Gemini thinking

Gemini thinking

Gemini 3 및 2.5 시리즈 모델은 추론과 다단계 계획 능력을 크게 향상시키는 "thinking 프로세스"를 사용해, 코딩, 고급 수학, 데이터 분석 같은 복잡한 작업에 매우 효과적이에요.

thinking 모델을 사용하면 Gemini가 응답하기 전에 내부적으로 추론해요. Interactions API는 이 추론을 steps 배열에서 함수 호출, 사용자 입력 또는 모델 출력과 함께 시간순으로 나타나는 전용 단계인 thought 단계로 표면화해요.

모든 thought 단계에는 두 개의 필드가 포함돼요.

필드	필수	설명
signature	✅ 예	모델의 내부 추론 상태의 암호화된 표현. 모델이 최소한의 추론만 수행해도 항상 존재해요.
summary	❌ 아니요	추론을 요약하는 콘텐츠(텍스트 및/또는 이미지) 배열. thinking_summaries 구성, 모델이 충분히 추론했는지 여부 또는 콘텐츠 유형(예: 이미지 잠재값은 텍스트 요약이 없을 수 있음)에 따라 비어 있을 수 있어요.

출처: 원문

본문

thinking 사용 상호작용

thinking 모델로 상호작용을 시작하는 것은 다른 상호작용 요청과 비슷해요. model 필드에 thinking 지원 모델 중 하나를 지정하세요.

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Explain the concept of Occam's Razor and provide a simple, everyday example."
)
print(interaction.output_text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: "Explain the concept of Occam's Razor and provide a simple, everyday example."
});
console.log(interaction.output_text);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(
            InteractionsInput.of(
                "Explain the concept of Occam's Razor and provide a simple, everyday example."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-pro"),
            Input: interactions.NewInteractionsInput("Explain the concept of Occam's Razor and provide a simple, everyday example."),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: *** \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "Explain the concept of Occam'\''s Razor and provide a simple example."
  }'

Thought 요약

Thought 요약은 모델의 내부 추론 과정에 대한 통찰을 제공해요. 기본적으로 최종 출력만 반환돼요. thinking_summaries로 thought 요약을 활성화할 수 있어요.

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="What is the sum of the first 50 prime numbers?",
    generation_config={
        "thinking_summaries": "auto"
    }
)

for step in interaction.steps:
    if step.type == "thought":
        print("Thought summary:")
        if step.summary:
            for content_block in step.summary:
                if content_block.type == "text":
                    print(content_block.text)
        print()
    elif step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print("Answer:")
                print(content_block.text)
                print()

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: "What is the sum of the first 50 prime numbers?",
    generation_config: {
        thinking_summaries: "auto"
    }
});

for (const step of interaction.steps) {
    if (step.type === "thought") {
        console.log("Thought summary:");
        if (step.summary) {
            for (const contentBlock of step.summary) {
                if (contentBlock.type === "text") console.log(contentBlock.text);
            }
        }
    } else if (step.type === "model_output") {
        for (const contentBlock of step.content) {
            if (contentBlock.type === "text") {
                console.log("Answer:");
                console.log(contentBlock.text);
            }
        }
    }
}

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.GenerationConfig;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.interactions.ThinkingSummaries;
import com.google.genai.gaos.models.interactions.ThoughtStep;
import com.google.genai.gaos.models.interactions.ThoughtSummaryContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Collections;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("What is the sum of the first 50 prime numbers?"))
        .generationConfig(
            GenerationConfig.builder().thinkingSummaries(ThinkingSummaries.AUTO).build())
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

for (Step step : interaction.steps().orElse(Collections.emptyList())) {
  if (step instanceof ThoughtStep thoughtStep) {
    System.out.println("Thought summary:");
    for (ThoughtSummaryContent contentBlock : thoughtStep.summary().orElse(Collections.emptyList())) {
      if (contentBlock instanceof TextContent textContent) {
        System.out.println(textContent.text().orElse(""));
      }
    }
    System.out.println();
  } else if (step instanceof ModelOutputStep outputStep) {
    for (Content contentBlock : outputStep.content().orElse(Collections.emptyList())) {
      if (contentBlock instanceof TextContent textContent) {
        System.out.println("Answer:");
        System.out.println(textContent.text().orElse(""));
        System.out.println();
      }
    }
  }
}

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput("Provide a list of 3 famous physicists and their key contributions"),
            GenerationConfig: &interactions.GenerationConfig{
                ThinkingLevel: interactions.ThinkingLevelLow.ToPointer(),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: *** \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "What is the sum of the first 50 prime numbers?",
    "generation_config": {
      "thinking_summaries": "auto"
    }
  }'

다음 경우 thought 블록은 요약 없이 서명만 포함할 수 있어요.

• 모델이 요약을 생성할 만큼 추론하지 않은 단순 요청
• 요약이 명시적으로 비활성화된 thinking_summaries: "none"
• 이미지 같은 특정 thought 콘텐츠 유형은 텍스트 요약이 없을 수 있음

summary가 비어 있거나 없는 thought 블록을 항상 처리하도록 코드를 작성해야 해요.

thinking과 스트리밍

스트리밍을 사용해 생성 중 증가하는 thought 요약을 점진적으로 받을 수 있어요. Thought 블록은 두 가지 고유한 델타 유형으로 Server-Sent Events(SSE)를 통해 전달돼요.

델타 유형	포함 내용	전송 시점
thought_summary	텍스트 또는 이미지 요약 콘텐츠	증가하는 요약이 있는 하나 이상의 델타
thought_signature	암호화 서명	step.stop 전의 마지막 델타

from google import genai

client = genai.Client()

prompt = """
Alice, Bob, and Carol each live in a different house on the same street: red, green, and blue.
Alice does not live in the red house.
Bob does not live in the green house.
Carol does not live in the red or green house.
Which house does each person live in?
"""

thoughts = ""
answer = ""

stream = client.interactions.create(
    model="gemini-3.8-flash",
    input=prompt,
    generation_config={
        "thinking_summaries": "auto"
    },
    stream=True
)

for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "thought_summary":
            if not thoughts:
                print("Thinking...")
            summary_text = event.delta.content.text
            print(f"[Thought] {summary_text}", end="")
            thoughts += summary_text
        elif event.delta.type == "text" and event.delta.text:
            if not answer:
                print("\nAnswer:")
            print(event.delta.text, end="")
            answer += event.delta.text

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const prompt = `Alice, Bob, and Carol each live in a different house on the same
street: red, green, and blue. Alice does not live in the red house.
Bob does not live in the green house.
Carol does not live in the red or green house.
Which house does each person live in?`;

let thoughts = "";
let answer = "";

const stream = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: prompt,
    generation_config: {
        thinking_summaries: "auto"
    },
    stream: true
});

for await (const event of stream) {
    if (event.event_type === "step.delta") {
        if (event.delta.type === "thought_summary") {
            if (!thoughts) console.log("Thinking...");
            const text = event.delta.content?.text || "";
            process.stdout.write(`[Thought] ${text}`);
            thoughts += text;
        } else if (event.delta.type === "text" && event.delta.text) {
            if (!answer) console.log("\nAnswer:");
            process.stdout.write(event.delta.text);
            answer += event.delta.text;
        }
    }
}

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.GenerationConfig;
import com.google.genai.gaos.models.interactions.InteractionSSEEvent;
import com.google.genai.gaos.models.interactions.InteractionSSEStreamEvent;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.StepDelta;
import com.google.genai.gaos.models.interactions.StepDeltaData;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.interactions.TextDelta;
import com.google.genai.gaos.models.interactions.ThinkingSummaries;
import com.google.genai.gaos.models.interactions.ThoughtSummaryDelta;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.operations.CreateInteractionResponse;
import com.google.genai.gaos.utils.EventStream;

Client client = new Client();

String prompt =
    "Alice, Bob, and Carol each live in a different house on the same street: red, green, and blue.\n"
        + "Alice does not live in the red house.\n"
        + "Bob does not live in the green house.\n"
        + "Carol does not live in the red or green house.\n"
        + "Which house does each person live in?";

StringBuilder thoughts = new StringBuilder();
StringBuilder answer = new StringBuilder();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of(prompt))
        .generationConfig(
            GenerationConfig.builder().thinkingSummaries(ThinkingSummaries.AUTO).build())
        .stream(true)
        .build();

CreateInteractionResponse response =
    client.interactions.create(CreateInteractionRequestBody.of(params));

try (EventStream<InteractionSSEStreamEvent> stream = response.events()) {
  for (InteractionSSEStreamEvent streamEvent : stream) {
    InteractionSSEEvent event = streamEvent.data().orElse(null);
    if (event instanceof StepDelta stepDelta) {
      StepDeltaData delta = stepDelta.delta().orElse(null);
      if (delta instanceof ThoughtSummaryDelta thoughtDelta) {
        Content content = thoughtDelta.content().orElse(null);
        if (content instanceof TextContent textContent) {
          if (thoughts.length() == 0) {
            System.out.println("Thinking...");
          }
          String summaryText = textContent.text().orElse("");
          System.out.print("[Thought] " + summaryText);
          thoughts.append(summaryText);
        }
      } else if (delta instanceof TextDelta textDelta) {
        String text = textDelta.text().orElse("");
        if (!text.isEmpty()) {
          if (answer.length() == 0) {
            System.out.println("\nAnswer:");
          }
          System.out.print(text);
          answer.append(text);
        }
      }
    }
  }
}

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput("What is the sum of the first 50 prime numbers?"),
            GenerationConfig: &interactions.GenerationConfig{
                ThinkingLevel:     interactions.ThinkingLevelHigh.ToPointer(),
                ThinkingSummaries: interactions.ThinkingSummariesAuto.ToPointer(),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range res.Interaction.Steps {
        if thought := step.ThoughtStep; thought != nil {
            for _, part := range thought.Summary {
                if part.TextContent != nil {
                    fmt.Printf("Thought summary:\n%s\n\n", part.TextContent.Text)
                }
            }
        }
    }

    if res.Interaction.OutputText != nil {
        fmt.Printf("Answer:\n%s\n", *res.Interaction.OutputText)
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: *** \
  -H 'Content-Type: application/json' \
  --no-buffer \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "Alice, Bob, and Carol each live in a different house on the same street: red, green, and blue. Alice does not live in the red house. Bob does not live in the green house. Carol does not live in the red or green house. Which house does each person live in?",
    "generation_config": {
      "thinking_summaries": "auto"
    },
    "stream": true
  }'

스트리밍 응답은 Server-Sent Events(SSE)를 사용하며 단계와 이벤트로 구성돼요. 예:

event: interaction.created
data: {"interaction":{"id":"v1_xxx","status":"in_progress","object":"interaction","model":"gemini-3.8-flash"},"event_type":"interaction.created"}

event: step.start
data: {"index":0,"step":{"signature":"","summary":[{"text":"**Evaluating the clues**\n\nI'm considering...","type":"text"}],"type":"thought"},"event_type":"step.start"}

event: step.delta
data: {"index":0,"delta":{"signature":"EpoGCpcGAXLI2nx/...","type":"thought_signature"},"event_type":"step.delta"}

event: step.stop
data: {"index":0,"event_type":"step.stop"}

event: step.start
data: {"index":1,"step":{"content":[{"text":"Based on the clues provided, here","type":"text"}],"type":"model_output"},"event_type":"step.start"}

event: step.delta
data: {"index":1,"delta":{"text":" is the answer to your question...","type":"text"},"event_type":"step.delta"}

event: step.stop
data: {"index":1,"event_type":"step.stop"}

event: interaction.completed
data: {"interaction":{"id":"v1_xxx","status":"completed","usage":{"total_tokens":530,"total_input_tokens":62,"total_output_tokens":171,"total_thought_tokens":297}},"event_type":"interaction.completed"}

event: done
data: [DONE]

thinking 제어

Gemini 모델은 기본적으로 동적 thinking을 사용하여 요청의 복잡성에 따라 추론 노력의 양을 자동으로 조정해요. thinking_level 매개변수로 이 동작을 제어할 수 있어요.

모델	기본 Thinking	지원 수준
gemini-3.8-flash	켜짐(medium)	low, medium, high
gemini-3.7-flash	켜짐(medium)	low, medium, high
gemini-3.6-flash	켜짐(medium)	minimal, low, medium, high
gemini-3.5-flash-lite	켜짐(minimal)	minimal, low, medium, high
gemini-3.1-pro-preview	켜짐(high)	low, medium, high
gemini-3.1-flash-lite-image	켜짐(minimal)	minimal, high
gemini-3-flash-preview	켜짐(high)	minimal, low, medium, high
gemini-3-pro-preview	켜짐(high)	low, high
gemini-3.5-flash	켜짐(medium)	minimal, low, medium, high
gemini-2.5-pro	켜짐	low, medium, high
gemini-2.5-flash	켜짐	low, medium, high
gemini-2.5-flash-lite	꺼짐	low, medium, high
gemini-robotics-er-2-preview	켜짐(high)	minimal, low, medium, high

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Provide a list of 3 famous physicists and their key contributions",
    generation_config={
        "thinking_level": "low"
    }
)
print(interaction.output_text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: "Provide a list of 3 famous physicists and their key contributions",
    generation_config: {
        thinking_level: "low"
    }
});
console.log(interaction.output_text);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.GenerationConfig;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ThinkingLevel;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(
            InteractionsInput.of(
                "Provide a list of 3 famous physicists and their key contributions"))
        .generationConfig(GenerationConfig.builder().thinkingLevel(ThinkingLevel.LOW).build())
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-pro"),
            Input: interactions.NewInteractionsInput("What is the sum of the first 50 prime numbers?"),
            GenerationConfig: &interactions.GenerationConfig{
                ThinkingLevel:     interactions.ThinkingLevelHigh.ToPointer(),
                ThinkingSummaries: interactions.ThinkingSummariesAuto.ToPointer(),
            },
            Stream: genai.Ptr(true),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    stream := res.InteractionSSEStreamEvent
    defer stream.Close()

    for stream.Next() {
        event := stream.Value()
        if stepDelta := event.GetDataStepDelta(); stepDelta != nil {
            if thoughtDelta := stepDelta.GetDeltaThoughtSummary(); thoughtDelta != nil {
                if textContent := thoughtDelta.GetContentText(); textContent != nil {
                    fmt.Printf("[Thought Summary] %s\n", textContent.Text)
                }
            }
            if textDelta := stepDelta.GetDeltaText(); textDelta != nil {
                fmt.Print(textDelta.GetText())
            }
        }
    }
    if err := stream.Err(); err != nil {
        log.Fatal(err)
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: *** \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "Provide a list of 3 famous physicists and their key contributions",
    "generation_config": {
      "thinking_level": "low"
    }
  }'

토큰 한도와 max_output_tokens

max_output_tokens 생성 매개변수는 thought 토큰을 포함해 응답이 생성할 수 있는 최대 토큰 수를 설정해요.

설정되면 이 매개변수는 모델이 thinking 예산(thinking_level)을 할당하는 방식을 바꾸지 않고 인프라가 강제하는 하드 컷오프 역할을 해요.

모델이 추론 중에 이 한도에 도달하면 "incomplete" 상태로 생성을 중단하고 잘리거나 빈 출력을 반환해요(생성된 thought 토큰은 계속 청구돼요). 응답을 자르지 않고 비용이나 지연 시간을 줄이려면 작은 max_output_tokens를 설정하는 대신 thinking_level을 낮추세요(low 또는 medium).

Thought 서명

Thought 서명은 모델 내부 추론의 암호화된 표현이에요. 다중 턴 상호작용에서 추론 연속성을 유지하는 데 필요해요.

Interactions API는 generateContent API보다 thought 서명 처리를 훨씬 간단하게 만들어요.

상태 저장 모드(권장)

기본적으로 상태 저장 모드에서 Interactions API를 사용할 때(store: true를 설정하고 후속 턴에서 previous_interaction_id를 전달) 서버가 모든 thought 블록과 서명을 포함한 대화 상태를 자동으로 관리해요. 이 모드에서는 서명에 대해 아무것도 할 필요가 없어요. 서버 측에서 완전히 처리돼요.

무상태 모드

대화 상태를 직접 관리하고(무상태 모드) 각 요청에 전체 입력·출력 히스토리를 전달하는 경우:

• 모델에서 받은 그대로 모든 thought 블록을 항상 다시 전송해야 해요.
• thought 블록은 모델이 추론을 계속하는 데 필요한 서명을 포함하므로 히스토리에서 제거하거나 수정하면 안 돼요.
• 세션 내에서 모델을 전환할 때도 이전 모델의 thought 블록을 다시 전송해야 해요. 백엔드가 호환성을 관리해요.

가격

thinking이 켜져 있으면 응답 가격은 출력 토큰과 thought 토큰의 합이에요. 생성된 전체 thought 토큰 수는 total_thought_tokens 필드에서 얻을 수 있어요.

print("Thoughts tokens:", interaction.usage.total_thought_tokens)
print("Output tokens:", interaction.usage.total_output_tokens)

console.log(`Thoughts tokens: ${interaction.usage.total_thought_tokens}`);
console.log(`Output tokens: ${interaction.usage.total_output_tokens}`);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.Usage;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Explain the concept of Occam's Razor."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.usage().isPresent()) {
  Usage usage = interaction.usage().get();
  System.out.println("Thoughts tokens: " + usage.totalThoughtTokens().orElse(0));
  System.out.println("Output tokens: " + usage.totalOutputTokens().orElse(0));
}

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    // Turn 1: Execute a reasoning + tool use interaction
    turn1, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-pro"),
            Input: interactions.NewInteractionsInput("Compare the GDP growth of Japan and Germany in 2025."),
            Tools: []interactions.Tool{
                interactions.NewTool(interactions.GoogleSearch{}),
            },
            GenerationConfig: &interactions.GenerationConfig{
                ThinkingLevel: interactions.ThinkingLevelHigh.ToPointer(),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    // Turn 2: Pass PreviousInteractionID so thought signatures are automatically preserved
    turn2, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model:                 interactions.Model("gemini-3.8-pro"),
            PreviousInteractionID: turn1.Interaction.ID,
            Input:                 interactions.NewInteractionsInput("Now summarize that comparison in a 3-row markdown table."),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if turn2.Interaction.OutputText != nil {
        fmt.Println(*turn2.Interaction.OutputText)
    }
}

Thinking 모델은 최종 응답의 품질을 개선하기 위해 완전한 thought를 생성하고, 그 후 요약을 출력해 thought 과정에 대한 통찰을 제공해요. 가격은 API에서 요약만 출력되더라도 모델이 생성해야 하는 전체 thought 토큰을 기준으로 해요.

토큰에 대해 더 자세히 알아보려면 토큰 계산 가이드를 참조하세요.

모범 사례

다음 지침에 따라 thinking 모델을 효율적으로 사용하세요.

• 추론 검토: thought 요약을 분석해 실패를 이해하고 프롬프트를 개선하세요.
• thinking 예산 제어: 긴 출력에 대해서는 모델에게 덜 생각하도록 프롬프트해 토큰을 절약하세요.
• 단순 작업: 사실 조회나 분류에는 minimal 또는 low thinking을 사용하세요(예: "DeepMind는 어디에서 설립되었나요?").
• 중간 작업: 개념 비교나 창의적 추론에는 기본 thinking을 사용하세요(예: 전기차와 하이브리드차 비교).
• 복잡한 작업: 고급 코딩, 수학, 다단계 계획에는 최대 thinking을 사용하세요(예: AIME 수학 문제 풀기).

다음 단계

• 텍스트 생성: 기본 텍스트 응답
• 함수 호출: 도구에 연결
• Gemini 3 가이드: 모델별 기능

더 알아보기 (Learn more)

• 모델
• 토큰 계산
• 텍스트 생성
• 함수 호출