> For the complete documentation index, see [llms.txt](https://docs.scraperapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.scraperapi.com/resources/release-notes/july-2026/new-turn-ai-conversations-into-structured-json-with-one-api-call..md).

# NEW! Turn AI conversations into structured JSON with one API call.

Extract structured results from ChatGPT, Perplexity, Gemini, and Google AI Mode without managing browsers, proxies, CAPTCHAs, or custom parsers.

{% hint style="info" %}
Beta: AI Results APIs is currently in BETA. Features, supported engines and response fields may change as we continue improving the product.
{% endhint %}

## What's new

AI Results API lets you send a prompt to a supported AI platform and receive a normalized response in either **structured JSON** or **raw HTML**.

You simply send a request and receive clean, consistent data.

#### Supported engines

* ChatGPT
* Perplexity
* Gemini
* Google AI Mode

**Why use AI Results API?**

Building against consumer AI interfaces yourself means dealing with:

* Anti-bot protection
* Browser automation
* Streaming response assembly
* Constant UI changes
* Fragile parsers

Our AI Results API removes that operational overhead so you can focus on building products.

Common use cases include:

* Brand monitoring
* Competitive intelligence
* GEO / AI search tracking
* Market research
* Large-scale AI answer collection

### Response format

Every request returns the same schema regardless of provider.

| Field             | Description                                                               |
| ----------------- | ------------------------------------------------------------------------- |
| `query`           | The original prompt                                                       |
| `answer`          | Complete response in Markdown                                             |
| `sources`         | Citations including title, URL, domain, and snippet (only when available) |
| `model`           | Model used to generate the response (when available)                      |
| `related_queries` | Suggested follow-up searches (currently Perplexity only)                  |

Fields are always returned. If data isn't available, empty arrays or `null` values are used instead of omitting fields.

Available for all plans under standard ScraperAPI pricing.

| Engine                                                 | Cost                   |
| ------------------------------------------------------ | ---------------------- |
| ChatGPT, Perplexity, Gemini, Google AI Mode            | **25 credits/request** |
| ChatGPT (`sources=true`) - Not available for free plan | **75 credits/request** |

<a href="https://dashboard.scraperapi.com/apiplayground?method=async_google_ai_mode" class="button primary" data-icon="play">Try it in Playground</a><a href="https://docs.scraperapi.com/structured-data-endpoints/ai-results" class="button secondary" data-icon="book">Documentation</a>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.scraperapi.com/resources/release-notes/july-2026/new-turn-ai-conversations-into-structured-json-with-one-api-call..md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.