, not a per-decision quote: input size, image tokens, cache behavior and the number of requests determine an application’s bill.

OpenAI says regional processing is supported in the US and Europe, while data residency is available in supported API regions. Zero Data Retention and HIPAA use have eligibility requirements. Developers need to check their project’s model access and rate limits, plus the [data-controls terms](https://developers.openai.com/api/docs/guides/your-data), for the region and handling they require. The organization usage endpoint reports request counts and tokens; a request containing many questions counts as one model request, according to the [guide](https://developers.openai.com/api/docs/guides/decisions).

OpenAI advertises answers **up to 10 times faster than GPT-6 Luna through the Responses API** for bounded questions. The [launch](https://openai.com/index/decisions-api/) gives that comparator, but does not publish the test set, sample size, latency statistic or request settings behind the figure. Its customer examples report separate workloads: Box, for instance, says route selection was about five times faster than Responses on 30 certificate-of-insurance cases in its evaluation. A useful evaluation would label examples from the actual routing task, compare false positives and false negatives at the chosen threshold, count refusals, and measure latency and token usage under the expected request mix. OpenAI itself recommends labeled examples and thresholds tied to error costs. BIG CHANGE has not run such an evaluation.

## The big change

- The October 22 GA provides a published, typed API contract for bounded questions, with one supported model and a 400-question request limit.
- JSON, question-specific images, caching and GPT-Live integration widen where that contract can be used; the application remains responsible for execution and permissions.
- The low input-token rate is a starting price. Accuracy, refusals, latency, cache hits and regional terms still need assessment in the intended workflow.

## Sources

- [OpenAI: Build more responsive apps with the Decisions API](https://openai.com/index/decisions-api/) — October 22, 2026 GA announcement and attributed product/performance claims; customer statements are not independent validation.
- [OpenAI API: Decisions developer guide](https://developers.openai.com/api/docs/guides/decisions) — Current October 24 read of interface, typed answers, limits, caching, access and evaluation guidance; living documentation.
- [OpenAI API reference: Decisions](https://developers.openai.com/api/reference/resources/decisions) — Current October 24 read of accepted request/response shapes, refusal handling and JSON/image constraints.
- [OpenAI API changelog](https://developers.openai.com/api/docs/changelog) — Dated October 6 beta, October 15 Live integration and October 22 GA entries.
- [OpenAI API pricing](https://developers.openai.com/api/docs/pricing) — Standard GPT-6 Luna cached-read and cache-write rates; Decisions guide establishes Decisions-specific no-output-charge rule.
- [OpenAI API data controls](https://developers.openai.com/api/docs/guides/your-data) — Eligibility and handling terms to check for residency, ZDR and HIPAA.
- [BIG CHANGE: OpenAI’s Decisions API preview](https://bigchange.ai/blog/openai-decisions-api-preview-developer-guide) — Earlier coverage and timeline context, not evidence for current contract or pricing.