Use a context cache

from google import genai
from google.genai.types import GenerateContentConfig, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
# Use content cache to generate text response
# E.g cache_name = 'projects/.../locations/.../cachedContents/1111111111111111111'
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Summarize the pdfs",
    config=GenerateContentConfig(
        cached_content=cache_name,
    ),
)
print(response.text)
# Example response
#   The Gemini family of multimodal models from Google DeepMind demonstrates remarkable capabilities across various
#   modalities, including image, audio, video, and text....

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// useContentCacheWithTxt shows how to use content cache to generate text content.
func useContentCacheWithTxt(w io.Writer, cacheName string) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	resp, err := client.Models.GenerateContent(ctx,
		"gemini-2.5-flash",
		genai.Text("Summarize the pdfs"),
		&genai.GenerateContentConfig{
			CachedContent: cacheName,
		},
	)
	if err != nil {
		return fmt.Errorf("failed to use content cache to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// The provided research paper introduces Gemini 1.5 Pro, a multimodal model capable of recalling
	// and reasoning over information from very long contexts (up to 10 million tokens).  Key findings include:
	//
	// * **Long Context Performance:**
	// ...

	return nil
}

import com.google.genai.Client;
import com.google.genai.types.GenerateContentConfig;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;

public class ContentCacheUseWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    // E.g cacheName = "projects/111111111111/locations/global/cachedContents/1111111111111111111"
    String cacheName = "your-cache-name";
    contentCacheUseWithText(modelId, cacheName);
  }

  // Shows how to generate text using cached content
  public static String contentCacheUseWithText(String modelId, String cacheName) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              "Summarize the pdfs",
              GenerateContentConfig.builder().cachedContent(cacheName).build());

      System.out.println(response.text());
      // Example response
      // The Gemini family of multimodal models from Google DeepMind demonstrates remarkable
      // capabilities across various
      // modalities, including image, audio, video, and text....
      return response.text();
    }
  }
}

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function useContentCache(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION,
  cacheName = 'example-cache'
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
    httpOptions: {
      apiVersion: 'v1',
    },
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'Summarize the pdfs',
    config: {
      cachedContent: cacheName,
    },
  });

  console.log(response.text);

  return response.text;
}
// Example response
//    The Gemini family of multimodal models from Google DeepMind demonstrates remarkable capabilities across various
//    modalities, including image, audio, video, and text....