# OpenAI Decisions API: Price, Question Types, vs Jev

> OpenAI's Decisions API returns typed answers on gpt-6-luna at $0.10 per 1M input tokens, no output charge. Question types, limits and the Jev comparison.

- Author: Nitish Garg, Founder & CEO, CellCog
- Published: 2026-10-06
- Canonical (HTML): https://cellcog.ai/blog/openai-decisions-api/
- Section: Guides / Choosing a platform
- Publisher: CellCog (https://cellcog.ai), the AI employee platform. Blog index for agents: https://cellcog.ai/blog/llms.txt

## Key points

- OpenAI released the Decisions API in public beta on October 6, 2026: POST /v1/decisions takes text or images plus typed questions and returns answers instead of written text.
- Three question types: predicate returns a probability that a condition is true, choice returns one option plus probabilities, score returns a weighted position on ordered levels.
- It runs only on gpt-6-luna and charges $0.10 per million input tokens, with no output, cache-read or cache-write charges; Luna on the Responses API costs $0.50 per million output tokens.
- OpenAI says it returns typed answers about 10x faster than the Responses API and expects general availability in the coming weeks.
- TypeSafe's Jev lists $0.042 per million input tokens, so 1M classifications of 500 tokens cost about $21 on Jev against $50 on OpenAI; neither vendor has published head-to-head accuracy.
- Images must be inline base64; hosted image URLs and file IDs are refused. Zero Data Retention and HIPAA are available to eligible customers, with US and EU data residency.

## At a glance

- **What is the Decisions API?** OpenAI's beta endpoint POST /v1/decisions, released October 6, 2026, that returns typed answers (probability, choice, score) on gpt-6-luna.
- **What does it cost?** $0.10 per million input tokens, with no output, cache-read or cache-write charges, per OpenAI's guide.
- **How does it compare with Jev?** Jev lists $0.042 per million input tokens and is text-only; OpenAI's endpoint costs more per token but reads images.

**OpenAI released the Decisions API in beta on October 6, 2026: a new endpoint, `POST /v1/decisions`, that takes text or images plus a list of questions and returns typed answers (a probability, a choice or a score) instead of written text.** It runs only on `gpt-6-luna`, charges $0.10 per million input tokens and nothing for output, and OpenAI says it "returns typed answers about 10x faster than the Responses API". The product is a direct answer to Jev, the decision model from TypeSafe AI that spread through Vercel's AI Gateway in September. This page reads OpenAI's [API changelog](https://developers.openai.com/api/docs/changelog), the [Decisions guide](https://developers.openai.com/api/docs/guides/decisions), the [GPT-6 Luna model page](https://developers.openai.com/api/docs/models/gpt-6-luna) and the [pricing page](https://developers.openai.com/api/docs/pricing), as of October 6, 2026.

## What OpenAI shipped

A request has three parts: the `model` (only `gpt-6-luna` today), the `input` (a text string, or user messages mixing text and images) and the `questions`, each with a unique name, a type and instructions. The response is an `answers` array keyed by those names. On status, the guide is plain: "The Decisions API is in public beta, and we expect to GA in the coming weeks."

*Table: OpenAI Decisions API at a glance (OpenAI docs, October 6, 2026)*

| Item | Decisions API |
|---|---|
| Released | October 6, 2026, public beta |
| Endpoint | POST /v1/decisions |
| Model | gpt-6-luna only |
| Inputs | Text, or text and images (images as inline base64 only) |
| Question types | Predicate, choice, score |
| Price | $0.10 per million input tokens; no output, cache-read or cache-write charges |
| Speed claim | About 10x faster than the Responses API |
| Data controls | Zero Data Retention and HIPAA for eligible customers; US and EU data residency |
| Playground | platform.openai.com/decisions |

*The Decisions API in two pictures, from OpenAI's docs*

![Three cards: predicate returns 0.92, choice returns billing with probabilities, score returns 3.4 on a five-level rubric](https://cellcog.ai/blog/media/openai-decisions-api/slide-1.webp)
*Three question types: a probability, a choice from a set, or a score on a rubric*

![Two bars: TypeSafe Jev at 21 dollars and OpenAI Decisions API at 50 dollars, with no output charge on either](https://cellcog.ai/blog/media/openai-decisions-api/slide-2.webp)
*Input cost for 1M classifications of 500 tokens: Jev $21, Decisions API $50*

## The three question types

Each type returns a different kind of answer, and the guide gives one worked example per type: a damaged-product photo, a billing complaint routed to a department, and a bug scored for severity.

*Table: Decisions API question types (OpenAI Decisions guide, October 6, 2026)*

| Type | Use it to | What comes back |
|---|---|---|
| predicate | Check whether a condition holds, such as visible damage in a photo | A probability from 0 to 1 that the condition is true |
| choice | Pick one option from a fixed set, such as a department | The chosen value, a probability for every option, and a confidence |
| score | Rate an input on ordered levels, such as severity | The probability-weighted average of the level indices, which can fall between levels |

OpenAI's advice on reading the numbers is to set thresholds from your own labeled examples, weighed by the cost of a false positive against a false negative. When the task is to produce an object of your own shape (extracted fields, a written explanation), the guide points back to Structured Outputs on the Responses API; Decisions is for answers, not generation.

## What it costs, and the Jev comparison

The pricing is the headline. On the guide's own wording: "You pay only for input tokens: there are no cache-read, cache-write, or output-token charges." Regional processing premiums and long-context multipliers still apply. The same model through the Responses API costs $0.10 per million input tokens and $0.50 per million output tokens, so a Decisions call removes the output bill entirely.

*Table: Decision-style APIs compared (OpenAI docs October 6, 2026; Jev from our record, read September 19, 2026)*

| Item | OpenAI Decisions API | TypeSafe Jev 1.13 | gpt-6-luna on Responses |
|---|---|---|---|
| Input price per 1M tokens | $0.10 | $0.042 | $0.10 |
| Output price per 1M tokens | None | Free | $0.50 |
| Images | Yes, inline base64 | No, text only | Yes |
| Answer types | Predicate, choice, score | Boolean, choice, score | Free text or your JSON schema |
| Status | Public beta | Early access; on Vercel AI Gateway | Generally available |

The worked example is our arithmetic: one million inputs of 500 tokens is 500 million tokens, $50 at OpenAI's rate and $21 at Jev's list price on our [September 19 record](https://cellcog.ai/blog/jev-typesafe-decision-model/). Jev stays cheaper per token and text-only; OpenAI's version reads images, sits inside an account most teams already have, and carries ZDR and HIPAA eligibility. Neither vendor has published a head-to-head accuracy number, so the right test is your own labeled set on both.

## What changes if you build on it

- **Routing and triage get a native endpoint.** Ticket routing, content moderation, lead scoring and relevance checks used to be a chat call parsed back into a label. Here the label and its probability come back typed.
- **Images must be inline.** The endpoint takes base64 data URLs only; hosted image links and uploaded file IDs are refused, so pipelines that pass URLs need a fetch-and-encode step.
- **Beta terms apply.** OpenAI expects general availability in the coming weeks; plan for field names and limits to move until then.
- **Voice is wired in.** The guide links a [voice delegation](https://developers.openai.com/api/docs/guides/decisions-voice) pattern that pairs the Live API with Decisions to choose actions from spoken requests.

## What we are watching

- **General availability.** The GA date, and whether more models than `gpt-6-luna` join the endpoint.
- **Accuracy numbers.** A published calibration or accuracy benchmark from OpenAI or an independent tester, against Jev or a Responses baseline.
- **Jev's reply.** Any TypeSafe price or feature change after October 6.
- **The 10x claim.** Independent latency measurements of the speed gap OpenAI states.

## Sources

- OpenAI API changelog, October 6, 2026: [developers.openai.com](https://developers.openai.com/api/docs/changelog)
- OpenAI Decisions guide: [developers.openai.com](https://developers.openai.com/api/docs/guides/decisions)
- GPT-6 Luna model page: [developers.openai.com](https://developers.openai.com/api/docs/models/gpt-6-luna)
- OpenAI API pricing: [developers.openai.com](https://developers.openai.com/api/docs/pricing)
- Our record of TypeSafe's Jev, September 2026: [cellcog.ai](https://cellcog.ai/blog/jev-typesafe-decision-model/)

## FAQ

**What is the OpenAI Decisions API?**

The Decisions API is an OpenAI endpoint, POST /v1/decisions, released in public beta on October 6, 2026. It takes text or images plus a list of questions and returns typed answers: a probability for a predicate, one option for a choice, or a score on ordered levels. It runs on gpt-6-luna.

**How much does the Decisions API cost?**

With gpt-6-luna, input costs $0.10 per million tokens and there are no output, cache-read or cache-write charges, according to OpenAI's guide. Regional processing premiums and long-context multipliers still apply.

**Is the Decisions API faster than the Responses API?**

OpenAI says it returns typed answers about 10x faster than the Responses API. We have not seen an independent latency measurement yet.

**How does the Decisions API compare with TypeSafe's Jev?**

Both return typed decisions with no output charge. Jev lists $0.042 per million input tokens and accepts text only; OpenAI charges $0.10 and accepts images. Neither has published a head-to-head accuracy benchmark, so test both on your own labeled data.

**Can the Decisions API read images?**

Yes, but only as inline base64 data URLs inside user messages. Hosted HTTP or HTTPS image URLs and file IDs are not supported by this endpoint.

## Related

- [Jev, TypeSafe's Decision Model: What It Is, Why It Spread](https://cellcog.ai/blog/jev-typesafe-decision-model/index.md)
- [OpenAI API Usage Tiers: Build, Launch and Grow Explained](https://cellcog.ai/blog/openai-api-usage-tiers/index.md)
- [The Agents API: OpenAI Just Made the Harness a Product](https://cellcog.ai/blog/openai-agents-api/index.md)
- [Best AI Agent Harnesses: October 2026 Rankings](https://cellcog.ai/blog/best-ai-agent-harnesses/index.md)

## The AI employee for this read

[AI Software Engineer](https://cellcog.ai/ai-employees/ai-software-engineer): I built this page. For what it covers, hire an engineer: it works in your repo behind an approval gate, so nothing reaches your world unclassified.

---

Markdown alternate of https://cellcog.ai/blog/openai-decisions-api/. Try CellCog free, no credit card needed: https://cellcog.ai/signup