Pensando

Os modelos de pensamento geram um processo interno de "pensamento" antes de retornar uma resposta. Esse recurso ajuda o modelo a realizar um planejamento complexo de várias etapas, resolver problemas matemáticos e gerar código preciso.

Nesta página, descrevemos como:

• Configurar níveis de pensamento e orçamentos de token
• Ver resumos de ideias
• Preservar o estado de raciocínio em conversas multiturno usando assinaturas de pensamento

Modelos compatíveis

O recurso de pensamento é compatível com os seguintes modelos:

Clique para abrir os modelos compatíveis

• Gemini Omni Flash pré-lançamento
• Gemini Omni 1.1 Flash pré-lançamento
• 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 pré-lançamento
• Imagem do Gemini 3.1 Flash-Lite (Nano Banana 2 Lite)
• Gemini 3.1 Flash-Lite
• Criação de imagens do Gemini 3.1 Flash
• Gemini 3 Pro Image
• Gemini 3 Flash pré-lançamento
• Gemini 2.5 Pro
• Gemini 2.5 Flash-Lite
• Gemini 2.5 Flash

Controlar o raciocínio do modelo

O raciocínio está ativado por padrão nos modelos do Gemini compatíveis. No Agent Studio, você pode inspecionar todo o processo de pensamento junto com a resposta gerada.

A configuração do pensamento depende da versão do modelo:

• Modelos do Gemini 3 e mais recentes
• Modelos do Gemini 2.5 e anteriores

Modelos do Gemini 3 e mais recentes

Os modelos do Gemini 3 usam o parâmetro thinking_level. Esse parâmetro define níveis de raciocínio discretos para que você possa otimizar a latência e a profundidade do raciocínio.

Console

1. Acesse o Agent Studio e selecione Novo > Chat e expanda o painel de modelos.

   Abrir o Agent Studio

2. No painel Configurações do modelo, selecione um modelo compatível no menu Modelo.
3. Selecione um valor no menu suspenso Nível de pensamento.

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)

Aviso:o parâmetro thinking_budget foi descontinuado para modelos do Gemini 3 e versões mais recentes. Usar thinking_budget com esses modelos pode causar erros intermitentes de 400: INVALID_ARGUMENT.

Especificar thinking_level e thinking_budget na mesma solicitação retorna um erro. Remova thinking_budget das suas solicitações ao usar modelos do Gemini 3 para evitar esses erros.

Valores de nível de raciocínio

É possível definir thinking_level como um dos seguintes valores:

• MINIMAL: usa o menor número possível de tokens para raciocínio. Ideal para tarefas simples que não exigem raciocínio extenso. O MINIMAL exige assinaturas de pensamento em conversas multiturno. Se omitidas, o modelo retorna um erro 400: INVALID_ARGUMENT.
• LOW: usa menos tokens para raciocínio e respostas mais rápidas. Ideal para aplicativos de alta capacidade com baixa complexidade de tarefas.
• MEDIUM: equilibra a qualidade do raciocínio e a latência. Adequado para tarefas de complexidade moderada que se beneficiam de etapas intermediárias de raciocínio.
• HIGH: usa a capacidade máxima de análise. Ideal para comandos complexos que exigem raciocínio profundo, resolução de problemas em várias etapas, verificação formal de código ou execução de ferramentas multiturno.

Níveis de raciocínio compatíveis por modelo

A tabela a seguir lista os valores de thinking_level compatíveis e as configurações padrão por modelo:

Modelo	thinking_level: valores aceitos:	Padrão
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 pré-lançamento	LOW, MEDIUM, HIGH	HIGH
Imagem do Gemini 3.1 Flash-Lite (Nano Banana 2 Lite)	MINIMAL, HIGH	MINIMAL
Gemini 3.1 Flash-Lite	MINIMAL, LOW, MEDIUM, HIGH	MINIMAL
Criação de imagens do Gemini 3.1 Flash	MINIMAL, HIGH	MINIMAL
Gemini 3 Pro Image	HIGH	HIGH
Gemini 3 Flash pré-lançamento	MINIMAL, LOW, MEDIUM, HIGH	HIGH

Modelos Gemini 2.5 e anteriores

Cuidado: não use o parâmetro thinking_level com o Gemini 2.5 e modelos anteriores. Suas solicitações vão retornar um erro se esse parâmetro estiver presente.

Para o Gemini 2.5 e modelos anteriores, configure o raciocínio usando o parâmetro thinking_budget. Esse parâmetro define um limite flexível para o número de tokens que o modelo pode usar durante o raciocínio interno.

Console

1. Acesse o Agent Studio e selecione Novo > Chat.

   Abrir o Agent Studio

2. No painel Configurações do modelo, selecione um modelo compatível no menu Modelo.
3. No seletor Orçamento de pensamento, selecione Manual e use o controle deslizante para ajustar o limite de tokens.

Python

Instalar

pip install --upgrade google-genai

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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

Instalar

npm install @google/genai

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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

Saiba como instalar ou atualizar o Go.

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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

Saiba como instalar ou atualizar o Java.

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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();
    }
  }
}

Se você não especificar um orçamento, o modelo vai definir o orçamento de token dinamicamente até 8.192 tokens. Para ativar explicitamente o orçamento dinâmico na API, defina thinking_budget como -1.

Observação: o orçamento de pensamento é um limite flexível. O número real de tokens de pensamento gerados pode variar um pouco. Se o aplicativo exigir uma latência menor, defina um orçamento mais baixo ou defina o orçamento como 0.

Orçamentos de pensamento compatíveis por modelo

A tabela a seguir lista os limites de tokens mínimos, máximos e padrão para cada modelo:

Modelo	Mínimo de tokens	Máximo de tokens	Padrão
Gemini 2.5 Flash	1	24.576	Automático (até 8.192 tokens)
Gemini 2.5 Pro	128	32.768	Automático (até 8.192 tokens)
Gemini 2.5 Flash Lite	512	24.576	Automático (até 8.192 tokens)

Desativar raciocínio

Você pode desativar o pensamento para o Gemini 2.5 Flash e o Gemini 2.5 Flash-Lite definindo thinking_budget como 0. Embora o conteúdo de raciocínio não seja retornado na resposta, o texto gerado ainda pode mostrar uma saída de estilo de raciocínio.

Não é possível desativar o recurso de pensamento do Gemini 2.5 Pro.

Ver resumos de raciocínio

Os resumos de ideias mostram as etapas intermediárias de raciocínio ao lado da resposta final do modelo. Os resumos de ideias são compatíveis com os modelos do Gemini 2.5 e versões mais recentes.

Console

Os resumos de ideias são ativados por padrão no Agent Studio. Para conferir as etapas de raciocínio resumidas, expanda o painel Pensamentos.

Python

Instalar

pip install --upgrade google-genai

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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

Instalar

npm install @google/genai

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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

Saiba como instalar ou atualizar o Go.

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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

Saiba como instalar ou atualizar o Java.

Para saber mais, consulte a documentação de referência do SDK.

Defina variáveis de ambiente para usar o SDK de IA generativa do Google com a 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();
    }
  }
}

Uma resposta pode retornar uma assinatura de pensamento sem texto de resumo nas seguintes situações:

• Solicitações de baixa complexidade: a solicitação exigiu etapas de raciocínio mínimas.
• Resumos desativados: os resumos de ideias não foram solicitados ou foram desativados.
• Modalidades não textuais: o raciocínio sobre determinadas modalidades (como análise de imagens) pode não produzir resumos de texto.

Seu aplicativo precisa processar campos de resumo de pensamento vazios ou ausentes de maneira adequada, preservando as assinaturas de pensamento acompanhantes.

Assinaturas de raciocínio

As assinaturas de pensamento são representações criptografadas do estado de raciocínio interno do modelo. Eles mantêm o contexto em conversas multiturno, principalmente ao usar a chamada de função.

Para preservar o contexto de raciocínio em interações multiturno, transmita as assinaturas de pensamento retornadas em respostas anteriores de volta para solicitações subsequentes, independente do nível de pensamento configurado.

Se você usar o SDK de IA Generativa do Google (Python, Node.js, Go ou Java), as assinaturas de pensamento serão gerenciadas automaticamente ao usar sessões de chat padrão ou ao anexar objetos de resposta completos ao histórico de mensagens.

Para conferir padrões, requisitos e exemplos de implementação, consulte Assinaturas de pensamento.

Preços

Você recebe uma cobrança pelos tokens gerados durante o processo de pensamento. Para modelos em que o raciocínio está ativado por padrão, como o Gemini 3 Pro e o Gemini 2.5 Pro, esses tokens de raciocínio são incluídos no uso faturável.

Para detalhes completos sobre as tarifas, consulte Preços.

A seguir

Guia

Assinaturas de raciocínio

Saiba como preservar o estado de raciocínio do Gemini durante conversas multiturno e com várias etapas usando assinaturas de pensamento.

Guia

Guia de comandos para pensar

Conheça técnicas e práticas recomendadas de engenharia de comando personalizadas para os modelos de raciocínio do Gemini.

Console

Console do Google Cloud

Teste o Gemini no console do Google Cloud.