Razonamiento

Los modelos de pensamiento generan un proceso de "pensamiento" interno antes de devolver una respuesta. Esta capacidad ayuda al modelo a realizar una planificación compleja de varios pasos, resolver problemas matemáticos y generar código preciso.

En esta página se explica cómo:

Modelos compatibles

El pensamiento se admite en los siguientes modelos:

Haz clic para expandir los modelos compatibles

Cómo controlar el razonamiento del modelo

El pensamiento está habilitado de forma predeterminada en los modelos de Gemini compatibles. En Agent Studio, puedes inspeccionar el proceso de pensamiento completo junto con la respuesta generada.

La forma en que configures el pensamiento depende de la versión del modelo:

Modelos de Gemini 3 y versiones posteriores

Los modelos de Gemini 3 usan el parámetro thinking_level. Este parámetro establece niveles de razonamiento discretos para que puedas optimizar la latencia y la profundidad del razonamiento.

Console

  1. Ve a Agent Studio, selecciona Nuevo > Chat y expande el panel del modelo.

    Abrir Agent Studio

  2. En el panel Configuración del modelo, selecciona un modelo compatible en el menú Modelo.
  3. Selecciona un valor en el menú desplegable Nivel de pensamiento.

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)

Valores del nivel de razonamiento

Puedes establecer thinking_level en uno de los siguientes valores:

  • MINIMAL: Usa la menor cantidad posible de tokens para pensar. Es mejor para tareas sencillas que no requieren un razonamiento extenso. MINIMAL requiere firmas de pensamiento en conversaciones de varios turnos. Si se omiten, el modelo devuelve un error 400: INVALID_ARGUMENT.
  • LOW: Usa menos tokens de pensamiento para obtener respuestas más rápidas. Es ideal para aplicaciones de alto rendimiento con baja complejidad de tareas.
  • MEDIUM: Equilibra la calidad y la latencia del razonamiento. Es adecuado para tareas de complejidad moderada que se benefician de pasos de razonamiento intermedios.
  • HIGH: Usa la capacidad de pensamiento máxima. Es ideal para instrucciones complejas que requieren razonamiento profundo, resolución de problemas de varios pasos, verificación formal de código o ejecución de herramientas de varios turnos.

Niveles de razonamiento admitidos por modelo

En la siguiente tabla, se enumeran los valores de thinking_level admitidos y las configuraciones predeterminadas por modelo:

Modelo Valores admitidos de thinking_level: Predeterminado
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 versión preliminar 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
Imagen de Gemini 3.1 Flash MINIMAL, HIGH MINIMAL
Gemini 3 Pro Image HIGH HIGH
Gemini 3 Flash vista previa MINIMAL, LOW, MEDIUM, HIGH HIGH

Modelos de Gemini 2.5 y versiones anteriores

Para los modelos de Gemini 2.5 y versiones anteriores, configura el pensamiento con el parámetro thinking_budget. Este parámetro establece un límite flexible en la cantidad de tokens que el modelo puede usar durante el razonamiento interno.

Console

  1. Ve a Agent Studio y selecciona Nuevo > Chat.

    Abrir Agent Studio

  2. En el panel Configuración del modelo, selecciona un modelo compatible en el menú Modelo.
  3. En el selector Presupuesto de pensamiento, selecciona Manual y usa el control deslizante para ajustar el límite de tokens.

Python

Instalar

pip install --upgrade google-genai

Para obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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 obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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

Obtén información para instalar o actualizar Go.

Para obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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

Obtén información para instalar o actualizar Java.

Para obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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();
    }
  }
}

Si no especificas un presupuesto, el modelo establece el presupuesto de tokens de forma dinámica hasta 8,192 tokens. Para habilitar explícitamente el presupuesto dinámico en la API, establece thinking_budget en -1.

Presupuestos de pensamiento admitidos por modelo

En la siguiente tabla, se indican los límites de tokens mínimos, máximos y predeterminados para cada modelo:

Modelo Cantidad mínima de tokens Cantidad máxima de tokens Predeterminado
Gemini 2.5 Flash 1 24,576 Automático (hasta 8,192 tokens)
Gemini 2.5 Pro 128 32,768 Automático (hasta 8,192 tokens)
Gemini 2.5 Flash-Lite 512 24,576 Automático (hasta 8,192 tokens)

Desactivar el pensamiento

Puedes desactivar el pensamiento para Gemini 2.5 Flash y Gemini 2.5 Flash-Lite configurando thinking_budget en 0. Si bien el contenido de pensamiento no se devuelve en la respuesta, es posible que el texto generado muestre un resultado de estilo de razonamiento.

No puedes desactivar el proceso de pensamiento de Gemini 2.5 Pro.

Ver resúmenes de razonamiento

Los Resúmenes de razonamiento muestran los pasos de razonamiento intermedio junto con la respuesta final del modelo. Los resúmenes de pensamientos son compatibles con los modelos de Gemini 2.5 y versiones posteriores.

Console

Los resúmenes de pensamientos están habilitados de forma predeterminada en Agent Studio. Para ver los pasos de razonamiento resumidos, expande el panel Pensamientos.

Python

Instalar

pip install --upgrade google-genai

Para obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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 obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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

Obtén información para instalar o actualizar Go.

Para obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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

Obtén información para instalar o actualizar Java.

Para obtener más información, consulta la documentación de referencia del SDK.

Establece variables de entorno para usar el SDK de IA generativa de Google con 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();
    }
  }
}

Una respuesta puede devolver una firma de pensamiento sin texto de resumen del pensamiento en las siguientes situaciones:

  • Solicitudes de baja complejidad: La solicitud requirió una cantidad mínima de pasos de razonamiento.
  • Resúmenes inhabilitados: No se solicitaron resúmenes de razonamiento o se desactivaron.
  • Modalidades que no son de texto: El razonamiento sobre ciertas modalidades (como el análisis de imágenes) podría no producir resúmenes de texto.

Tu aplicación debe controlar los campos de resumen de pensamiento vacíos o faltantes de forma correcta y conservar las firmas de pensamiento que los acompañan.

Firmas de razonamiento

Las firmas de pensamiento son representaciones encriptadas del estado de razonamiento interno del modelo. Mantienen el contexto en conversaciones de varios turnos, en especial cuando se usa la llamada a función.

Para conservar el contexto de razonamiento en las interacciones de varios turnos, pasa las firmas de pensamiento que se devolvieron en respuestas anteriores a las solicitudes posteriores, independientemente del nivel de pensamiento configurado.

Si usas el SDK de IA generativa de Google (Python, Node.js, Go o Java), las firmas de pensamiento se administran automáticamente cuando usas sesiones de chat estándar o cuando agregas objetos de respuesta completos a tu historial de mensajes.

Para conocer los patrones, los requisitos y los ejemplos de implementación, consulta Firmas de pensamiento.

Precios

Se te facturarán los tokens generados durante el proceso de pensamiento. En el caso de los modelos en los que el pensamiento está habilitado de forma predeterminada, como Gemini 3 Pro y Gemini 2.5 Pro, estos tokens de pensamiento se incluyen en tu uso facturable.

Para obtener todos los detalles de las tarifas, consulta Precios.

¿Qué sigue?

Guía

Aprende a conservar el estado de razonamiento de Gemini durante conversaciones de varios turnos y pasos con firmas de pensamiento.

Guía

Explora las técnicas y prácticas recomendadas de ingeniería de instrucciones diseñadas para los modelos de pensamiento de Gemini.

Consola

Prueba Gemini por tu cuenta en la Google Cloud Console.