AliExpress Product Reviews API and MCP — Buyer Reviews, Auto-Translated
Send an AliExpress product ID or URL and this source returns the product's buyer reviews as data, one record per review, with a filter for review type and an option to machine-translate the text.
- You send
- An AliExpress product ID or URL, with optional filter and translate
- You get back
- Individual buyer reviews with rating, text, author and images
- Coverage
- AliExpress products with a public reviews section.
- Price
- 1 point per returned result, up to 250 per request — $1 per 1,000
- Billed per review actually returned, capped by max_items. A product with no reviews costs nothing.
Ways to get this data
Three approaches teams use today, and where each one runs into trouble.
| Approach | What it takes | Cost | Trade-off |
|---|---|---|---|
| Reading reviews by hand | Open the listing, filter, scroll, translate manually | Free, and slow | Fine for one product, useless across a catalog — and most reviews aren't in your language |
| Building a scraper | Write it, host it, and add translation yourself | Engineering time | A maintenance commitment for something that isn't your product |
| NeuralVerge | One request per product | $1 per 1,000, misses not billed | Returns what's published — reviews are self-selected, not a representative sample |
What you get back
Every field in the example response below.
| Field | Type | Description |
|---|---|---|
total_items | number | How many reviews were returned in this batch (capped by max_items). |
reviews | array | Individual review records, when the product has any that match the filter. Each carries id, text, rating, buyer_name, created_at_text (the date as AliExpress shows it, e.g. "04 Oct 2026"), sku_text, images, up_vote_count, is_anonymous and labels, plus buyer_country, buyer_gender, buyer_image, created_at, sku_id, logistics, down_vote_count, additional_text, additional_at_text and additional_images, which can be null or empty. In the example, buyer_country, buyer_gender, buyer_image, created_at, sku_id, logistics, down_vote_count and the additional_* fields are null or empty. |
debug | null | Null in the example, where reviews were returned. When no reviews come back it holds a diagnostic snippet (page title, URL and a text excerpt) to help explain the empty result. |
Example response
A real response, as returned.
{
"session_id": "11111111-1111-1111-1111-111111111111",
"kind": "aliexpress_product_reviews",
"product": "1005012791281455",
"max_items": 2,
"language": null,
"currency": null,
"filter": "all",
"translate": true,
"human": "# AliExpress product reviews\n\n- **Product:** 1005012791281455\n- **Max items:** 2\n- **Records returned:** 1\n- **Proxy traffic:** 2.15 MB",
"machine": {
"total_items": 1,
"reviews": [
{
"@type": "AliexpressProductReview",
"id": "0",
"text": "There was a slight delay in delivery, but the store was very transparent and everything worked out well. The mouse arrived in perfect condition, is very beautiful, and works well.",
"rating": 5,
"buyer_name": "M***z",
"buyer_country": null,
"buyer_gender": null,
"buyer_image": null,
"created_at": null,
"created_at_text": "04 Oct 2026",
"sku_id": null,
"sku_text": "Color:Pink",
"logistics": null,
"images": [
"http://ae-pic-a1.aliexpress-media.com/kf/UT8NVOIXRhXXXagOFbX2.jpg_220x220.jpg_.avif"
],
"up_vote_count": 0,
"down_vote_count": null,
"is_anonymous": false,
"additional_text": null,
"additional_at_text": null,
"additional_images": [],
"labels": []
}
],
"proxy_traffic_bytes": 2254950,
"debug": null
},
"total_points": 1
}How to run it
The same lookup works from the app, the API, or as a tool an agent can call mid-task.
product accepts either an AliExpress product ID or URL. filter narrows to all/image/additional/local, and translate (default true) machine-translates review text — set it to false if you want the original language.
curl -X POST https://api.neuralverge.ai/functions/v1/run-aliexpress-product-reviews \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "product": "1005012791281455", "max_items": 10, "filter": "image" }'What teams use it for
Where this field shows up in an actual workflow.
Check recent buyer reviews before sourcing a product to resell.
Watch review volume and rating for a product you already sell.
Filter to image reviews to see what buyers actually received.
Read non-English reviews in translation without a manual lookup per review.
Coverage, freshness and limits
What this source covers, how fresh it is, and where it stops.
AliExpress products with a public reviews section.
Read at request time.
This source returns publicly visible review content, stamped with the product ID or URL it was read from and a session id you can trace.
- —Reviews are self-selected and skew towards strong opinions in both directions.
- —Machine translation can miss nuance, particularly for idioms or product-specific terms.
- —New or low-volume listings return few or no reviews.
Questions, answered
Yes — translate defaults to true, since a large share of AliExpress reviews aren't written in English. Set it to false to get the original text instead.
Related sources
Try aliexpress product reviews on your own data
One request format across every source in the catalog.