Gemini 4 Argon 現已推出，立即試用。

Google 會運用 AI 技術將內容翻譯成你偏好的語言，但可能會出錯。

Gemini 思考

Gemini 模型會使用「思考程序」，大幅提升推論和多步驟規劃能力，因此能有效處理程式設計、進階數學和資料分析等複雜工作。

使用思考模型時，Gemini 會先進行內部推論，再做出回覆。Interactions API 會透過 thought 步驟呈現這項推論，這些專屬步驟會與 steps 陣列中的函式呼叫、使用者輸入內容或模型輸出內容，按照時間順序顯示。

每個思考步驟都包含兩個欄位：

欄位	必要	說明
`signature`	✅ 是	模型內部推理狀態的加密表示法。一律會顯示，即使模型只執行最少的推理作業。
`summary`	❌ 否	內容陣列 (文字和/或圖片)，用於總結推論。視 `thinking_summaries` 設定、模型是否進行足夠的推理，或內容類型而定，可能為空白 (例如，圖片潛在空間可能沒有文字摘要)。

與思考過程互動

與思考模型互動的程序與其他互動要求類似。在 model 欄位中，指定支援思考輔助功能的模型：

Python

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)

JavaScript

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);

Java

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(""));

Go

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("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)
    }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_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."
  }'

想法重點摘要

想法摘要可深入瞭解模型的內部推論過程。根據預設，系統只會傳回最終輸出內容。您可以使用 thinking_summaries 啟用思考摘要：

Python

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()

JavaScript

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);
            }
        }
    }
}

Java

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();
      }
    }
  }
}

Go

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)
    }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_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"
    }
  }'

在下列情況下，想法區塊可能只包含簽名，沒有摘要：

簡單要求：模型未充分推理，因此無法生成摘要
thinking_summaries: "none"，明確停用摘要功能
某些想法內容類型 (例如圖片) 可能沒有文字摘要

您的程式碼應一律處理 summary 為空或不存在的思考區塊。

思考時串流

在生成期間使用串流功能，逐步接收想法摘要。思考區塊會透過伺服器傳送事件 (SSE) 傳送，並有兩種不同的差異類型：

差異類型	包含	傳送時間
`thought_summary`	文字或圖片摘要內容	一或多個差異，附有增量摘要
`thought_signature`	密碼編譯簽章	`step.stop`之前的最後一個增量

Python

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

JavaScript

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;
        }
    }
}

Java

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);
        }
      }
    }
  }
}

Go

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)
    }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_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
  }'

串流回覆會使用伺服器傳送事件 (SSE)，並由步驟和事件組成，例如：

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]

控制思考

Gemini 模型預設會進行動態思考，根據要求的複雜程度，自動調整推論工作量。您可以使用 thinking_level 參數控制這項行為。

模型	預設思考	支援的層級
gemini-4-argon	開啟 (中)	低、中、高
gemini-3.8-flash	開啟 (中)	低、中、高
gemini-3.6-flash	開啟 (中)	極低、低、中、高
gemini-3.5-flash-lite	開啟 (極簡)	極低、低、中、高
gemini-3.1-pro-preview	開啟 (高)	低、中、高
gemini-3.1-flash-lite-image	開啟 (極簡)	極低、高
gemini-3-flash-preview	開啟 (高)	極低、低、中、高
gemini-3-pro-preview	開啟 (高)	低、高
gemini-2.5-pro	開啟	低、中、高
gemini-2.5-flash	開啟	低、中、高
gemini-2.5-flash-lite	關閉	低、中、高
gemini-robotics-er-2-preview	開啟 (高)	極低、低、中、高

Python

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)

JavaScript

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);

Java

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(""));

Go

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)
    }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_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"
    }
  }'

詞元數量上限和`max_output_tokens`

max_output_tokens 生成參數會設定回覆可生成的詞元數量上限，包括思考詞元。

設定後，這項參數會做為基礎架構強制執行的硬性截斷，不會改變模型分配思考預算 (thinking_level) 的方式。

如果模型在推理時達到這項限制，就會停止生成內容，並傳回 "incomplete" 狀態和截斷或空白的輸出內容 (但仍會針對產生的任何思考詞元計費)。如要降低成本或延遲時間，同時避免截斷回覆，請降低 thinking_level (low 或 medium)，而非設定較小的 max_output_tokens。

使用 Gemini 4 模型 (gemini-4-argon) 時，請注意下列脈絡和輸出內容限制：

共用 100 萬個詞元的脈絡窗口：輸入、思考和輸出詞元共用 100 萬個詞元的脈絡窗口 (1,048,576 個詞元)。如果輸入的詞元加上 max_output_tokens 超過 1,048,576 個詞元，API 會自動將輸出上限設為脈絡窗口的剩餘空間 (1,048,576 減去輸入的詞元)。
預設同步輸出上限 (64K)：當 background=False (適用於串流和非串流要求) 的預設和最大 max_output_tokens 上限為 65,536 個權杖。使用 background=False 設定 max_output_tokens > 65536 會傳回 400 錯誤。
長解碼 (最多 100 萬個詞元)：如要讓 Gemini 4 推論及生成超過 65,536 個詞元 (最多 1,048,576 個詞元)，請設定 background=True，並將 max_output_tokens 設為大於 65,536。詳情請參閱「長時間解碼」。

想法簽名

思考簽章是模型內部推理的加密表示法。在多輪互動中，模型必須維持推論的連貫性。

相較於 generateContent API，Interactions API 處理思考簽章的方式更簡單。

有狀態模式 (建議)

根據預設，在有狀態模式下使用 Interactions API 時 (設定 store: true 並在後續回合中傳遞 previous_interaction_id)，伺服器會自動管理對話狀態，包括所有想法區塊和簽章。在這個模式下，您不需要對簽名執行任何操作。這些作業完全在伺服器端處理。

無狀態模式

如果您自行管理對話狀態 (無狀態模式)，並在每個要求中傳遞完整的輸入和輸出記錄：

您必須一律重新傳送所有 thought 區塊，且內容必須與從模型收到的完全相同。
請勿從記錄中移除或修改想法區塊，因為這些區塊包含模型繼續推理所需的簽章。
在工作階段中切換模型時，仍應重新傳送先前模型的思考區塊。後端會管理相容性。

定價

開啟思考功能後，回覆價格為輸出詞元和思考詞元的總和。您可以從 total_thought_tokens 欄位取得生成的思考詞元總數。

Python

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

JavaScript

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

Java

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));
}

Go

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)
    }
}

思考型模型會生成完整想法，提升最終回覆的品質，然後輸出摘要，讓您瞭解思考過程。即使 API 只會輸出摘要，但計價依據仍是模型需要生成的所有思考權杖。

如要進一步瞭解權杖，請參閱「權杖計數」指南。

最佳做法

請遵循下列指南，有效率地使用思考型模型。

查看推論過程：分析思考摘要，瞭解失敗原因並改良提示。
控管思考預算：提示模型減少思考，以節省詞元。
簡單工作：使用「極少」或「低」思考模式，擷取事實或分類 (例如「DeepMind 在哪裡創立？」)。
中等難度工作：使用預設思考模式比較概念或進行創意推理 (例如比較電動車和油電混合車)。
複雜工作：使用最大思考時間，處理進階程式設計、數學或多步驟規劃 (例如解決 AIME 數學問題)。

後續步驟

生成文字：基本文字回覆
函式呼叫：連結工具
Gemini 4 指南：Gemini 4 的新功能
Gemini 3 指南：模型專屬功能

Gemini 思考

與思考過程互動

Python

JavaScript

Java

Go

REST

想法重點摘要

Python

JavaScript

Java

Go

REST

思考時串流

Python

JavaScript

Java

Go

REST

控制思考

Python

JavaScript

Java

Go

REST

詞元數量上限和max_output_tokens

想法簽名

有狀態模式 (建議)

無狀態模式

定價

Python

JavaScript

Java

Go

最佳做法

後續步驟

詞元數量上限和`max_output_tokens`