Google is adding a new feature for third-party developers to build its Gemini AI models, which rivals like OpenAI’s ChatGPT, Anthropic’s Cloud, and a growing range of Chinese open source alternatives aren’t likely to get any time soon: Grounding with Google Maps.
This addition allows developers to combine the reasoning capabilities of Google’s Gemini AI models with live geospatial data from Google Maps, enabling apps to deliver detailed, location-relevant responses to user queries – such as business hours, reviews or the atmosphere of a specific location.
By harnessing data from over 250 million locations, developers can now create more intelligent and responsive location-aware experiences.
This is especially useful for applications where proximity, real-time availability, or location-specific personalization matters – such as local search, delivery services, real estate, and travel planning.
When the user’s location is known, developers can pass latitude and longitude in the request to increase response quality.
By tightly integrating real-time and historical map data into the Gemini API, Google enables applications to generate grounded, location-specific responses with the factual accuracy and contextual depth that are uniquely possible through its mapping infrastructure.
Merging AI and Geospatial Intelligence
The new feature is available in Google AI Studio, where developers can try out a live demo powered by the Gemini Live API. Models that support Grounding with Google Maps include:
-
gemini 2.5 pro
-
gemini 2.5 flash
-
Gemini 2.5 Flash-Lite
-
gemini 2.0 flash
in one DisplayA user asked for recommendations for Italian restaurants in Chicago.
Leveraging Maps data, the assistant retrieved top-rated options and clarified misspelled restaurant names before locating the correct location with accurate business details.
Developers can also retrieve a context token to embed a Google Maps widget in their app’s user interface. This interactive component displays photos, reviews, and other familiar content typically found in Google Maps.
Integration is controlled through generateContent Method in Gemini API, where developers are involved googleMaps As a tool. They can also enable the Maps widget by setting a parameter in the request. A widget, rendered using the returned context token, can provide a visual layer with AI-generated text.
Use cases across all industries
The Maps Grounding tool is designed to support a wide range of practical use cases:
-
Itinerary Generation: Travel apps can create detailed daily plans with route, time, and location information.
-
Personalized local recommendations: Real estate platforms can highlight listings near kid-friendly amenities like schools and parks.
-
Detailed location questions: Apps can provide specific information using community reviews and map metadata, such as whether a café offers outdoor seating.
Developers are encouraged to enable the tool only when the geographic context is relevant, to optimize both performance and cost.
According to developer documentation, pricing starts at $25 per 1,000 grounded prompts – a hefty sum for someone trafficking multiple queries.
Combination of search and maps for advanced reference
Developers can use grounding with Google Search as well as grounding with Google Maps in a single request.
While the Maps tool contributes factual data such as addresses, hours and ratings, the Search tool adds broader context from web content, such as news or event listings.
For example, when asked about live music on Beale Street, the combined tools provide venue details from Maps and event times from Search.
According to Google, internal testing shows that using both tools together significantly improves response quality.
Unfortunately, it doesn’t appear that Google Maps grounding includes live vehicle traffic data – at least not yet.
Customization and developer flexibility
The experience is designed for customization. Developers can make changes to system prompts, choose from different Gemini models, and configure voice settings to customize conversations.
Demo apps are also remixable in Google AI Studio, enabling developers to test ideas, add features, and iterate on designs in a flexible development environment.
The API returns structured metadata – including source links, location IDs, and citation spans – that developers can use to create inline citations or verify AI-generated output.
It supports transparency and increases trust in user-facing applications. Google also requires that maps-based sources be clearly attributed and linked back to the source using their URI.
Implementation Considerations for AI Builders
For technical teams looking to integrate this capability, Google recommends:
-
Passing user location context when known for better results.
-
Displaying Google Maps source link right below relevant content.
-
Enabling the tool only when the query explicitly includes geographic context.
-
Monitoring latency and disabling grounding when performance is critical.
Grounding with Google Maps is currently available globally, although restricted in several regions (including China, Iran, North Korea, and Cuba), and is not allowed for emergency response use cases.
Availability and accessibility
Grounding with Google Maps is now generally available through the Gemini API.
With this release, Google continues to expand the capabilities of the Gemini API, empowering developers to create AI-powered applications that understand and respond to the world around them.
