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

# Amazon Rufus API Overview

> Ask Amazon Rufus (Alexa for Shopping) and get complete answers and recommended product cards as structured JSON, with optional ASIN product context.

## Overview

The ScrapeBadger **Amazon Rufus API** sends shopping questions to the real **Alexa for Shopping** experience, formerly branded Rufus. It returns the complete answer and any recommended products as structured JSON.

ScrapeBadger manages the authenticated browser sessions, residential exits, and streamed-response reconstruction. You make one REST call.

> [!NOTE]
>
> Endpoints live under `https://scrapebadger.com/v1/rufus/*` and authenticate with the `X-API-Key` header. `/ask` accepts both `GET` and `POST`. Successful responses report credits on the `X-Credits-Used` response header.

> [!WARNING]
>
> Allow up to **100 seconds** for `/ask`. Rufus composes each answer live. Blocked, empty, truncated, and upstream-failed answers are not billed.

## Features

* **Real Rufus answers** — responses come from Amazon's shopping assistant, not a generic model imitating it.
* **Product-aware context** — add an ASIN to ask about a specific product, its reviews, tradeoffs, or alternatives.
* **Complete streamed answers** — JSON Patch events are reduced in order; intermediate fragments are never returned as the final answer.
* **Structured product cards** — ASIN, title, URL, price, rating, rating count, badge, image, and rank when Amazon supplies them.
* **Independent conversations** — every call starts a new conversation so unrelated questions cannot leak context into one another.

> [!WARNING]
>
> Each request is a fresh, independent question. `thread_id` identifies the exchange for tracing; it is not a multi-turn input. Multi-turn conversations, model selection, and client-side streaming are not supported.

## Credits

| Endpoint | Path | Credits |
| - | - | - |
| Ask | `GET`/`POST` `/v1/rufus/ask` | 50 |
| List models | `GET /v1/rufus/models` | 1 |
| Health | `GET`/`HEAD` `/v1/rufus/health` | 0 |

At PAYG, 50 credits is **$0.0075 per answer**, or **$7.50 per 1,000 answers**. Subscription tiers reduce that rate.

## Quickstart

```bash cURL theme={null}
curl "https://scrapebadger.com/v1/rufus/ask?asin=B09M7WWTFP&prompt=What%20are%20the%20main%20tradeoffs%20of%20this%20product%3F" \
  -H "X-API-Key: YOUR_API_KEY" \
  --max-time 100
```

```javascript Node.js theme={null}
const res = await fetch("https://scrapebadger.com/v1/rufus/ask", {
  method: "POST",
  headers: {
    "X-API-Key": process.env.SCRAPEBADGER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "What are the main tradeoffs of this product?",
    asin: "B09M7WWTFP",
  }),
  signal: AbortSignal.timeout(100_000),
});
const data = await res.json();
console.log(data.answer);
console.log(data.products);
```

```python Python theme={null}
import requests

res = requests.post(
    "https://scrapebadger.com/v1/rufus/ask",
    headers={"X-API-Key": "YOUR_API_KEY"},
    json={
        "prompt": "What are the main tradeoffs of this product?",
        "asin": "B09M7WWTFP",
    },
    timeout=100,
)
data = res.json()
print(data["answer"])
print(data["products"])
```

## What you can build

> [card] Product research
>
> Compare products, identify tradeoffs, and collect structured recommendations with prices and ratings.

> [card] Review analysis
>
> Ask about common complaints, praised features, and suitability for a specific customer or use case.

> [card] Shopping assistants
>
> Add real Amazon shopping answers to your own application without maintaining browser profiles.

> [card] Competitor monitoring
>
> Track which products Rufus recommends for the buying questions your customers ask.

## Run this asynchronously

Calls on this API can run in the background, so you don't hold a connection open while they work. Add one of these to the call:

| Add | What you get |
| - | - |
| `async=true` | The normal response if the call finishes within 25 s. Otherwise `202` with a `request_id`, which you poll at `GET /v1/requests/{request_id}` for free. |
| `callback_url=https://…` | `202` at once. When the call completes, the result is POSTed to your URL, signed with your webhook secret. |
| `Idempotency-Key: <your id>` header | A resent submit returns the first call instead of running it again. |

```bash theme={null}
curl -s "https://scrapebadger.com/v1/...?your=params&async=true" \
  -H "X-API-Key: $SCRAPEBADGER_API_KEY"
# 202 {"request_id": "…", "status": "running", …}, then:
curl -s "https://scrapebadger.com/v1/requests/REQUEST_ID" \
  -H "X-API-Key: $SCRAPEBADGER_API_KEY"
```

An async call is billed once, when it completes. See [Async requests and webhooks](https://docs.scrapebadger.com/long-running-requests.md) for webhooks, signatures and the SDK helpers.


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