> ## Documentation Index
> Fetch the complete documentation index at: https://docs.scaledown.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> A Jev-compatible decisions API: ask typed choice, noul, and score questions against a shared state object.

## What it does

The `/v1/scaledown` endpoint answers typed questions about a piece of text or a document, in the same request/response shape as [TypeSafe's Jev Decisions API](https://openrouter.ai/docs/guides/community/jev) (`POST /api/alpha/decisions` on OpenRouter). If you already have integration code written against Jev, it should work against `/v1/scaledown` with only the base URL changed.

You send a `state` object (the item being decided on) and a `questions` map, where each question is one of three typed primitives:

* **`choice`** - pick exactly one option from a set of criteria. Backed by the same calibrated single-label decode as [`/classify`](/api-reference/classify).
* **`noul`** - an independent yes/no question, answered as a probability. Backed by the same calibrated binary decode `/classify` uses in multi-label mode.
* **`score`** - an ordered-scale question. **Not supported** - see [Unsupported: `score`](#unsupported-score) below.

Every question in a request is answered against the same shared `state`, concurrently.

## When to use it

**You're porting an existing Jev integration.** `/v1/scaledown` accepts the same request shape and returns the same response shape, so a Jev-based routing or tagging layer can point at `api.scaledown.xyz` instead with minimal changes.

**You want several classification decisions from one request.** Mix `choice` and `noul` questions in a single call - e.g. pick a category *and* check three independent tags - instead of making separate `/classify` calls.

**You don't need our classify-specific features.** `/v1/scaledown` is a thin, standard-shaped layer over `/classify`. If you need batching (`chunks`), image-direct multimodal input, or the free-form `reasoning` explanation, use [`/classify`](/api-reference/classify) directly - `/v1/scaledown` intentionally doesn't expose those.

## How it fits into your workflow

```
[Jev-shaped request] → [POST /v1/scaledown] → [choice/noul answered via /classify's scoring] → [answers + usage]
```

Internally, each `choice` question becomes one single-label classify call (its `criteria` become labels), and each `noul` question becomes one binary yes/no classify call. Both run concurrently against the shared `state`, and the response's `usage` is the sum of every internal call's tokens.

## Unsupported: `score`

We have no ordered-scale scoring primitive today - only mutually-exclusive `choice` and independent `noul` decodes. What happens with a `score` question depends on what else is in the request:

* **Alongside a `choice`/`noul` question:** the request still succeeds (`200`). Every other question is answered normally; the `score` question's answer comes back as:

  ```json theme={null}
  { "type": "unsupported", "reason": "'score' questions are not supported by this API" }
  ```

* **On its own, or with only other `score` questions:** the request fails with `422` instead - there's nothing in it that could be answered, so it doesn't make sense to return a `200` full of `"unsupported"` placeholders.

If you need an ordered scale today, model it as a `choice` question with your scale points as options (e.g. `"1"`, `"2"`, `"3"`, `"4"`, `"5"`) and use `probabilities` to see how confident the model was, or ask us about adding native `score` support.

## Model

The only supported `model` value is `"classify-1"`, which is also the default when the field is omitted. Sending any other value returns `422`. There's currently no way to select a different backend model through this endpoint.

## Differences from Jev

|                                      | Jev             | `/v1/scaledown`                                                                                 |
| ------------------------------------ | --------------- | ----------------------------------------------------------------------------------------------- |
| `choice` / `noul`                    | ✅               | ✅                                                                                               |
| `score`                              | ✅               | ❌ - `"unsupported"` in a mixed request, `422` if the whole request is `score`                   |
| Mixed question types per request     | ✅               | ✅ - routed internally, answered concurrently                                                    |
| Arbitrary multi-field `state` object | ✅               | Only `state.text` / `state.document` are read                                                   |
| Model selection                      | Multiple models | Only `"classify-1"`                                                                             |
| Batch input (many items per request) | ❌               | Not on `/v1/scaledown` - use [`/classify`](/api-reference/classify)'s `chunks`                  |
| Document / image classification      | ❌               | `state.document` + `state.document_mime_type` (non-standard extension)                          |
| Free-form reasoning explanation      | ❌               | Not available on this endpoint (see [`/classify`](/api-reference/classify)'s `reasoning` field) |