Berpikir

Model penalaran menghasilkan proses "penalaran" internal sebelum menampilkan respons. Kemampuan ini membantu model melakukan perencanaan multi-langkah yang kompleks, menyelesaikan masalah matematika, dan menghasilkan kode yang akurat.

Halaman ini menjelaskan cara:

• Mengonfigurasi tingkat penalaran dan anggaran token
• Melihat ringkasan pemikiran
• Mempertahankan status penalaran di seluruh percakapan multi-turn menggunakan tanda tangan pemikiran

Model yang didukung

Penalaran didukung dalam model berikut:

Klik untuk meluaskan model yang didukung

• Gemini Omni Flash pratinjau
• Gemini Omni 1.1 Flash pratinjau
• Gemini Nano Banana 2.1
• Gemini 3.8 Flash Cyber
• Gemini 3.8 Flash
• Gemini 3.7 Flash
• Gemini 3.6 Flash
• Gemini 3.5 Flash-Lite
• Gemini 3.5 Flash
• Gemini 3.1 Pro pratinjau
• Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite)
• Gemini 3.1 Flash-Lite
• Gemini 3.1 Flash Image
• Gemini 3 Pro Image
• Gemini 3 Flash pratinjau
• Gemini 2.5 Pro
• Gemini 2.5 Flash-Lite
• Gemini 2.5 Flash

Mengontrol penalaran model

Penalaran diaktifkan secara default di model Gemini yang didukung. Di Agent Studio, Anda dapat memeriksa seluruh proses berpikir bersama dengan respons yang dihasilkan.

Cara Anda mengonfigurasi penalaran bergantung pada versi model:

• Model Gemini 3 dan yang lebih baru
• Model Gemini 2.5 dan yang lebih lama

Model Gemini 3 dan yang lebih baru

Model Gemini 3 menggunakan parameter thinking_level. Parameter ini menetapkan tingkat penalaran diskret sehingga Anda dapat mengoptimalkan antara latensi dan kedalaman penalaran.

Konsol

1. Buka Agent Studio, pilih New > Chat, lalu perluas panel model.

   Buka Agent Studio

2. Di panel Model settings, pilih model yang didukung dari menu Model.
3. Pilih nilai dari menu drop-down Thinking level.

Python

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(
            # Options: MINIMAL, LOW, MEDIUM, HIGH
            thinking_level=types.ThinkingLevel.THINKING_LEVEL_VALUE
        )
    ),
)

print(response.text)

Peringatan: Parameter thinking_budget tidak digunakan lagi untuk model Gemini 3 dan yang lebih baru. Penggunaan thinking_budget dengan model ini dapat menyebabkan error 400: INVALID_ARGUMENT yang terputus-putus.

Menentukan thinking_level dan thinking_budget dalam permintaan yang sama akan menampilkan error. Hapus thinking_budget dari permintaan Anda saat menggunakan model Gemini 3 untuk menghindari error ini.

Nilai tingkat penalaran

Anda dapat menetapkan thinking_level ke salah satu nilai berikut:

• MINIMAL: Menggunakan token sesedikit mungkin untuk penalaran. Paling cocok untuk tugas sederhana yang tidak memerlukan penalaran panjang. MINIMAL memerlukan tanda tangan pemikiran dalam percakapan multi-turn; jika dihilangkan, model akan menampilkan error 400: INVALID_ARGUMENT.
• LOW: Menggunakan lebih sedikit token penalaran untuk respons yang lebih cepat. Paling cocok untuk aplikasi dengan throughput tinggi dan kompleksitas tugas yang rendah.
• MEDIUM: Menyeimbangkan kualitas penalaran dan latensi. Cocok untuk tugas dengan kompleksitas sedang yang memerlukan langkah-langkah penalaran menengah.
• HIGH: Menggunakan kapasitas penalaran maksimum. Terbaik untuk perintah kompleks yang memerlukan penalaran mendalam, pemecahan masalah multi-langkah, verifikasi kode formal, atau eksekusi alat multi-turn.

Tingkat penalaran yang didukung menurut model

Tabel berikut mencantumkan nilai thinking_level yang didukung dan konfigurasi default menurut model:

Model	Nilai thinking_level yang didukung	Default
Gemini Nano Banana 2.1	MINIMAL, MEDIUM, HIGH	MEDIUM
Gemini 3.8 Flash Cyber	LOW, MEDIUM, HIGH	MEDIUM
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
Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite)	MINIMAL, HIGH	MINIMAL
Gemini 3.1 Flash-Lite	MINIMAL, LOW, MEDIUM, HIGH	MINIMAL
Gemini 3.1 Flash Image	MINIMAL, HIGH	MINIMAL
Gemini 3 Pro Image	HIGH	HIGH
Gemini 3 Flash pratinjau	MINIMAL, LOW, MEDIUM, HIGH	HIGH

Model Gemini 2.5 dan yang lebih lama

Perhatian: Jangan gunakan parameter thinking_level dengan model Gemini 2.5 dan yang lebih lama. Permintaan Anda akan menampilkan error jika parameter ini ada.

Untuk model Gemini 2.5 dan yang lebih lama, konfigurasi kemampuan berpikir menggunakan parameter thinking_budget. Parameter ini menetapkan batas lunak pada jumlah token yang dapat digunakan model selama penalaran internal.

Konsol

1. Buka Agent Studio, lalu pilih New > Chat.

   Buka Agent Studio

2. Di panel Model settings, pilih model yang didukung dari menu Model.
3. Di pemilih Anggaran Penalaran, pilih Manual dan gunakan penggeser untuk menyesuaikan batas token.

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();
    }
  }
}

Jika Anda tidak menentukan anggaran, model akan menetapkan anggaran token secara dinamis hingga 8.192 token. Untuk mengaktifkan penganggaran dinamis secara eksplisit di API, tetapkan thinking_budget ke -1.

Catatan: Anggaran penalaran adalah batas fleksibel. Jumlah sebenarnya token penalaran yang dihasilkan mungkin sedikit berbeda. Jika aplikasi Anda memerlukan latensi yang lebih rendah, tetapkan anggaran yang lebih rendah atau tetapkan anggaran ke 0.

Anggaran penalaran yang didukung menurut model

Tabel berikut mencantumkan batas token minimum, maksimum, dan default untuk setiap model:

Model	Token minimum	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)

Menonaktifkan penalaran

Anda dapat menonaktifkan penalaran untuk Gemini 2.5 Flash dan Gemini 2.5 Flash-Lite dengan menetapkan thinking_budget ke 0. Meskipun konten pemikiran tidak ditampilkan dalam respons, teks yang dihasilkan mungkin masih menampilkan output gaya penalaran.

Anda tidak dapat menonaktifkan penalaran untuk Gemini 2.5 Pro.

Melihat ringkasan pemikiran

Ringkasan pemikiran menampilkan langkah-langkah penalaran menengah bersama dengan respons akhir model. Ringkasan pemikiran didukung di model Gemini 2.5 dan yang lebih baru.

Konsol

Ringkasan pemikiran diaktifkan secara default di Agent Studio. Untuk melihat ringkasan langkah-langkah penalaran, luaskan panel Thoughts.

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 mungkin menampilkan tanda tangan pemikiran tanpa teks ringkasan pemikiran dalam situasi berikut:

• Permintaan dengan kompleksitas rendah: Permintaan memerlukan langkah-langkah penalaran minimal.
• Ringkasan dinonaktifkan: Ringkasan penalaran tidak diminta atau dinonaktifkan.
• Modalitas non-teks: Penalaran atas modalitas tertentu (seperti analisis gambar) mungkin tidak menghasilkan ringkasan teks.

Aplikasi Anda harus menangani kolom ringkasan pemikiran yang kosong atau tidak ada dengan baik sambil mempertahankan tanda tangan pemikiran yang menyertainya.

Tanda tangan penalaran

Thought signatures adalah representasi terenkripsi dari status penalaran internal model. Model ini mempertahankan konteks di seluruh percakapan multi-turn, terutama saat menggunakan panggilan fungsi.

Untuk mempertahankan konteks penalaran di seluruh interaksi multi-giliran, teruskan tanda tangan pemikiran yang ditampilkan dalam respons sebelumnya kembali ke permintaan berikutnya, terlepas dari tingkat pemikiran yang dikonfigurasi.

Jika Anda menggunakan Google Gen AI SDK resmi dari Google (Python, Node.js, Go, atau Java), tanda tangan pemikiran akan dikelola secara otomatis saat menggunakan sesi chat standar atau saat menambahkan objek respons lengkap ke histori pesan Anda.

Untuk pola, persyaratan, dan contoh implementasi, lihat Tanda tangan pemikiran.

Harga

Anda akan ditagih untuk token yang dihasilkan selama proses penalaran. Untuk model yang mengaktifkan penalaran secara default—seperti Gemini 3 Pro dan Gemini 2.5 Pro—token penalaran ini disertakan dalam penggunaan yang dapat ditagih.

Untuk mengetahui detail tarif lengkap, lihat Harga.

Langkah berikutnya

Panduan

Tanda tangan penalaran

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

Panduan

Panduan pembuatan perintah penalaran

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

Konsol

Google Cloud console

Coba sendiri perintah Gemini di konsol Google Cloud .