---
title: "AI Recommendation Index — dated answer excerpts per engine"
method: GET
path: "/api/index/{slug}/answers"
tags: ["AI Index"]
---

# AI Recommendation Index — dated answer excerpts per engine

`GET /api/index/{slug}/answers`

## Request

- Base URL: `https://api.orbator.io`
- URL: `https://api.orbator.io/api/index/{slug}/answers`
- Auth: one of:
  - none
  - API key in header `X-Api-Key`
  - HTTP bearer

What each engine actually said for this category on one date, grouped by engine: the run date, the prompt INTENT (never the prompt text), a short excerpt of at most 400 characters, and server-computed {start, end, name} highlight offsets for the entities the extractor recorded. Only Index category runs are archived — customer scans never appear at any granularity — and full engine output is never served. Engines outside the verbatim allowlist (ARCHIVE_VERBATIM_ENGINES; Perplexity is excluded by default under its terms) are reported as having answered with excerpt_withheld: true rather than hidden. Defaults to the most recent archived date; available_dates lists the rest, and every dated view is a stable ?date= URL.

## Path parameters

- `slug` string, required

## Query parameters

- `date` string, date
- `engine` string

## Response `200`

Answer excerpts for the date, grouped by engine (capped at 50, highest-sample prompts first), with the available dates and the published exposure policy

## Other responses

- `400`: Malformed date or engine id
- `404`: Unknown or unpublished category
- `429`: Hourly quota exceeded for the current tier. Retry after the Retry-After header.

---

[API](https://skmtc.dev/orbator/apis/orbator-public-api.md) · [All operations](https://skmtc.dev/orbator/apis/orbator-public-api/llms.txt) · [OpenAPI document](https://skmtc.dev/orbator/apis/orbator-public-api/revisions/7d1cf20c2163?raw)