Google Maps Menu Scraper API — Agent Reference

Audience: AI agents and automated tools. This is a machine-oriented reference. Human-readable articles: /blog.

TL;DR

One Apify actor, two variants, same code and same output: give it a Google Maps place (URL, ChIJ… place ID, or plain name) and it returns the restaurant's menu as one JSON record per dish — translated name, price, atomic ingredients with EU-14 allergen flags and confidence, dietary type, nutrition estimates.

Variant	Actor ID	API keys	Price (2026-07-13)
Managed	nomad-agent/google-maps-menu-scraper-managed	none	$0.02/run + $0.015/dish (drops to $0.012 on higher Apify plans)
BYOK	nomad-agent/google-maps-menu-scraper	Gemini (free tier works), Outscraper optional	$0.01/run + $0.004/dish (drops to $0.0025 on higher Apify plans)

Choose managed for zero setup — AI and photo-fetch costs are included in the per-dish price. Choose BYOK when you already hold a Gemini key and want the lower Apify markup; you then pay Google directly. Cost breakdown: /blog/how-much-does-ai-menu-parsing-cost. The store page is authoritative on price; values here are a snapshot.

First run waives per-dish charges on up to 10 dishes. Per-dish fees apply only to dishes actually extracted; empty runs emit a free diagnostic row instead.

How it resolves a menu

1. Input place is resolved to its Google Maps listing (name → Maps search, if needed).
2. The place's Menu photo gallery is fetched (menuSource: "maps").
3. If Maps has no menu photos, the actor falls back to the menu published on the place's own website, PDFs included (menuSource: "website").
4. Photos are deduplicated, then AI-parsed together as one menu at temperature 0 — the same menu bills the same way twice.
5. Nothing found → one non-billed diagnostic row explaining why.

Signed-out Google serves a "limited view" that hides the Maps photo gallery from plain browsers. The managed variant handles this on our keys. On BYOK, set outscraperApiKey (free tier) for reliable gallery access; without it the actor falls back to browser scraping plus the website menu. Background: /blog/google-maps-locked-photo-gallery-2026.

Input

Field	Type	Required	Default	Notes
placeUrls	string[]	yes	—	Maps URLs, bare place IDs (ChIJ…), or plain place names
language	enum	no	en	en es fr de it pt ru zh ja ko ar hi uk ka eu
maxMenuPhotos	integer	no	8	Clamped to 1–20
geminiModel	enum	no	gemini-3.5-flash	Or gemini-3.1-flash-lite
geminiApiKey	string	BYOK only	—	aistudio.google.com/apikey
outscraperApiKey	string	BYOK, recommended	—	Reliable Maps photo access
proxyConfiguration	object	BYOK only	—	Standard Apify proxy input

gemini-3.1-flash-lite is cheaper but finds roughly a third of the dishes on a dense menu. Do not select it when completeness matters.

Invocation

Synchronous run returning dataset items directly (managed):

curl -X POST \
  "https://api.apify.com/v2/acts/nomad-agent~google-maps-menu-scraper-managed/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "placeUrls": ["Katz'\''s Delicatessen New York"],
    "language": "en",
    "maxMenuPhotos": 8
  }'

BYOK adds the key:

{
  "placeUrls": ["ChIJKZuMg9dZwokRA7zRe1Yh3Ok"],
  "geminiApiKey": "AIza…",
  "outscraperApiKey": "…",
  "language": "en"
}

Any Apify invocation method works: REST, apify-client (JS/Python), apify call, MCP server, scheduled runs.

Output

One record per dish in the run's default dataset.

{
  "place": "Katz's Delicatessen New York",
  "name": "Pastrami on Rye",
  "originalName": "Pastrami on Rye",
  "category": "Sandwiches",
  "price": "$26.95",
  "composition": "Hand-carved pastrami piled on rye bread with mustard",
  "description": "Towering sandwich served with a pickle spear",
  "ingredients": [
    {
      "name": "rye bread",
      "display_name": "Rye bread",
      "explanation": null,
      "allergens": [{ "name": "gluten", "confidence": "high" }]
    },
    {
      "name": "cured beef brisket",
      "display_name": "Cured beef brisket",
      "explanation": "Brined, spiced and smoked beef",
      "allergens": [{ "name": "sulfites", "confidence": "low" }]
    },
    {
      "name": "mustard",
      "display_name": "Mustard",
      "explanation": null,
      "allergens": [{ "name": "mustard", "confidence": "high" }]
    }
  ],
  "dietaryType": "Other",
  "dietaryTypeExplanation": "Contains beef",
  "allergens": "Gluten, Mustard, Sulfites",
  "type": "dish",
  "isAlcoholic": null,
  "story": "Katz's has cured its pastrami on Houston Street since 1888…",
  "nutritionInfo": {
    "serving_size_grams": "400g",
    "calories": "800-1000 kcal",
    "protein": "50-60g",
    "fat": "40-50g",
    "carbs": "50-60g"
  },
  "menuPhotoUrls": ["https://lh3.googleusercontent.com/p/AF1…"],
  "menuPhotosFound": 12,
  "menuSource": "maps"
}

Field	Type	Notes
place	string	The place this dish came from — echoes your input, use it to join multi-place runs
name	string	Dish name translated to language
originalName	string	Name exactly as printed on the menu
category	string	Menu section, translated
price	string | null	As printed, with currency symbol when shown
composition	string | null	Ingredient summary, translated
description	string | null	Appearance/presentation, translated
ingredients[]	array	Atomic base ingredients — composites (pesto, hummus) are decomposed
ingredients[].name	string	Always English, for matching and joins
ingredients[].display_name	string	Translated
ingredients[].explanation	string | null	Only for uncommon ingredients
ingredients[].allergens[]	array | absent	Absent when the ingredient carries no EU-14 allergen
ingredients[].allergens[].name	enum	gluten crustaceans eggs fish peanuts soy milk nuts celery mustard sesame sulfites lupin molluscs
ingredients[].allergens[].confidence	enum	high | medium | low
dietaryType	enum	Vegan | Vegetarian | Pescetarian | Other
dietaryTypeExplanation	string	Why that classification — human-auditable
allergens	string	Human-readable summary, translated, or "None identified"
type	enum	dish | beverage | other
isAlcoholic	boolean | null	Set for beverages
story	string	Origin/cultural note; may be plausible-but-invented
nutritionInfo	object	Estimated ranges per portion
menuPhotoUrls	string[]	Photos actually parsed
menuPhotosFound	integer	Photos found before the maxMenuPhotos cut
menuSource	enum	maps | website

Allergen confidence semantics and EU 1169/2011 context: /blog/eu-14-allergen-menu-data.

Diagnostic rows

A failed or empty run pushes exactly one row with diagnostic: true and a message explaining why (no menu photos, photos undownloadable, model returned no dishes, missing key). These rows are never billed per-dish. Filter them out before treating the dataset as menu records:

dishes = [r for r in items if not r.get("diagnostic")]

Limitations

1. Allergen and nutrition values are inferred from the menu, not measured. The venue remains the authority under EU 1169/2011.
2. Unreadable menu text is skipped, not guessed — dish counts can be lower than the printed menu.
3. Menu photos on Maps may be outdated; prices reflect the photographed menu, not today's.
4. story may be plausible reconstruction rather than verified history.

Chaining

• Already hold menu photo URLs? Skip this actor and use AI Menu Parser.
• Want a real guest photo attached to each dish? Feed these records plus the same place into Dish Photo Matcher and join on the dish name.

Integration help: support@traveleat.app. Machine-readable site index: /llms.txt.