Gemini Google Maps

Use Google Maps via Gemini for places lookup and geocoding.

Overview

Gemini Google Maps sends a user query to the Gemini generateContent API with the google_maps tool enabled, allowing the model to perform places lookup, geocoding, directions, and other Maps-related queries. The model uses Google Maps data to ground its responses with real location information. Returns the generated text response along with model metadata and token usage.

Category: AI
Tool Name: gemini_google_maps
Version: 1

Appearance: Icon: gemini | Color: #ffffff

Node Type

Action — processes input items and produces output

Input / Output

Direction	Port(s)
Input	Input
Output	Output, Error

Credentials

This tool requires Google AI credentials. See the Credentials Guide for setup instructions.

Parameters

Parameter	Type	Required	Default	Description
Model	options	No	(current default)	The Gemini model to use for the maps query. Pick a specific version — labels are pinned, not aliased to “latest”.
				Options: the Gemini chat models available to your workspace — pick one from the dropdown.
System Prompt	string	No	—	Optional system instruction that sets the behavior and context for the model. Supports expressions.
User Message	string	Yes	—	The maps query to send to Gemini. Include location names, addresses, or coordinates. Falls back to item.message or item.prompt if empty. Supports expressions like {{ $json.address }}.
File URIs	string	No	—	Optional. fileUri value(s) from the Gemini File Upload tool. Pass a single URI or a JSON array for multiple files. Files are sent as multimodal context alongside the message. Falls back to item.fileUris if empty. Gemini File API retains uploads for 48 hours. Supports expressions.
Options	collection	No	{}	Optional generation and output settings — add only the fields you need.
— Temperature	number	No	1	Controls randomness. Lower values are more deterministic, higher values more creative. Range: 0-2.
— Max Output Tokens	number	No	8192	Maximum number of tokens in the generated response.
— Response Field Name	string	No	response	The key name in the output JSON where the generated text will be stored.
Include Input	boolean	No	false	Whether to merge the input item JSON into the output item.
Max Concurrency	number	No	10	Maximum number of items to process concurrently.

Output Data

One maps-grounded request per input item, and one output item per input item. The answer lands on the field named by Response Field Name (response by default), with model, finishReason and usage beside it. The rest of the input item JSON is dropped unless Include Input is on; binary data on the input item is forwarded unchanged.

{
  "response": "The location answer, grounded in Google Maps data",
  "model": "the model that produced the answer",
  "finishReason": "the API's reason for ending generation",
  "usage": { "promptTokenCount": 210, "candidatesTokenCount": 128 }
}

• The answer is free text, not a structured place record. When you need fields a downstream node can address — coordinates, a formatted address, a rating — ask for them explicitly in the System Prompt (for example, “reply with JSON only”) and parse the text afterwards.
• finishReason is the API’s own reason for ending generation — the field to check when an answer looks cut off against the Max Output Tokens cap.
• usage is the token accounting the API returned for that call.

Reference the result downstream by expression, e.g. {{ $json.response }}.

Usage Examples

• Find restaurants near a specific location
• Get directions between two addresses
• Geocode an address to latitude/longitude coordinates
• Search for nearby points of interest
• Look up business hours and ratings for a place

Example Configuration

Minimal — one location question per item:

{
  "type": "gemini_google_maps",
  "parameters": {
    "userMessage": "What are the coordinates of the Eiffel Tower in Paris?"
  }
}

Geocode deterministically and ask for a machine-readable answer:

{
  "type": "gemini_google_maps",
  "parameters": {
    "systemPrompt": "Return only valid JSON with the fields name, lat, lng and formattedAddress. No other text.",
    "userMessage": "Geocode: {{ $json.address }}",
    "includeInput": true,
    "maxConcurrency": 20,
    "options": {
      "temperature": 0,
      "maxOutputTokens": 256,
      "responseFieldName": "geocodeResult"
    }
  }
}

Nearby-places lookup with a descriptive answer:

{
  "type": "gemini_google_maps",
  "parameters": {
    "userMessage": "List 5 highly-rated Italian restaurants within 1 mile of {{ $json.landmark }}, with their addresses.",
    "options": {
      "temperature": 0.5,
      "maxOutputTokens": 1024,
      "responseFieldName": "nearbyPlaces"
    }
  }
}

Error Handling

Mode	Behavior
stop	Halts workflow on first error
continue	Skips failed items, passes successful ones through
errorPort	Routes failed items to Error output port

Tips

Gemini Google Maps sends a query to the Gemini generateContent API with the Google Maps tool enabled, performing places lookup, geocoding, and directions using real map data. Use this tool when a workflow needs to resolve addresses to coordinates, find nearby businesses, or answer location-based questions requiring live geographic grounding. It produces a generated text response with resolved location details, model metadata, and token usage on the main output.