# Amazon review analysis. What buyers praise and what they complain about.

> Pull Amazon reviews with text, rating, date, verified-purchase flag and helpful votes, up to 100 per product, then let your agent find the themes.

Canonical: https://apiforagents.dev/use-cases/amazon-review-analysis · Updated 2026-10-21

Find the products in a category, pull their reviews, and let a model group the complaints and the praise. Reviews come with rating, date, verified-purchase and Vine flags, helpful votes and the variant bought.

- Records: from $0.00045 per record
- Per call: Up to ten products
- Free to start: $0.10

## The workflow

1. Run Amazon search with a query and a marketplace such as "com" or "in". Every hit is a full product card with its search rank.
2. Pick the ASINs to study: yours and the top competitors.
3. Run Amazon reviews with up to ten ASINs per call. Amazon caps reviews at 100 per product.
4. Keep verified-purchase reviews, weight by helpful votes, and split by variant to see whether one size or colour drives the complaints.
5. Run Amazon products for price, rating and count, and best-sellers rank, so each theme sits next to the numbers.

## Three ways to use it

- **Product teams.** Find the faults buyers mention most often in your own reviews and fix them in the next version.
- **Brands against competitors.** Read the top competitors' reviews side by side and see where they disappoint the buyers you want.
- **[New product research](https://apiforagents.dev/platforms/amazon/search-api).** Search a category, then look for recurring complaints on the best sellers. A gap people keep asking for is a product idea.

## Operations used

List prices per record. A call can carry a minimum, so quote first: the quote is free, and a record that does not come back is not charged.

| Step | Operation | What comes back | Price |
|---|---|---|---|
| 1 | Amazon search | Full product cards with search rank | $0.00045 per record |
| 2 | Amazon reviews | Text, rating, date, verified-purchase and Vine flags, helpful votes, variant | $0.00045 per record |
| 3 | Amazon products | Price, list price, rating and count, best-sellers rank, seller | $0.0014 per record |

> **Quote first** Ten ASINs at 100 reviews each is up to a thousand records. Send the call with "estimateOnly": true, then run it with "maxUsd" set to that figure.

## The operations in this workflow

- [Amazon search](https://apiforagents.dev/platforms/amazon/search-api): Full product cards with search rank
- [Amazon reviews](https://apiforagents.dev/platforms/amazon/reviews-api): Text, rating, date, verified-purchase and Vine flags, helpful votes, variant
- [Amazon products](https://apiforagents.dev/platforms/amazon/product-api): Price, list price, rating and count, best-sellers rank, seller

## Questions

### Which Amazon sites are covered?

com, in, co.uk, de, fr, it, es, ca, com.au, co.jp, com.mx and com.br, chosen with marketplace. A product URL carries its own site.

### Is there a limit on reviews per product?

Amazon caps reviews at 100 per product, so that is the most one product can return.

### Can I track rating changes over time?

Yes. The free history operation charts rating and ratings count for products you have already captured.

## Why API for Agents

- One key for 26 platforms: social, commerce, jobs, places, search and contacts, with one request shape and one response shape.
- A free quote before any spend: add "estimateOnly": true to any call and see the most it can cost.
- Pay per record in US dollars. No subscription, nothing expires, top-ups from $5.
- $0.10 free to try, no card. An AI agent can sign itself up in one request; a person claims it later.
- Measured, not estimated: every answer says when each row was measured, whether it was fresh or a recent capture, and how sure to be of each field.
- Partial success is success: anything that could not be fetched is named with a reason, and the charge settles to what came back, never above the quote.
- Typed fields that keep their names whichever source answered, and a details object last with everything else the source sent, under our own field names.
- Try any endpoint in the playground and download the answer as CSV or JSON.

## Start

The playground runs any endpoint by hand: pick a platform and what you want from it, fill a short form named in plain words (or press Use sample input), see the free quote on the Run button, run it, then read the answer as a table or JSON and download it as CSV or JSON. The same call is written out as cURL, Python and Node while you type. Open it at https://apiforagents.dev/dashboard/run (sign in first).

Agents register at https://apiforagents.dev/auth.md (one POST, $0.10 free). People: https://apiforagents.dev/docs#start. Prices: https://apiforagents.dev/pricing.md