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

# Pricing

> How the Andi AI Search API is priced. Each call is charged for the work it performs, and every response reports its own cost.

The Andi AI Search API uses outcome-based pricing. Each call is charged for the work it actually performs, not a flat per-call rate. A simple lookup costs less than a research question that needs several searches and stronger reranking.

Calls are charged to your account in the [API Console](https://console.andiai.com), where you also manage billing.

## How each endpoint is priced

| Endpoint | How it is charged |
| - | - |
| Search (`/api/v1/search`) | A charge for the work the search performed, plus a per-token rate on the content returned. With the default `auto` mode, the charge follows the effort Andi chose for each query. |
| Fetch (`/api/v1/fetch`) | $0.001 per request plus $0.05 per 1M tokens of extracted content. A page that needs extra retrieval work can cost more. |
| News (`/api/v1/news/:topic`) | A charge for the ranking work plus a per-token rate on the returned content. There is no flat per-call fee. |

Endpoint details:

* Search: [search modes](https://docs.andiai.com/search/search-modes.md#pricing)
* Fetch: [content retrieval](https://docs.andiai.com/search/content-retrieval.md#pricing)
* News: [news feeds](https://docs.andiai.com/search/news-feeds.md#pricing)

## What is not charged

* Failed fetches. `422` and `503` responses from the fetch endpoint are free.
* Search extracts. `extracts=true` adds passage-level text to each search result at no additional cost.
* The news topics index. `GET /api/v1/news` is free.

News cache hits are charged the per-token rate only, because no search runs.

## See the cost of each call

Every response reports what it cost, in USD, after any discounts:

* JSON responses: `metrics.cost_dollars`
* `format=context` responses: `cost_dollars` in the frontmatter

```json theme={null}
{
  "metrics": {
    "cost_dollars": 0.0207,
    "duration": 1240,
    "results_returned": 10
  }
}
```

See [metrics](https://docs.andiai.com/features/response-format.md#metrics) for the other fields. For usage totals over time, see the [API Console](https://console.andiai.com).

## Control your spend

* Use `auto` (the default) for most traffic. Simple queries stay cheap even when your mix includes hard ones.
* Pin a [search mode](https://docs.andiai.com/search/search-modes.md#setting-the-effort-yourself) when you want more uniform cost from call to call. `low-cost` has a cost ceiling.
* Cap page text with `maxContentLength` and `limit` when you request full content, because returned content is charged per token.
* Use search `extracts=true` instead of fetching each result page when passages are enough.

When your balance runs out, requests return `402`. See [error handling](https://docs.andiai.com/resources/error-handling.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.