Documentation

Everything you need to integrate Clusteva

This is the Clusteva developer documentation. Start with the quickstart to go from API key to your first categorisation response, then use the reference sections to understand the full request and response surface.

Get started API reference →

Quickstart

Four steps to your first categorisation

Create an account

Create account →

Copy your API key

Find your key in the dashboard under Settings › API keys. Treat it as a secret; it authenticates every request.

Open dashboard →

Send a categorisation request

POST to /v1/categorise with a product_name. One product per request - the response comes back in the same call.

See example →

Handle the structured response

The response contains a full category path, a Google taxonomy ID, and a calibrated confidence score. Wire it into your pipeline.

Response format →

Example

Request and response

POST /v1/categorize

curl -X POST https://api.clusteva.com/v1/categorize \
  -H "Authorization: Bearer $CLUSTEVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "product_name": "14-inch Non-Stick Wok with Lid, Hard Anodised"
  }'

200 OK

{
  "category": "Home & Garden > Kitchen & Dining > Cookware & Bakeware > Cookware > Woks",
  "taxonomy_id": "google_664",
  "confidence": 0.98
}

Also available as POST /v1/categorise - identical behaviour, British spelling alias.

Reference

Documentation areas

Quickstart

From API key to first successful categorisation response in a few minutes.

Authentication

Bearer token authentication over HTTPS. Key scopes, rotation, and best practices.

Categorisation requests

Request shape, required fields, validation behaviour, and response structure.

Response format

Schema reference for category, taxonomy_id, and confidence fields.

Errors & rate limits

Status codes, error objects, retry strategies, and plan-based rate limits.

Examples & SDKs

curl, Python, Node.js, and community-maintained SDK links.

Concepts

How Clusteva works

Input

Send a product_name string - a raw product title, catalogue description, or any plain-text identifier. No preprocessing or normalisation required.

Resolution

Clusteva evaluates the input against the full Google product taxonomy (5,500+ categories) and selects the most precise applicable node.

Output

Receive a category path, its canonical Google taxonomy ID, and a confidence score between 0 and 1 indicating classification certainty.

Clusteva handles taxonomy maintenance on its side. When Google updates its product taxonomy, Clusteva absorbs those changes without any action required from your integration.

Get access

Ready to integrate?

Create an account to get API access and start sending categorisation requests. One endpoint, predictable output.

Get API access View pricing