\n
![](\"https:\/\/images.ctfassets.net\/jdtwqhzvc2n1\/2ehvkDsQ7NC7wQuECOcDGS\/cb89da9ccaf13f2888f005ac93cecffa\/cfr0z3n_realistic_graphic_novel_hyper_detailed_flat_illustratio_8aae43d5-1e50-4ebd-8760-ea28dbc0f328.png\")
<\/p>\n
\n<\/p>\n
Google is adding a new feature for third-party developers building atop its Gemini AI models that rivals like OpenAI's ChatGPT, Anthropic's Claude, and the growing array of Chinese open source options are unlikely to get anytime soon: grounding with Google Maps.<\/p>\n
This addition allows developers to connect Google's Gemini AI models' reasoning capabilities with live geospatial data from Google Maps, enabling applications to deliver detailed, location-relevant responses to user queries\u2014such as business hours, reviews, or the atmosphere of a specific venue. <\/p>\n
By tapping into data from over 250 million places, developers can now build more intelligent and responsive location-aware experiences.<\/p>\n
This is particularly useful for applications where proximity, real-time availability, or location-specific personalization matter\u2014such as local search, delivery services, real estate, and travel planning. <\/p>\n
When the user\u2019s location is known, developers can pass latitude and longitude into the request to enhance the response quality.<\/p>\n
By tightly integrating real-time and historical Maps data into the Gemini API, Google enables applications to generate grounded, location-specific responses with factual accuracy and contextual depth that are uniquely possible through its mapping infrastructure.<\/p>\n
The new feature is accessible in Google AI Studio, where developers can try a live demo powered by the Gemini Live API. Models that support the grounding with Google Maps include:<\/p>\n
Gemini 2.5 Pro<\/p>\n<\/li>\n
Gemini 2.5 Flash<\/p>\n<\/li>\n
Gemini 2.5 Flash-Lite<\/p>\n<\/li>\n
Gemini 2.0 Flash<\/p>\n<\/li>\n<\/ul>\n
In one demonstration, a user asked for Italian restaurant recommendations in Chicago. <\/p>\n
The assistant, leveraging Maps data, retrieved top-rated options and clarified a misspelled restaurant name before locating the correct venue with accurate business details.<\/p>\n
Developers can also retrieve a context token to embed a Google Maps widget in their app\u2019s user interface. This interactive component displays photos, reviews, and other familiar content typically found in Google Maps.<\/p>\n
Integration is handled via the The Maps grounding tool is designed to support a wide range of practical use cases:<\/p>\n Itinerary generation:<\/b> Travel apps can create detailed daily plans with routing, timing, and venue information.<\/p>\n<\/li>\n Personalized local recommendations:<\/b> Real estate platforms can highlight listings near kid-friendly amenities like schools and parks.<\/p>\n<\/li>\n Detailed location queries:<\/b> Applications can provide specific information, such as whether a cafe offers outdoor seating, using community reviews and Maps metadata.<\/p>\n<\/li>\n<\/ul>\n Developers are encouraged to only enable the tool when geographic context is relevant, to optimize both performance and cost. <\/p>\n According to the developer documentation, pricing starts at $25 per 1,000 grounded prompts \u2014 a steep sum for those trafficking in numerous queries.<\/p>\n Developers can use Grounding with Google Maps alongside Grounding with Google Search in the same request.<\/p>\n While the Maps tool contributes factual data\u2014like addresses, hours, and ratings\u2014the Search tool adds broader context from web content, such as news or event listings.<\/p>\n For example, when asked about live music on Beale Street, the combined tools provide venue details from Maps and event times from Search. <\/p>\n According to Google, internal testing shows that using both tools together leads to significantly improved response quality.<\/p>\n Unfortunately, it doesn't appear that the Google Maps grounding includes live vehicular traffic data \u2014 at least not yet.<\/p>\n The experience is built for customization. Developers can tweak system prompts, choose from different Gemini models, and configure voice settings to tailor interactions.<\/p>\n The demo app in Google AI Studio is also remixable, enabling developers to test ideas, add features, and iterate on designs within a flexible development environment.<\/p>\n The API returns structured metadata\u2014including source links, place IDs, and citation spans\u2014that developers can use to build inline citations or verify the AI-generated outputs. <\/p>\n This supports transparency and enhances trust in user-facing applications. Google also requires that Maps-based sources be attributed clearly and linked back to the source using their URI.<\/p>\n For technical teams integrating this capability, Google recommends:<\/p>\n Passing user location context when known, for better results.<\/p>\n<\/li>\n Displaying Google Maps source links directly beneath the relevant content.<\/p>\n<\/li>\n Only enabling the tool when the query clearly involves geographic context.<\/p>\n<\/li>\n Monitoring latency and disabling grounding when performance is critical.<\/p>\n<\/li>\n<\/ul>\n Grounding with Google Maps is currently available globally, though prohibited in several territories (including China, Iran, North Korea, and Cuba), and not permitted for emergency response use cases.<\/p>\n Grounding with Google Maps is now generally available through the Gemini API. <\/p>\n 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.<\/p>\ngenerateContent<\/code> method in the Gemini API, where developers include googleMaps<\/code> as a tool. They can also enable a Maps widget by setting a parameter in the request. The widget, rendered using a returned context token, can provide a visual layer alongside the AI-generated text.<\/p>\nUse Cases Across Industries<\/b><\/h3>\n
\n
Combining Search and Maps for Enhanced Context<\/b><\/h3>\n
Customization and Developer Flexibility<\/b><\/h3>\n
Implementation Considerations for AI Builders<\/b><\/h3>\n
\n
Availability and Access<\/b><\/h3>\n