Developers can now add live data from Google Maps to the output of Gemini-based AI apps

Google is adding a new feature for third-party developers building on its Gemini AI models that competitors like OpenAI’s ChatGPT, Anthropic’s Claude and the growing selection of Chinese open source options are unlikely to get 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, allowing applications to provide detailed, location-relevant answers to user queries – such as business hours, ratings, or the atmosphere of a particular venue.

By leveraging data from over 250 million locations, developers can now create smarter and more responsive location-based experiences.

This is particularly useful for applications where proximity, real-time availability, or location-specific personalization are important – such as: B. local search, delivery services, real estate and travel planning.

If the user’s location is known, developers can enter latitude and longitude in the request to improve the quality of the response.

By tightly integrating real-time and historical map data with the Gemini API, Google enables applications to generate informed, location-specific answers with the factual accuracy and contextual depth only possible through its mapping infrastructure.

Merging AI and geointelligence

The new feature can be accessed in Google AI Studio, where developers can test a live demo based on 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 demonstrationone user asked for recommendations for Italian restaurants in Chicago.

Using map data, the assistant retrieved the top-rated options and clarified a misspelled restaurant name before finding the correct venue with accurate business details.

Developers can also obtain a context token to embed a Google Maps widget in their app’s UI. This interactive component displays photos, reviews, and other familiar content typically found on Google Maps.

The integration takes place via the generateContent Method in Gemini API where developers include googleMaps as a tool. You can also enable a map 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.

Cross-industry use cases

The Maps grounding tool is designed to support a variety of practical use cases:

• Itinerary creation: Travel apps can create detailed daily plans with route, time and venue information.

• Personalized local recommendations: Real estate platforms can highlight listings near child-friendly amenities like schools and parks.

• Detailed location queries: Using community reviews and Maps metadata, applications can provide specific information, such as whether a cafe offers outdoor seating.

Developers are recommended to enable the tool only when geographic context is relevant to optimize both performance and cost.

According to the developer documentation, pricing starts at $25 per 1,000 prompts – a hefty sum for those who make numerous requests.

Combining search and maps for expanded context

Developers can use grounding with Google Maps along with grounding with Google Search in the same query.

While the map tool contributes factual data such as addresses, opening times and reviews, 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 tests show that using both tools together leads to significantly improved response quality.

Unfortunately, it doesn’t appear that Google Maps grounding data includes live vehicle traffic data – at least not yet.

Customization and developer flexibility

The experience is customizable. Developers can optimize system prompts, choose from different Gemini models, and configure voice settings to customize interactions.

The demo app in Google AI Studio is also remixable, allowing developers to test ideas, add features, and iterate designs in a flexible development environment.

The API returns structured metadata—including source links, location IDs, and citation ranges—that developers can use to create inline citations or review AI-generated output.

This promotes transparency and increases trust in user-centric applications. Google also requires that Maps-based sources be uniquely attributed and linked to the source via their URI.

Implementation considerations for AI builders

For technical teams integrating this feature, Google recommends:

• Sharing the user’s location context, if known, to provide better results.

• Display Google Maps source links directly below relevant content.

• Only enable the tool if the query clearly involves a geographic context.

• Monitor latency and disable grounding when performance is critical.

Landing using Google Maps is currently available worldwide, but is banned in several territories (including China, Iran, North Korea and Cuba) and is not permitted for emergency operations.

Availability and access

Grounding with Google Maps is now generally available via the Gemini API.

With this release, Google further expands the capabilities of the Gemini API, enabling developers to build AI-driven applications that understand and respond to the world around them.