Google is adding a new feature for third-party developers to build on top of its Gemini AI model that rivals like Openai’s ChatGupt, Anthropic’s Cloud, and a growing array of Chinese open-source options aren’t likely to get anytime soon. Grounding with Google Maps.
This addition allows developers to integrate the reasoning capabilities of Google’s Gemini AI models with geospatial data directly from Google Maps, enabling the delivery of detailed, location-specific responses to user queries—such as business hours, reviews, or the environment of a specific location.
By tapping data from more than 250 million locations, developers can now create more intelligent and responsive location-aware experiences.
This is particularly useful for applications where proximity, real-time availability, or location-related personalization matter—such as local search, delivery services, real estate, and travel planning.
When the user’s location is known, developers can transmit the latitude and longitude in the application to increase the quality of the response.
By tightly integrating real-time and historical mapping data into the Gemini API, Google enables applications to generate reality-based, location-specific responses with the depth of accuracy and context that is uniquely possible through its mapping infrastructure.
Integrating AI and Geospatial Intelligence
The new feature is accessible in Google AI Studio, where developers can try live demos 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 Flashlight
Gemini 2.0 Flash
In one Demonstrationa user asked for Italian restaurant recommendations in Chicago.
The assistant, leveraging maps data, retrieves advanced options and clears up misunderstood restaurant names before locating the correct location with the correct business details.
Developers can also retrieve context to embed a Google Maps widget into their app’s user interface. This interactive component displays photos, reviews, and other familiar content typically found in Google Maps.
is handled by integration generateContent method in the Gemini API, where developers include googleMaps as a tool. They can also enable the Maps widget by setting a parameter in the application. The widget, rendered using the returned context token, can provide AI-infilled text as well as a visual layer.
Use cases in industries
The Maps grounding tool is designed to support a wide range of practical uses:
Generation of Travel: Travel apps can create detailed daily plans with routing, timing and venue information.
Personalized Local Recommendations: Real estate platforms can highlight listings near kid-friendly amenities like schools and parks.
Detailed Location Questions: Applications can provide specific information, such as whether a cafe offers outdoor seating, community reviews and maps using metadata.
Developers are encouraged to enable this tool when it comes to geographic context, to improve both performance and cost.
According to developer documentation, pricing starts at $25 per 1,000 ground prompts — a steep sum for trafficking in multiple queries.
Combining search and maps for better context
Developers can use Grounding with Google Search as well as Grounding with Google Maps in the same application.
While the Maps tool contributes factual data — such as addresses, times, and rankings — the Search tool adds context to broader web content, such as news or event listings.
For example, when asked about live music on Beale Street, shared tools provide venue details from searches from maps and event times.
According to Google, internal testing shows that using both tools together significantly improves response quality.
Customization and developer flexibility
The experience is customized. Developers can customize the system’s gestures, choose from different Gemini models, and tailor voice settings to tailor interactions.
A demo app is also available 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, place identifiers, and reference periods—that developers can use to build inline references or verify AI-infill output.
It supports transparency and enhances trust in user-facing applications. Google also requires that sources based on maps be clearly attributed and linked back to the source using their URI.
Implementation Considerations for AI Builders
For technical teams integrating this capability, Google recommends:
For better results, passing the context of the user’s location when known.
Displaying Google Maps source links directly below related content.
Only activate this tool when the query explicitly includes geographic context.
Monitoring delay and passive grounding when performance is critical.
Grounding with Google Maps is currently available globally, although prohibited in several regions (including China, Iran, North Korea, and Cuba), and not permitted 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 build AI-driven applications that understand and respond to the world around them.