AI credits

AI Food Analysis

One call turns a product's raw data into something you can show a user: a plain-language summary, factual health highlights and warnings, diet compatibility (vegan, vegetarian, gluten-free, lactose-free), and a NOVA-style processing level — in six languages, grounded strictly in the product's label data.

Get API key Go to Dashboard View docs See it on a product Analyze your own data

200 OK

POST /v1/analyze/product

curl -X POST -H "X-API-Key: food_•••" \
  -H "Content-Type: application/json" \
  -d '{"barcode":"8000500082379","lang":"en"}' \
  "https://foodbase.dev/v1/analyze/product"

{
  "analysis": {
    "summary": "Nutella is a chocolate hazelnut
      spread... 533 kcal per 100g.",
    "highlights": ["Contains 13% hazelnuts"],
    "warnings": [
      "High in sugar (56.3g per 100g)",
      "Contains milk and tree nuts"
    ],
    "diets": { "vegan": "no", "vegetarian": "yes" },
    "processing_level": "ultra_processed"
  },
  "cached": false
}

Prefer to click around? Try the product explorer or the photo playground.

What you get back

`summary`

2–3 plain sentences describing the product and its nutritional character.

`highlights / warnings`

Short, factual points grounded in the label data — never invented.

`diets`

vegan / vegetarian / gluten_free / lactose_free — yes, no, or unknown.

`processing_level`

NOVA-style judgement from the ingredients list.

`lang`

en, fr, es, de, it, or bg — the analysis is written in the requested language.

`cached`

Each product+language is generated once, then served instantly. 1 credit per call.

Available on every plan through monthly AI credits — each call has a fixed credit price, and every plan (including Free) comes with a credit allowance. See plans →

Build with it

Product detail screens

Show shoppers an instant, readable verdict next to the raw numbers.

Diet filters that explain themselves

Vegan or gluten-free flags with the reasoning behind them.

Health & coaching apps

Turn scans into guidance-ready text without building your own LLM pipeline.

Explore more endpoints

Food Image Recognition

Turn a photo into food data. Four vision endpoints cover the whole camera flow: decode a barcode, identify a product from its front, read the nutrition label and ingredients, or analyze a plate of food with portion estimates — matched against 6.1M products, in six languages including Cyrillic.

Learn more →

Nutrition data

Go beyond the headline macros. Pull a detailed breakdown of 40+ nutrients per product — energy, protein, carbs, fats, sugars, fiber, sodium, vitamins, and minerals — all per 100g, for any food by ID.

Learn more →

Food Database

A single source for 6.1 million foods. Fetch a complete product record by ID — name, brand, ingredients, allergens, Nutri-Score, NOVA group, images, and more.

Learn more →

Start building with the AI Food Analysis API

Free to start. No credit card required.

Get API key Go to Dashboard