> ## AI Agent Context
> Get the complete documentation index at: https://aistudio.google.com/docs/llms.txt
> Use this file to discover all available pages.
> For the full documentation in a single file, fetch: https://aistudio.google.com/docs/llms-full.txt

# Grounding with Google Search

Grounding with Google Search connects the Gemini model to real-time web content
and works with all available languages. This allows
Gemini to provide more accurate answers and cite verifiable sources beyond its
knowledge cutoff.

Grounding helps you build applications that can:

*   **Increase factual accuracy:** Reduce model hallucinations by basing
  responses on real-world information.

*   **Access real-time information:** Answer questions about recent events and
  topics.

*   **Provide citations:** Build user trust by showing the sources for the
  model's claims.


{% tabs %}
  {% tab label="Python" %}
  ```python
  from google import genai
  
  client = genai.Client()
  
  interaction = client.interactions.create(
      model="gemini-3.8-flash",
      input="Who won the euro 2024?",
      tools=[{"type": "google_search"}]
  )
  
  print(interaction.output_text)
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```javascript
  import { GoogleGenAI } from "@google/genai";
  
  const client = new GoogleGenAI({});
  
  const interaction = await client.interactions.create({
      model: "gemini-3.8-flash",
      input: "Who won the euro 2024?",
      tools: [{ type: "google_search" }]
  });
  
  console.log(interaction.output_text);
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  import com.google.genai.Client;
  import com.google.genai.gaos.models.interactions.CreateModelInteraction;
  import com.google.genai.gaos.models.interactions.GoogleSearch;
  import com.google.genai.gaos.models.interactions.Interaction;
  import com.google.genai.gaos.models.interactions.InteractionsInput;
  import com.google.genai.gaos.models.interactions.Model;
  import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
  import java.util.Arrays;
  
  Client client = new Client();
  
  CreateModelInteraction params =
      CreateModelInteraction.builder()
          .model(Model.of("gemini-3.8-flash"))
          .input(InteractionsInput.of("Who won the euro 2024?"))
          .tools(Arrays.asList(GoogleSearch.builder().build()))
          .build();
  
  Interaction interaction =
      client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
  
  System.out.println(interaction.outputText().orElse(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(
              interactions.CreateModelInteraction{
                  Model: interactions.Model("gemini-3.8-flash"),
                  Input: interactions.NewInteractionsInput("Who won the euro 2024?"),
                  Tools: []interactions.Tool{
                      interactions.NewTool(interactions.GoogleSearch{}),
                  },
              },
          ),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      fmt.Println(resp.Interaction.GetOutputText())
  }
  ```

  {% /tab %}

  {% tab label="REST" %}
  ```shell
  curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -H "Api-Revision: 2026-05-20" \
    -d '{
      "model": "gemini-3.8-flash",
      "input": "Who won the euro 2024?",
      "tools": [{"type": "google_search"}]
    }'
  ```

  {% /tab %}

{% /tabs %}

## How grounding with Google Search works  {% id="how-it-works" %}

When you enable the `google_search` tool, the model handles the entire workflow
of searching, processing, and citing information automatically.

![](https://www.gstatic.com/cloud-cms/0c893db002557e538dbe4c9afe8f5abf.png)

1.   **User Prompt:** Your application sends a user's prompt to the Gemini API
  with the `google_search` tool enabled.

2.   **Prompt Analysis:** The model analyzes the prompt and determines if a
  Google Search can improve the answer.

3.   **Google Search:** If needed, the model automatically generates one or
  multiple search queries and executes them.

4.   **Search Results Processing:** The model processes the search results,
  synthesizes the information, and formulates a response.

5.   **Grounded Response:** The API returns a final, user-friendly response that
  is grounded in the search results. This response includes the model's text
  answer with inline `annotations` containing the citations, as well as
  `google_search_call` and `google_search_result` steps with the search
  queries and search suggestions.


## Understanding the grounding response  {% id="understanding-the-grounding-response" %}

When a response is successfully grounded, the model's text output includes
inline `annotations` directly on the text content block. These annotations
provide citation information linking parts of the response to their sources.

```json
{
  "steps": [
    {
      "type": "thought",
      "summary": [
        {
          "type": "text",
          "text": "The user is asking for the winner of Euro 2024. I need to search for the result of the Euro 2024 final."
        }
      ],
      "signature": "CoMDAXLI2nynRYojJIy6B1Jh9os2crpWLfB0..."
    },
    {
      "type": "google_search_call",
      "arguments": {
        "queries": ["UEFA Euro 2024 winner"]
      }
    },
    {
      "type": "google_search_result",
      "call_id": "search_001",
      "result": [
        {
          "search_suggestions": "<!-- HTML and CSS for the search widget -->"
        }
      ]
    },
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "Spain won Euro 2024, defeating England 2-1 in the final. This victory marks Spain's record fourth European Championship title.",
          "annotations": [
            {
              "type": "url_citation",
              "url": "https://www.aljazeera.com/sports/euro-2024-final",
              "title": "aljazeera.com",
              "start_index": 0,
              "end_index": 56
            },
            {
              "type": "url_citation",
              "url": "https://www.uefa.com/euro2024/news/spain-wins-euro-2024",
              "title": "uefa.com",
              "start_index": 57,
              "end_index": 124
            }
          ]
        }
      ]
    }
  ]
}
```

The key fields in the response:

*   `google_search_call` : Contains the search `queries` the model executed.

*   `google_search_result` : Contains `search_suggestions`, an HTML snippet
  for rendering search suggestions in your UI. Full usage requirements are
  detailed in the [Terms of Service](/docs/terms#grounding-with-google-search).

*   `text` with `annotations` : The model's synthesized answer with inline
  citations. Each `url_citation` annotation links a text segment (defined
  by `start_index` and `end_index`) to a source URL. This is the key to
  building inline citations.


Grounding with Google Search can also be used in combination with the [URL
context tool](/docs/url-context) to ground responses in
both public web data and the specific URLs you provide.

## Attributing sources with inline citations  {% id="attributing-sources-with-inline-citations" %}

The API returns inline `url_citation` annotations on the text content block,
giving you complete control over how you display sources in your user interface.
Each annotation includes `start_index` and `end_index` to identify which part
of the text it cites. Here's how to extract and display them.

{% tabs %}
  {% tab label="Python" %}
  ```python
  for step in interaction.steps:
      if step.type == "model_output":
          for content_block in step.content:
              if content_block.type == "text":
                  print(content_block.text)
                  if content_block.annotations:
                      print("\nCitations:")
                      for annotation in content_block.annotations:
                          if annotation.type == "url_citation":
                              cited_text = content_block.text[annotation.start_index:annotation.end_index]
                              print(f" [{annotation.title}]({annotation.url})")
                              print(f" Cited text: \"{cited_text}\"")
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```javascript
  for (const step of interaction.steps) {
    if (step.type === 'model_output') {
      for (const contentBlock of step.content || []) {
        if (contentBlock.type === 'text') {
          console.log(contentBlock.text);
          if (contentBlock.annotations) {
            console.log("\nCitations:");
            for (const annotation of contentBlock.annotations) {
              if (annotation.type === 'url_citation') {
                const citedText = contentBlock.text.slice(annotation.startIndex, annotation.endIndex);
                console.log(` [${annotation.title}](${annotation.url})`);
                console.log(` Cited text: "${citedText}"`);
              }
            }
          }
        }
      }
    }
  }
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  import com.google.genai.Client;
  import com.google.genai.gaos.models.interactions.Annotation;
  import com.google.genai.gaos.models.interactions.Content;
  import com.google.genai.gaos.models.interactions.CreateModelInteraction;
  import com.google.genai.gaos.models.interactions.GoogleSearch;
  import com.google.genai.gaos.models.interactions.Interaction;
  import com.google.genai.gaos.models.interactions.InteractionsInput;
  import com.google.genai.gaos.models.interactions.Model;
  import com.google.genai.gaos.models.interactions.ModelOutputStep;
  import com.google.genai.gaos.models.interactions.Step;
  import com.google.genai.gaos.models.interactions.TextContent;
  import com.google.genai.gaos.models.interactions.URLCitation;
  import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
  import java.util.Arrays;
  
  Client client = new Client();
  
  CreateModelInteraction params =
      CreateModelInteraction.builder()
          .model(Model.of("gemini-3.8-flash"))
          .input(InteractionsInput.of("Who won the euro 2024?"))
          .tools(Arrays.asList(GoogleSearch.builder().build()))
          .build();
  
  Interaction interaction =
      client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
  
  if (interaction.steps().isPresent()) {
    for (Step step : interaction.steps().get()) {
      if (step instanceof ModelOutputStep) {
        ModelOutputStep outputStep = (ModelOutputStep) step;
        if (outputStep.content().isPresent()) {
          for (Content contentBlock : outputStep.content().get()) {
            if (contentBlock instanceof TextContent) {
              TextContent textContent = (TextContent) contentBlock;
              String text = textContent.text().orElse("");
              System.out.println(text);
              if (textContent.annotations().isPresent()
                  && !textContent.annotations().get().isEmpty()) {
                System.out.println("\nCitations:");
                for (Annotation annotation : textContent.annotations().get()) {
                  if (annotation instanceof URLCitation) {
                    URLCitation citation = (URLCitation) annotation;
                    int start = citation.startIndex().orElse(0);
                    int end = citation.endIndex().orElse(0);
                    String citedText =
                        (start >= 0 && end <= text.length() && start <= end)
                            ? text.substring(start, end)
                            : "";
                    System.out.printf(
                        "  [%s](%s)%n", citation.title().orElse(""), citation.url().orElse(""));
                    System.out.printf("    Cited text: \"%s\"%n", citedText);
                  }
                }
              }
            }
          }
        }
      }
    }
  }
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(
              interactions.CreateModelInteraction{
                  Model: interactions.Model("gemini-3.8-flash"),
                  Input: interactions.NewInteractionsInput("Who won the euro 2024?"),
                  Tools: []interactions.Tool{
                      interactions.NewTool(interactions.GoogleSearch{}),
                  },
              },
          ),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      for _, step := range resp.Interaction.Steps {
          if step.ModelOutputStep != nil {
              for _, content := range step.ModelOutputStep.Content {
                  if content.TextContent != nil {
                      text := content.TextContent.Text
                      fmt.Println(text)
                      if len(content.TextContent.Annotations) > 0 {
                          fmt.Println("\nCitations:")
                          for _, annotation := range content.TextContent.Annotations {
                              if annotation.URLCitation != nil {
                                  c := annotation.URLCitation
                                  start := 0
                                  if c.StartIndex != nil {
                                      start = *c.StartIndex
                                  }
                                  end := 0
                                  if c.EndIndex != nil {
                                      end = *c.EndIndex
                                  }
                                  citedText := ""
                                  if start >= 0 && end <= len(text) && start <= end {
                                      citedText = text[start:end]
                                  }
                                  title := ""
                                  if c.Title != nil {
                                      title = *c.Title
                                  }
                                  url := ""
                                  if c.URL != nil {
                                      url = *c.URL
                                  }
                                  fmt.Printf("  [%s](%s)\n", title, url)
                                  fmt.Printf("    Cited text: %q\n", citedText)
                              }
                          }
                      }
                  }
              }
          }
      }
  }
  ```

  {% /tab %}

{% /tabs %}

The output will show the text followed by its citations:

```none
Spain won Euro 2024, defeating England 2-1 in the final. This victory marks Spain's record fourth European Championship title.

Citations:
  [aljazeera.com](https://www.aljazeera.com/sports/euro-2024-final)
    Cited text: "Spain won Euro 2024, defeating England 2-1 in the final."
  [uefa.com](https://www.uefa.com/euro2024/news/spain-wins-euro-2024)
    Cited text: "This victory marks Spain's record fourth European Championship title."
```

## Pricing  {% id="pricing" %}

When you use Grounding with Google Search with Gemini 3 and newer models, your
project is billed for **each** search query that the model decides to execute.
This per-query billing model includes 5,000 free search requests per month
shared across all Gemini 3 and newer models, and then costs **$14 per 1,000
search requests**.

For example, if the model decides to execute multiple search queries to answer
a single prompt (e.g. searching for `"UEFA Euro 2024 winner"` and `"Spain vs
England Euro 2024 final score"` within the same API call), this counts as two
billable uses of the tool for that request. For billing purposes, we ignore
empty web search queries when counting unique queries.

When you use search grounding with Gemini 2.5 or older models, your project is
billed per prompt.

For detailed pricing information, see the [Gemini API pricing
page](/docs/pricing).

{% callout type="note" %}
  **Note:** Grounding with Google Search has a default limit of **1,500 requests
  per day (RPD)** per project on Gemini 3 and newer models in the Paid Tier of the
  Gemini Developer API. If your application requires a higher daily limit, submit
  a request in [Google AI Studio](https://aistudio.google.com/rate-limit) (select
  **Request more quota** next to the `generate_content_search_request_paid` limit).

{% /callout %}

## Supported models  {% id="supported-models" %}

You can find full capabilities on the [model
overview](https://ai.google.dev/docs/models) page.

| Model | Grounding with Google Search |
| --- | :---: |
| Gemini 4 Argon | ✔️ |
| Gemini 3.8 Flash | ✔️ |
| Gemini 3.6 Flash | ✔️ |
| Gemini 3.5 Flash-Lite | ✔️ |
| Gemini 3.1 Flash Image Preview | ✔️ |
| Gemini 3.1 Pro Preview | ✔️ |
| Gemini 3 Pro Image Preview | ✔️ |
| Gemini 3 Flash Preview | ✔️ |
| Gemini 2.5 Pro | ✔️ |
| Gemini 2.5 Flash | ✔️ |
| Gemini 2.5 Flash-Lite | ✔️ |
| Gemini 2.0 Flash | ✔️ |

{% callout type="note" %}
  Older models use a `google_search_retrieval` tool. For all current models,
  use the `google_search` tool as shown in the examples.

{% /callout %}

## Supported tool combinations  {% id="tool-combination" %}

You can use Grounding with Google Search with other tools like
[code execution](/docs/code-execution),
[URL context](/docs/url-context), and
[Grounding with Google Maps](/docs/maps-grounding) (supported on Gemini 3.5
Flash and later models) to power more complex use cases. Gemini 3 models also
support combining these built-in tools with custom tools (function calling).
Learn more on the [tool combinations](/docs/tool-combination) page.

## What's next  {% id="whats-next" %}

* Learn about other available tools, like [Function Calling](/docs/function-calling).
* Learn how to augment prompts with specific URLs using the [URL context tool](/docs/url-context).