Berpikir

Model pemikiran dilatih untuk menghasilkan "proses pemikiran" internal sebelum menghasilkan respons. Hasilnya, model pemikiran mampu melakukan penalaran yang lebih kuat, perencanaan multi-langkah, pemecahan masalah matematika, dan pembuatan kode yang lebih baik daripada model tanpa kemampuan pemikiran.

Proses penalaran diaktifkan secara default di seluruh model Gemini. Saat menggunakan Agent Studio di Gemini Enterprise Agent Platform, Anda dapat melihat seluruh proses pemikiran bersama dengan respons yang dihasilkan model.

Model yang didukung

Kemampuan berpikir didukung di model berikut:

Klik untuk meluaskan model yang didukung

Mengontrol pemikiran model

Anda dapat mengontrol jumlah pemikiran yang dilakukan model sebelum memberikan respons. Metode untuk mengontrol pemikiran berbeda-beda, bergantung pada versi model.

Model Gemini 3 dan yang lebih baru

Model Gemini 3 memperkenalkan parameter thinking_level, yang menyederhanakan konfigurasi anggaran penalaran ke dalam tingkat diskrit. Untuk respons yang lebih cepat dan latensi yang lebih rendah saat penalaran yang kompleks tidak diperlukan, Anda dapat membatasi thinking_level model.

Tabel berikut merangkum nilai thinking_level yang didukung oleh setiap model, dan thinking_level default untuk setiap model:

Model Nilai thinking_level yang didukung Default
Gemini 3.8 Flash LOW, MEDIUM, HIGH MEDIUM
Gemini 3.7 Flash LOW, MEDIUM, HIGH MEDIUM
Gemini 3.6 Flash MINIMAL, LOW, MEDIUM, HIGH MEDIUM
Gemini 3.5 Flash-Lite MINIMAL, LOW, MEDIUM, HIGH MINIMAL
Gemini 3.5 Flash MINIMAL, LOW, MEDIUM, HIGH MEDIUM
Gemini 3.1 Pro pratinjau LOW, MEDIUM, HIGH HIGH
Gambar Gemini 3.1 Flash-Lite (Nano Banana 2 Lite) MINIMAL, HIGH MINIMAL
Gemini 3.1 Flash-Lite MINIMAL, LOW, MEDIUM, HIGH MINIMAL
Gambar Gemini 3.1 Flash MINIMAL, HIGH MINIMAL
Gemini 3 Pro Image HIGH HIGH
Gemini 3 Flash pratinjau MINIMAL, LOW, MEDIUM, HIGH HIGH

  • MINIMAL: Membatasi model untuk menggunakan token sesedikit mungkin untuk berpikir dan paling baik digunakan untuk tugas dengan kompleksitas rendah yang tidak akan mendapatkan manfaat dari penalaran yang ekstensif. Ini adalah tingkat default untuk Gemini 3.1 Flash-Lite. MINIMAL sedekat mungkin dengan anggaran nol untuk berpikir, tetapi masih memerlukan tanda tangan pemikiran. Jika tanda tangan pemikiran tidak diberikan dalam permintaan Anda, model akan menampilkan error 400. Untuk mengetahui informasi selengkapnya, lihat Tanda tangan pemikiran.

    from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="How does AI work?",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_level=types.ThinkingLevel.MINIMAL
        )
    ),
)
print(response.text)

  • LOW: Membatasi model untuk menggunakan lebih sedikit token untuk penalaran dan cocok untuk tugas yang lebih sederhana yang tidak memerlukan penalaran ekstensif. LOW ideal untuk tugas dengan throughput tinggi yang membutuhkan kecepatan:

    from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="How does AI work?",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_level=types.ThinkingLevel.LOW
        )
    ),
)
print(response.text)

  • MEDIUM: Menawarkan pendekatan seimbang yang cocok untuk tugas dengan kompleksitas sedang yang memerlukan penalaran, tetapi tidak memerlukan perencanaan multi-langkah yang mendalam. Model ini memberikan kemampuan penalaran yang lebih baik daripada LOW sekaligus mempertahankan latensi yang lebih rendah daripada HIGH:

    from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3-flash-preview",
    contents="How does AI work?",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_level=types.ThinkingLevel.MEDIUM
        )
    ),
)
print(response.text)

  • HIGH: Memungkinkan model menggunakan lebih banyak token untuk berpikir dan cocok untuk perintah kompleks yang memerlukan penalaran mendalam, seperti perencanaan multi-langkah, pembuatan kode terverifikasi, atau skenario panggilan fungsi tingkat lanjut. Ini adalah tingkat default untuk model Gemini 3 Pro dan Gemini 3 Flash. Gunakan konfigurasi ini saat mengganti tugas yang mungkin sebelumnya Anda andalkan pada model penalaran khusus:

    from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Find the race condition in this multi-threaded C++ snippet: [code here]",
    config=types.GenerateContentConfig(
        thinking_config=types.ThinkingConfig(
            thinking_level=types.ThinkingLevel.HIGH
        )
    ),
)
print(response.text)

Penalaran tidak dapat dinonaktifkan untuk Gemini 3 Pro dan Gemini 3.1 Pro.

Jika Anda menentukan thinking_level dan thinking_budget dalam permintaan yang sama untuk model Gemini 3, model akan menampilkan error.

Model Gemini 2.5 dan yang lebih lama

Untuk model yang lebih lama dari Gemini 3, Anda dapat mengontrol proses penalaran menggunakan parameter thinking_budget, yang menetapkan batas atas jumlah token yang dapat digunakan model untuk proses berpikirnya. Secara default, jika thinking_budget tidak disetel, model akan otomatis mengontrol jumlah token yang digunakan hingga maksimum 8.192 token. Untuk menggunakan anggaran dinamis melalui API, tetapkan thinking_budget ke -1.

Anda dapat menyetel thinking_budget secara manual untuk menerapkan batas atas sementara pada jumlah token dalam situasi saat Anda mungkin memerlukan lebih banyak atau lebih sedikit token daripada anggaran pemikiran default. Anda dapat menyetel batas token yang lebih rendah untuk tugas yang kurang kompleks, atau batas yang lebih tinggi untuk tugas yang lebih kompleks. Perhatikan bahwa ini adalah batas lunak dan oleh karena itu dapat terjadi variabilitas dalam total token pemikiran. Jika latensi lebih penting, gunakan anggaran yang lebih rendah atau tetapkan anggaran ke 0 untuk mencegah konten pemikiran ditampilkan dengan respons.

Tabel berikut menunjukkan jumlah minimum dan maksimum yang dapat Anda tetapkan untuk thinking_budget untuk setiap model yang didukung, dan anggaran pemikiran default untuk setiap model:

Model Jumlah token minimum Jumlah token maksimum Default
Gemini 2.5 Flash 1 24.576 Otomatis (hingga 8.192 token)
Gemini 2.5 Pro 128 32.768 Otomatis (hingga 8.192 token)
Gemini 2.5 Flash-Lite 512 24.576 Otomatis (hingga 8.192 token)

Jika Anda menyetel thinking_budget ke 0 saat menggunakan Gemini 2.5 Flash dan Gemini 2.5 Flash-Lite, tidak ada konten pemikiran yang ditampilkan dengan respons. Namun, teks gaya penalaran mungkin masih ada dalam output model. Kemampuan berpikir tidak dapat dinonaktifkan untuk Gemini 2.5 Pro.

Jika Anda menggunakan parameter thinking_level dengan model yang lebih lama dari Gemini 3, model akan menampilkan error.

Konsol

  1. Buka Agent Studio > Buat perintah.
  2. Di panel Model, klik Ganti model, lalu pilih salah satu model yang didukung dari menu.
  3. Pilih Manual dari pemilih drop-down Anggaran berpikir, lalu gunakan penggeser untuk menyesuaikan batas anggaran berpikir.

Python

Instal

pip install --upgrade google-genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="solve x^2 + 4x + 4 = 0",
    config=GenerateContentConfig(
        thinking_config=ThinkingConfig(
            thinking_budget=1024,  # Use `0` to turn off thinking
        )
    ),
)

print(response.text)
# Example response:
#     To solve the equation $x^2 + 4x + 4 = 0$, you can use several methods:
#     **Method 1: Factoring**
#     1.  Look for two numbers that multiply to the constant term (4) and add up to the coefficient of the $x$ term (4).
#     2.  The numbers are 2 and 2 ($2 \times 2 = 4$ and $2 + 2 = 4$).
#     ...
#     ...
#     All three methods yield the same solution. This quadratic equation has exactly one distinct solution (a repeated root).
#     The solution is **x = -2**.

# Token count for `Thinking`
print(response.usage_metadata.thoughts_token_count)
# Example response:
#     886

# Total token count
print(response.usage_metadata.total_token_count)
# Example response:
#     1525

Node.js

Instal

npm install @google/genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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 generateWithThoughts(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'solve x^2 + 4x + 4 = 0',
    config: {
      thinkingConfig: {
        thinkingBudget: 1024,
      },
    },
  });

  console.log(response.text);
  // Example response:
  //  To solve the equation $x^2 + 4x + 4 = 0$, you can use several methods:
  //  **Method 1: Factoring**
  //  1.  Look for two numbers that multiply to the constant term (4) and add up to the coefficient of the $x$ term (4).
  //  2.  The numbers are 2 and 2 ($2 \times 2 = 4$ and $2 + 2 = 4$).
  //  ...
  //  ...
  //  All three methods yield the same solution. This quadratic equation has exactly one distinct solution (a repeated root).
  //  The solution is **x = -2**.

  // Token count for `Thinking`
  console.log(response.usageMetadata.thoughtsTokenCount);
  // Example response:
  //  886

  // Total token count
  console.log(response.usageMetadata.totalTokenCount);
  // Example response:
  //  1525
  return response.text;
}

Go

Pelajari cara menginstal atau mengupdate Go.

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

import (
	"context"
	"fmt"
	"io"

	"google.golang.org/genai"
)

// generateThinkingBudgetContentWithText demonstrates how to generate text including the model's thought process.
func generateThinkingBudgetContentWithText(w io.Writer) 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)
	}

	modelName := "gemini-2.5-flash"
	thinkingBudget := int32(1024) //Use `0` to turn off thinking
	contents := []*genai.Content{
		{
			Parts: []*genai.Part{
				{Text: "solve x^2 + 4x + 4 = 0"},
			},
			Role: "user",
		},
	}

	resp, err := client.Models.GenerateContent(ctx,
		modelName,
		contents,
		&genai.GenerateContentConfig{
			ThinkingConfig: &genai.ThinkingConfig{
				ThinkingBudget: &thinkingBudget,
			},
		},
	)
	if err != nil {
		return fmt.Errorf("generate content failed: %w", err)
	}

	if resp.UsageMetadata != nil {
		fmt.Fprintf(w, "Thoughts token count: %d\n", resp.UsageMetadata.ThoughtsTokenCount)
		//Example response:
		//  908
		fmt.Fprintf(w, "Total token count: %d\n", resp.UsageMetadata.TotalTokenCount)
		//Example response:
		//  1364
	}

	fmt.Fprintln(w, resp.Text())

	// Example response:
	//    To solve the equation $x^2 + 4x + 4 = 0$, you can use several methods:
	//    **Method 1: Factoring**
	//    1.  Look for two numbers that multiply to the constant term (4) and add up to the coefficient of the $x$ term (4).
	//    2.  The numbers are 2 and 2 ($2 \times 2 = 4$ and $2 + 2 = 4$).
	//    ...
	//    ...
	//    Both methods yield the same result.
	//    The solution to the equation $x^2 + 4x + 4 = 0$ is **$x = -2$**.

	return nil
}

Java

Pelajari cara menginstal atau mengupdate Java.

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 


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

public class ThinkingBudgetWithTxt {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text controlling the thinking budget
  public static String generateContent(String modelId) {
    // 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()) {

      GenerateContentConfig contentConfig =
          GenerateContentConfig.builder()
              .thinkingConfig(ThinkingConfig.builder().thinkingBudget(1024).build())
              .build();

      GenerateContentResponse response =
          client.models.generateContent(modelId, "solve x^2 + 4x + 4 = 0", contentConfig);

      System.out.println(response.text());
      // Example response:
      // To solve the equation $x^2 + 4x + 4 = 0$, we can use several methods:
      //
      // **Method 1: Factoring (Recognizing a Perfect Square Trinomial)**
      //
      // Notice that the left side of the equation is a perfect square trinomial. It fits the form
      // $a^2 + 2ab + b^2 = (a+b)^2$...
      // ...
      // The solution is $x = -2$.

      response
          .usageMetadata()
          .ifPresent(
              metadata -> {
                System.out.println("Token count for thinking: " + metadata.thoughtsTokenCount());
                System.out.println("Total token count: " + metadata.totalTokenCount());
              });
      // Example response:
      // Token count for thinking: Optional[885]
      // Total token count: Optional[1468]
      return response.text();
    }
  }
}

Melihat ringkasan pemikiran

Ringkasan pemikiran memberikan visibilitas ke dalam langkah-langkah penalaran menengah yang dilakukan model saat menghasilkan respons. Anda dapat melihat ringkasan pemikiran di model Gemini 2.5 dan yang lebih baru.

Di Agent Studio, ringkasan pemikiran diaktifkan secara default dan dapat dilihat dengan meluaskan panel Pemikiran.

Saat menggunakan API, Anda dapat mengaktifkan ringkasan pemikiran dengan menetapkan include_thoughts=True di ThinkingConfig:

Konsol

Ringkasan pemikiran diaktifkan secara default di Agent Studio. Anda dapat melihat ringkasan proses pemikiran model dengan meluaskan panel Pemikiran.

Python

Instal

pip install --upgrade google-genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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

client = genai.Client()
response = client.models.generate_content(
    model="gemini-3.1-pro-preview",
    contents="solve x^2 + 4x + 4 = 0",
    config=GenerateContentConfig(
        thinking_config=ThinkingConfig(include_thoughts=True)
    ),
)

print(response.text)
# Example Response:
#     Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
#     ...
#     **Answer:**
#     The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

for part in response.candidates[0].content.parts:
    if part and part.thought:  # show thoughts
        print(part.text)
# Example Response:
#     **My Thought Process for Solving the Quadratic Equation**
#
#     Alright, let's break down this quadratic, x² + 4x + 4 = 0. First things first:
#     it's a quadratic; the x² term gives it away, and we know the general form is
#     ax² + bx + c = 0.
#
#     So, let's identify the coefficients: a = 1, b = 4, and c = 4. Now, what's the
#     most efficient path to the solution? My gut tells me to try factoring; it's
#     often the fastest route if it works. If that fails, I'll default to the quadratic
#     formula, which is foolproof. Completing the square? It's good for deriving the
#     formula or when factoring is difficult, but not usually my first choice for
#     direct solving, but it can't hurt to keep it as an option.
#
#     Factoring, then. I need to find two numbers that multiply to 'c' (4) and add
#     up to 'b' (4). Let's see... 1 and 4 don't work (add up to 5). 2 and 2? Bingo!
#     They multiply to 4 and add up to 4. This means I can rewrite the equation as
#     (x + 2)(x + 2) = 0, or more concisely, (x + 2)² = 0. Solving for x is now
#     trivial: x + 2 = 0, thus x = -2.
#
#     Okay, just to be absolutely certain, I'll run the quadratic formula just to
#     double-check. x = [-b ± √(b² - 4ac)] / 2a. Plugging in the values, x = [-4 ±
#     √(4² - 4 * 1 * 4)] / (2 * 1). That simplifies to x = [-4 ± √0] / 2. So, x =
#     -2 again – a repeated root. Nice.
#
#     Now, let's check via completing the square. Starting from the same equation,
#     (x² + 4x) = -4. Take half of the b-value (4/2 = 2), square it (2² = 4), and
#     add it to both sides, so x² + 4x + 4 = -4 + 4. Which simplifies into (x + 2)²
#     = 0. The square root on both sides gives us x + 2 = 0, therefore x = -2, as
#      expected.
#
#     Always, *always* confirm! Let's substitute x = -2 back into the original
#     equation: (-2)² + 4(-2) + 4 = 0. That's 4 - 8 + 4 = 0. It checks out.
#
#     Conclusion: the solution is x = -2. Confirmed.

Node.js

Instal

npm install @google/genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

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 generateWithThoughts(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-pro',
    contents: 'solve x^2 + 4x + 4 = 0',
    config: {
      thinkingConfig: {
        includeThoughts: true,
      },
    },
  });

  console.log(response.text);
  // Example Response:
  //  Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
  //  ...
  //  **Answer:**
  //  The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

  for (const part of response.candidates[0].content.parts) {
    if (part && part.thought) {
      console.log(part.text);
    }
  }

  // Example Response:
  // **My Thought Process for Solving the Quadratic Equation**
  //
  // Alright, let's break down this quadratic, x² + 4x + 4 = 0. First things first:
  // it's a quadratic; the x² term gives it away, and we know the general form is
  // ax² + bx + c = 0.
  //
  // So, let's identify the coefficients: a = 1, b = 4, and c = 4. Now, what's the
  // most efficient path to the solution? My gut tells me to try factoring; it's
  // often the fastest route if it works. If that fails, I'll default to the quadratic
  // formula, which is foolproof. Completing the square? It's good for deriving the
  // formula or when factoring is difficult, but not usually my first choice for
  // direct solving, but it can't hurt to keep it as an option.
  //
  // Factoring, then. I need to find two numbers that multiply to 'c' (4) and add
  // up to 'b' (4). Let's see... 1 and 4 don't work (add up to 5). 2 and 2? Bingo!
  // They multiply to 4 and add up to 4. This means I can rewrite the equation as
  // (x + 2)(x + 2) = 0, or more concisely, (x + 2)² = 0. Solving for x is now
  // trivial: x + 2 = 0, thus x = -2.
  //
  // Okay, just to be absolutely certain, I'll run the quadratic formula just to
  // double-check. x = [-b ± √(b² - 4ac)] / 2a. Plugging in the values, x = [-4 ±
  // √(4² - 4 * 1 * 4)] / (2 * 1). That simplifies to x = [-4 ± √0] / 2. So, x =
  // -2 again – a repeated root. Nice.
  //
  // Now, let's check via completing the square. Starting from the same equation,
  // (x² + 4x) = -4. Take half of the b-value (4/2 = 2), square it (2² = 4), and
  // add it to both sides, so x² + 4x + 4 = -4 + 4. Which simplifies into (x + 2)²
  // = 0. The square root on both sides gives us x + 2 = 0, therefore x = -2, as
  //  expected.
  //
  // Always, *always* confirm! Let's substitute x = -2 back into the original
  // equation: (-2)² + 4(-2) + 4 = 0. That's 4 - 8 + 4 = 0. It checks out.
  //
  // Conclusion: the solution is x = -2. Confirmed.

  return response.text;
}

Go

Pelajari cara menginstal atau mengupdate Go.

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 

import (
	"context"
	"fmt"
	"io"

	"google.golang.org/genai"
)

// generateContentWithThoughts demonstrates how to generate text including the model's thought process.
func generateContentWithThoughts(w io.Writer) 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)
	}

	modelName := "gemini-2.5-pro"
	contents := []*genai.Content{
		{
			Parts: []*genai.Part{
				{Text: "solve x^2 + 4x + 4 = 0"},
			},
			Role: "user",
		},
	}

	resp, err := client.Models.GenerateContent(ctx,
		modelName,
		contents,
		&genai.GenerateContentConfig{
			ThinkingConfig: &genai.ThinkingConfig{
				IncludeThoughts: true,
			},
		},
	)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	if len(resp.Candidates) == 0 || resp.Candidates[0].Content == nil {
		return fmt.Errorf("no content was generated")
	}

	// The response may contain both the final answer and the model's thoughts.
	// Iterate through the parts to print them separately.
	fmt.Fprintln(w, "Answer:")
	for _, part := range resp.Candidates[0].Content.Parts {
		if part.Text != "" && !part.Thought {
			fmt.Fprintln(w, part.Text)
		}
	}
	fmt.Fprintln(w, "\nThoughts:")
	for _, part := range resp.Candidates[0].Content.Parts {
		if part.Thought {
			fmt.Fprintln(w, part.Text)
		}
	}

	// Example response:
	//  Answer:
	//	Of course! We can solve this quadratic equation in a couple of ways.
	//
	//### Method 1: Factoring (the easiest method for this problem)
	//
	//1.  **Recognize the pattern.** The expression `x² + 4x + 4` is a perfect square trinomial. It fits the pattern `a² + 2ab + b² = (a + b)²`. In this case, `a = x` and `b = 2`.
	//
	//2.  **Factor the equation.**
	//    `x² + 4x + 4 = (x + 2)(x + 2) = (x + 2)²`
	//
	//3.  **Solve for x.** Now set the factored expression to zero:
	//    `(x + 2)² = 0`
	//
	//    Take the square root of both sides:
	//    `x + 2 = 0`
	//
	//    Subtract 2 from both sides:
	//    `x = -2`
	//
	//This type of solution is called a "repeated root" or a "double root" because the factor `(x+2)` appears twice.
	//
	//---
	//
	//### Method 2: Using the Quadratic Formula
	//
	//You can use the quadratic formula for any equation in the form `ax² + bx + c = 0`.
	//
	//The formula is: `x = [-b ± sqrt(b² - 4ac)] / 2a`
	//
	//1.  **Identify a, b, and c.**
	//    *   a = 1
	//    *   b = 4
	//    *   c = 4
	//
	//2.  **Plug the values into the formula.**
	//    `x = [-4 ± sqrt(4² - 4 * 1 * 4)] / (2 * 1)`
	//
	//3.  **Simplify.**
	//    `x = [-4 ± sqrt(16 - 16)] / 2`
	//    `x = [-4 ± sqrt(0)] / 2`
	//    `x = -4 / 2`
	//
	//4.  **Solve for x.**
	//    `x = -2`
	//Alright, the user wants to solve the quadratic equation `x² + 4x + 4 = 0`. My first instinct is to see if I can factor it; that's often the fastest approach if it works.  Looking at the coefficients, I see `a = 1`, `b = 4`, and `c = 4`.  Factoring is clearly the most direct path here. I need to find two numbers that multiply to 4 (c) and add up to 4 (b). Hmm, let's see… 1 and 4? Nope, that adds to 5.  2 and 2? Perfect!  2 times 2 is 4, and 2 plus 2 is also 4.
	//
	//So, `x² + 4x + 4` factors nicely into `(x + 2)(x + 2)`.  Ah, a perfect square trinomial! That's useful to note. Now, I can write the equation as `(x + 2)² = 0`.  Taking the square root of both sides gives me `x + 2 = 0`.  And finally, subtracting 2 from both sides, I get `x = -2`.  That's the solution.
	//
	//Just to be thorough, and maybe to offer an alternative explanation, let's verify this using the quadratic formula. It's `x = [-b ± √(b² - 4ac)] / 2a`. Plugging in my values:  `x = [-4 ± √(4² - 4 * 1 * 4)] / (2 * 1)`.  That simplifies to `x = [-4 ± √(16 - 16)] / 2`, or `x = [-4 ± 0] / 2`.  Therefore, `x = -2`. The discriminant being zero tells me I have exactly one real, repeated root.  Great. So, whether I factor or use the quadratic formula, the answer is the same.
	return nil
}

Java

Pelajari cara menginstal atau mengupdate Java.

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Google Gen AI SDK dengan Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_ENTERPRISE=True
 


import com.google.genai.Client;
import com.google.genai.types.Candidate;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentConfig;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.ThinkingConfig;

public class ThinkingIncludeThoughtsWithTxt {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-pro";
    generateContent(modelId);
  }

  // Generates text including thoughts in the response
  public static String generateContent(String modelId) {
    // 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()) {

      GenerateContentConfig contentConfig =
          GenerateContentConfig.builder()
              .thinkingConfig(ThinkingConfig.builder().includeThoughts(true).build())
              .build();

      GenerateContentResponse response =
          client.models.generateContent(modelId, "solve x^2 + 4x + 4 = 0", contentConfig);

      System.out.println(response.text());
      // Example response:
      // We can solve the equation x² + 4x + 4 = 0 using a couple of common methods.
      //
      // ### Method 1: Factoring (The Easiest Method for this Problem)
      // **Recognize the pattern:** The pattern for a perfect square trinomial
      // is a² + 2ab + b² = (a + b)².
      // ...
      // ### Final Answer:
      // The solution is **x = -2**.

      // Get parts of the response and print thoughts
      response
          .candidates()
          .flatMap(candidates -> candidates.stream().findFirst())
          .flatMap(Candidate::content)
          .flatMap(Content::parts)
          .ifPresent(
              parts -> {
                parts.forEach(
                    part -> {
                      if (part.thought().orElse(false)) {
                        part.text().ifPresent(System.out::println);
                      }
                    });
              });
      // Example response:
      // Alright, let's break down this quadratic equation, x² + 4x + 4 = 0. My initial thought is,
      // "classic quadratic."  I'll need to find the values of 'x' that make this equation true. The
      // equation is in standard form, and since the coefficients are relatively small, I
      // immediately suspect that factoring might be the easiest route.  It's worth checking.
      //
      // First, I assessed what I had. *a* is 1, *b* is 4, and *c* is 4. I consider my toolkit.
      // Factoring is the likely first choice, then I can use the quadratic formula as a backup,
      // because that ALWAYS works, and I could use graphing. However, for this, factoring seems the
      // cleanest approach.
      //
      // Okay, factoring. I need two numbers that multiply to *c* (which is 4) and add up to *b*
      // (also 4).  I quickly run through the factor pairs of 4: (1, 4), (-1, -4), (2, 2), (-2, -2).
      //  Aha! 2 and 2 fit the bill. They multiply to 4 *and* add up to 4.  Therefore, I can rewrite
      // the equation as (x + 2)(x + 2) = 0.  That simplifies to (x + 2)² = 0. Perfect square
      // trinomial – nice and tidy. Seeing that pattern from the outset can save a step or two. Now,
      // to solve for *x*:  if (x + 2)² = 0, then x + 2 must equal 0.  Therefore, x = -2. Done.
      //
      // But, for the sake of a full explanation, let's use the quadratic formula as a second
      // method. It's a reliable way to double-check the answer, plus it's good practice.  I plug my
      // *a*, *b*, and *c* values into the formula: x = [-b ± √(b² - 4ac)] / (2a). That gives me  x
      // = [-4 ± √(4² - 4 * 1 * 4)] / (2 * 1). Simplifying under the radical, I get x = [-4 ± √(16 -
      // 16)] / 2. So, x = [-4 ± √0] / 2. The square root of 0 is zero, which is very telling!  When
      // the discriminant (b² - 4ac) is zero, you get one real solution, a repeated root. This means
      // x = -4 / 2, which simplifies to x = -2.  Exactly the same as before.
      //
      // Therefore, the answer is x = -2.  Factoring was the most straightforward route.  For
      // completeness, I showed the solution via the quadratic formula, too. Both approaches lead to
      // the same single solution.  This is a repeated root – a double root, if you will.
      //
      // And to be absolutely sure...let's check our answer! Substitute -2 back into the original
      // equation. (-2)² + 4(-2) + 4 = 4 - 8 + 4 = 0.  Yep, 0 = 0. The solution is correct.
      return response.text();
    }
  }
}

Respons dapat berisi tanda tangan pemikiran tanpa teks ringkasan pemikiran dalam skenario berikut:

  • Permintaan kompleksitas rendah: Model memerlukan langkah-langkah penalaran minimal untuk merumuskan respons.
  • Ringkasan dinonaktifkan: Ringkasan pemikiran tidak diminta atau dinonaktifkan secara eksplisit.
  • Modalitas penalaran non-teks: Modalitas tertentu (seperti pemrosesan gambar) mungkin tidak menghasilkan ringkasan teks.

Aplikasi Anda harus selalu menangani respons dengan baik jika konten ringkasan pemikiran tidak ada atau kosong sambil mempertahankan tanda tangan pemikiran terkait.

Tanda tangan penalaran

Tanda tangan pemikiran adalah representasi terenkripsi dari proses pemikiran internal model yang mempertahankan status penalaran Gemini selama percakapan multi-giliran, terutama saat menggunakan panggilan fungsi.

Untuk memastikan model mempertahankan konteks penuh di beberapa giliran percakapan, Anda harus menampilkan tanda tangan pemikiran dari respons sebelumnya dalam permintaan berikutnya, terlepas dari tingkat pemikiran yang digunakan. Jika Anda menggunakan Google Gen AI SDK resmi (Python, Node.js, Go, atau Java) dan menggunakan fitur histori chat standar atau menambahkan respons model lengkap ke histori, tanda tangan pemikiran akan ditangani secara otomatis.

Untuk mengetahui aturan, contoh, dan pola alur kerja multi-giliran yang mendetail, lihat Tanda tangan pemikiran.

Teknik penulisan perintah

Desain perintah yang efektif membantu Anda mengarahkan penalaran model, mencadangkan anggaran token, dan mencapai kualitas output yang optimal dengan model penalaran.

Untuk mengetahui strategi komprehensif, pola multishot, perintah verifikasi, dan tips penelusuran bug, lihat Panduan perintah berpikir.

Harga

Anda dikenai biaya untuk token yang dihasilkan selama proses penalaran model. Untuk beberapa model, seperti Gemini 3 Pro dan Gemini 2.5 Pro, penalaran diaktifkan secara default dan Anda ditagih untuk token ini.

Untuk mengetahui informasi selengkapnya, lihat harga Platform Agen. Untuk mempelajari cara mengelola biaya, lihat Mengontrol pemikiran model.

Langkah berikutnya

Panduan

Pelajari cara mempertahankan status penalaran Gemini selama percakapan multi-turn dan multi-langkah menggunakan tanda tangan pemikiran.

Panduan

Pelajari teknik dan praktik terbaik rekayasa perintah yang disesuaikan untuk model penalaran Gemini.

Konsol

Coba sendiri perintah Gemini di Konsol Google Cloud.