Starting November 2, 2026, Firebase App Check enforcement will be required to use Firebase AI Logic. Learn more.

Model updates:

Gemini 4 Argon is now available to use with Firebase AI Logic! Learn more.
Gemini 2.5 models are limited to projects that actively used them in the past. For the Agent Platform Gemini API, these models will shut down for all projects in October 2026. To avoid service disruptions, update to a newer model (like gemini-4-argon, gemini-3.8-flash, or gemini-nano-banana-2.1). Any stable Gemini Live API 2.5 models are not impacted. Learn more.

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。

思考型

所有 Gemini 模型都採用內部「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。

思考模型提供下列設定和選項：

控制思考量
您可以設定思考等級，控制模型的「思考」量。如果優先考量是降低延遲時間或成本，這項設定就特別重要。此外，請參閱工作難度比較，判斷模型可能需要多少思考能力。
取得思考摘要
您可以啟用思考摘要，並將其納入生成的回覆中。這些摘要是模型原始思考過程的綜合版本，可讓您深入瞭解模型的內部推論過程。
處理思考簽章
Firebase AI Logic SDK 會自動為您處理思考簽章，確保模型能存取先前對話的思考脈絡，特別是在使用函式呼叫時。

請務必詳閱使用思考模型的最佳做法和提示指南。

使用思考模型的最佳做法和提示指南

建議您在 Google AI Studio 或 Agent Studio 測試提示，以便查看完整的思考過程。您可以找出模型可能出錯的部分，並調整提示，取得更一致且準確的回覆。

先輸入一般提示詞，說明所需結果，並觀察模型如何初步思考，決定回覆內容。如果回覆不符合預期，請使用下列任一提示技巧，協助模型生成更優質的回覆：

提供逐步說明
提供幾個輸入/輸出組合的範例
提供輸出內容和回覆的措辭和格式指南
提供具體驗證步驟

除了提示之外，也建議您採用下列做法：

設定系統指令，這就像是「前導提示」，在模型接觸到提示詞或使用者提供的任何其他指令之前，先加入這組指令。您可以根據特定需求和用途，引導模型的行為。
設定思考程度，控制模型可進行的思考量。如果設定較高，模型就能在需要時進行更多思考。如果設定較低的值，模型就不會「過度思考」回覆，也會保留更多總輸出詞元數量上限，用於實際回覆，並有助於降低延遲和成本。
在 Firebase 控制台中啟用 AI monitoring ，即可監控思考詞元數量，以及啟用思考功能的要求延遲時間。如果啟用思考摘要，控制台會顯示摘要，方便您查看模型的詳細推論，協助偵錯及調整提示。

控管思考量

您可以設定思考等級，控制模型在回覆前可進行的「思考」和推論程度。如果優先考量的是降低延遲時間或成本，這項設定就特別重要。

請務必查看工作難度比較，判斷模型可能需要多少思考能力。以下提供一些概略指引：

如果工作較不複雜，或您優先考量的是縮短延遲時間或降低成本，請設定較低的思考值。
執行複雜的工作時，請調高思考值。

思考程度

如要控制模型生成回覆時的思考程度，可以指定思考程度，限制模型可使用的思考詞元數量。

設定思考程度

按一下您的Gemini API供應商，即可在這個頁面查看供應商專屬內容和程式碼。

在建立 GenerativeModel 執行個體時，於 GenerationConfig 中設定思考程度。設定會在執行個體的生命週期內保留。如要針對不同要求使用不同思考等級，請建立 GenerativeModel 執行個體，並設定各個等級。

請參閱本節後續內容，瞭解思考程度支援的值。

Swift

在建立 GenerativeModel 執行個體時，於 GenerationConfig 中設定思考程度。


// ...

// Set the thinking configuration.
// Use a thinking level value appropriate for your model (example value shown here).
let generationConfig = GenerationConfig(
  thinkingConfig: ThinkingConfig(thinkingLevel: .low)
)

// Specify the config as part of creating the `GenerativeModel` instance.
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_3.x_MODEL_NAME",
  generationConfig: generationConfig
)

// ...

Kotlin

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking level value appropriate for your model (example value shown here).
val generationConfig = generationConfig {
  thinkingConfig = thinkingConfig {
      thinkingLevel = ThinkingLevel.LOW
  }
}

// Specify the config as part of creating the `GenerativeModel` instance.
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
  modelName = "GEMINI_3.x_MODEL_NAME",
  generationConfig,
)

// ...

Java

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking level value appropriate for your model (example value shown here).
ThinkingConfig thinkingConfig = new ThinkingConfig.Builder()
    .setThinkingLevel(ThinkingLevel.LOW)
    .build();

GenerationConfig generationConfig = GenerationConfig.builder()
    .setThinkingConfig(thinkingConfig)
    .build();

// Specify the config as part of creating the `GenerativeModel` instance.
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "GEMINI_3.x_MODEL_NAME",
                  /* generationConfig */ generationConfig
                );
);

// ...

Web

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Set the thinking configuration.
// Use a thinking level value appropriate for your model (example value shown here).
const generationConfig = {
  thinkingConfig: {
    thinkingLevel: ThinkingLevel.LOW
  }
};

// Specify the config as part of creating the `GenerativeModel` instance.
const model = getGenerativeModel(ai, { model: "GEMINI_3.x_MODEL_NAME", generationConfig });

// ...

Dart

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking level value appropriate for your model (example value shown here).
final thinkingConfig = ThinkingConfig.withThinkingLevel(ThinkingLevel.low);

final generationConfig = GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_3.x_MODEL_NAME',
  generationConfig: generationConfig,
);

// ...

Unity

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking level value appropriate for your model (example value shown here).
var thinkingConfig = new ThinkingConfig(thinkingLevel: ThinkingLevel.Low);

var generationConfig = new GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "GEMINI_3.x_MODEL_NAME",
  generationConfig: generationConfig
);

// ...

支援的思考程度值

下表列出您可以設定模型 thinkingLevel，為各模型設定的思考等級值。

	`MINIMAL`	`LOW`	`MEDIUM`	`HIGH`
	模型會盡可能減少使用的詞元數量，幾乎不思考低複雜度任務	模型使用的權杖數量較少，可盡量縮短延遲時間並降低成本簡單任務和高處理量任務	模型採用平衡做法中等複雜度工作	模型使用的詞元數量達到上限需要深入推論的複雜提示
Gemini 4 Argon `gemini-4-argon`	¹		(預設)
Gemini 3.x Pro `gemini-3.1-pro-preview`				(預設)
Gemini 3.x Flash `gemini-3.8-flash` `gemini-3.7-flash` `gemini-3.6-flash` `gemini-3.5-flash`	`gemini-3.8-flash` 或 `gemini-3.7-flash` 不支援 ¹		(預設)
Gemini 3.x Flash‑Lite `gemini-3.5-flash-lite` `gemini-3.1-flash-lite`	(預設)
Gemini Nano Banana 2.1 `gemini-nano-banana-2.1`			(預設)
Gemini Nano Banana 2 `gemini-3.1-flash-image`				(預設)
Gemini Nano Banana 2 Lite `gemini-3.1-flash-lite-image`	(預設)
Gemini Nano Banana Pro `gemini-3-pro-image`				(預設)

^{1 gemini-4-argon、gemini-3.8-flash 和 gemini-3.7-flash 不支援 MINIMAL 思考程度。如果將思考程度設為 MINIMAL，要求會失敗並傳回 400 錯誤。}

思考預算 (Gemini 2.5 模型)

如要控管 Gemini 2.5 模型生成回覆時的思考程度，可以指定思考預算，限制模型可使用的思考詞元數量。

設定思考預算 (Gemini 2.5 模型)

按一下您的Gemini API供應商，即可在這個頁面查看供應商專屬內容和程式碼。

在 GenerationConfig 中設定思考預算，做為建立 Gemini 2.5 模型 GenerativeModel 執行個體的一部分。設定會在執行個體的生命週期內維持不變。如要為不同要求使用不同的思考預算，請建立 GenerativeModel 執行個體，並為每個執行個體設定預算。

如要瞭解思考預算支援的值，請參閱本節後續內容。

Swift

建立 GenerativeModel 執行個體時，請在 GenerationConfig 中設定思考預算。


// ...

// Set the thinking configuration.
// Use a thinking budget value appropriate for your model (example value shown here).
let generationConfig = GenerationConfig(
  thinkingConfig: ThinkingConfig(thinkingBudget: 1024)
)

// Specify the config as part of creating the `GenerativeModel` instance.
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_2.5_MODEL_NAME",
  generationConfig: generationConfig
)

// ...

Kotlin

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking budget value appropriate for your model (example value shown here).
val generationConfig = generationConfig {
  thinkingConfig = thinkingConfig {
      thinkingBudget = 1024
  }
}

// Specify the config as part of creating the `GenerativeModel` instance.
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
  modelName = "GEMINI_2.5_MODEL_NAME",
  generationConfig,
)

// ...

Java

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking budget value appropriate for your model (example value shown here).
ThinkingConfig thinkingConfig = new ThinkingConfig.Builder()
    .setThinkingBudget(1024)
    .build();

GenerationConfig generationConfig = GenerationConfig.builder()
    .setThinkingConfig(thinkingConfig)
    .build();

// Specify the config as part of creating the `GenerativeModel` instance.
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "GEMINI_2.5_MODEL_NAME",
                  /* generationConfig */ generationConfig
                );
);

// ...

Web

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Set the thinking configuration.
// Use a thinking budget value appropriate for your model (example value shown here).
const generationConfig = {
  thinkingConfig: {
    thinkingBudget: 1024
  }
};

// Specify the config as part of creating the `GenerativeModel` instance.
const model = getGenerativeModel(ai, { model: "GEMINI_2.5_MODEL_NAME", generationConfig });

// ...

Dart

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking budget value appropriate for your model (example value shown here).
final thinkingConfig = ThinkingConfig.withThinkingBudget(1024);

final generationConfig = GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_2.5_MODEL_NAME',
  generationConfig: generationConfig,
);

// ...

Unity

在建立 GenerativeModel 執行個體時，設定 GenerationConfig 中的參數值。


// ...

// Set the thinking configuration.
// Use a thinking budget value appropriate for your model (example value shown here).
var thinkingConfig = new ThinkingConfig(thinkingBudget: 1024);

var generationConfig = new GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "GEMINI_2.5_MODEL_NAME",
  generationConfig: generationConfig
);

// ...

支援的思考預算值 (Gemini 2.5 模型)

下表列出您可以為各模型設定的思考預算值，方法是設定模型的 thinkingBudget。

模型	預設值	思考預算可用範圍		停用思考功能的值	啟用動態思考的值
模型	預設值			停用思考功能的值	啟用動態思考的值	最小值	最大值
Gemini 2.5 Pro	`8,192`	`128`	`32,768`	無法停用	`-1`
Gemini 2.5 Flash	`8,192`	`1`	`24,576`	`0`	`-1`
Gemini 2.5 Flash‑Lite	`0` (思考功能預設為停用)	`512`	`24,576`	`0` (或完全不設定思考預算)	`-1`

停用思考功能 (Gemini 2.5 模型)

對於較簡單的工作，思考能力並非必要，傳統推論就足夠。此外，如果降低延遲時間或成本是首要考量，您可能不希望模型花費更多時間或成本來生成回覆。

在這種情況下，您可以停用 (或關閉) 部分模型的思考功能：

Gemini 2.5 Pro：無法停用思考功能
Gemini 2.5 Flash：將 thinkingBudget 設為 0 個詞元，即可停用思考功能
Gemini 2.5 Flash‑Lite：思考功能預設為停用 (因此請勿明確設定 thinkingBudget，或直接設為 0)

請注意，所有 Gemini 3.x 和後續模型無法停用思考功能。

啟用動態思考功能 (Gemini 2.5 模型)

啟用動態思考功能後，模型會自行決定思考時機和程度 (上限為思考預算，詳情請見下文)。

將 thinkingBudget 設為 -1，啟用動態思考功能。
啟用動態思考功能時，思考詞元數量上限一律為 8,192 個。

請注意，所有 Gemini 3.x 和後續模型一律會使用動態思考。

所有思考模型的工作複雜度

簡單任務：不需要太多思考
不需要複雜推論的簡單要求，例如檢索事實或分類。範例：
- 「DeepMind 是在哪裡創立的？」
- 「這封電子郵件是要求開會，還是只是提供資訊？」
中等難度工作：可能需要思考
常見要求，需要一定程度的逐步處理或深入理解。範例：
- 「用光合作用比喻成長。」
- 「比較電動車和油電混合車的異同。」
困難任務：可能需要最大程度的思考
真正複雜的挑戰，例如解決複雜的數學問題或程式設計任務。這類工作需要模型充分發揮推論和規劃能力，通常要經過許多內部步驟才能提供答案。範例：
- 「Solve problem 1 in AIME 2025: Find the sum of all integer bases b > 9 for which 17b is a divisor of 97b.」
- 「為網頁應用程式編寫 Python 程式碼，以視覺化方式呈現即時股市資料，包括使用者驗證。請盡可能提高效率。」

想法重點摘要

思考摘要是模型原始想法的合成版本，可深入瞭解模型的內部推論過程。

在回覆中加入思考摘要有以下好處：

您可以在應用程式的使用者介面中顯示思考摘要，或讓使用者存取。思考摘要會以獨立部分的形式傳回，方便您控管在應用程式中的使用方式。
如果您也在 Firebase 控制台中啟用 AI monitoring，控制台就會顯示思考摘要，方便您查看模型的詳細推論，協助您偵錯及調整提示。

以下是思考摘要的重要注意事項：

思考摘要不受思考預算控制 (預算僅適用於模型的原始思考)。不過，如果停用思考功能，模型就不會傳回思考摘要。
思考摘要會視為模型一般生成的文字回覆，並計為輸出詞元。

啟用思考過程摘要

按一下您的Gemini API供應商，即可在這個頁面查看供應商專屬內容和程式碼。

如要啟用思考摘要，請在模型設定中將 includeThoughts 設為 true。接著，您可以查看回應中的 thoughtSummary 欄位，存取摘要。

以下範例說明如何啟用思考摘要，並在回覆中擷取：

Swift

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
let generationConfig = GenerationConfig(
  thinkingConfig: ThinkingConfig(includeThoughts: true)
)

// Specify the config as part of creating the `GenerativeModel` instance.
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  generationConfig: generationConfig
)

let response = try await model.generateContent("solve x^2 + 4x + 4 = 0")

// Handle the response that includes thought summaries.
if let thoughtSummary = response.thoughtSummary {
  print("Thought Summary: \(thoughtSummary)")
}
guard let text = response.text else {
  fatalError("No text in response.")
}
print("Answer: \(text)")

Kotlin

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
val generationConfig = generationConfig {
  thinkingConfig = thinkingConfig {
      includeThoughts = true
  }
}

// Specify the config as part of creating the `GenerativeModel` instance.
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
  modelName = "GEMINI_MODEL_NAME",
  generationConfig,
)

val response = model.generateContent("solve x^2 + 4x + 4 = 0")

// Handle the response that includes thought summaries.
response.thoughtSummary?.let {
    println("Thought Summary: $it")
}
response.text?.let {
    println("Answer: $it")
}

Java

在建立 GenerativeModel 執行個體時，於 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
ThinkingConfig thinkingConfig = new ThinkingConfig.Builder()
    .setIncludeThoughts(true)
    .build();

GenerationConfig generationConfig = GenerationConfig.builder()
    .setThinkingConfig(thinkingConfig)
    .build();

// Specify the config as part of creating the `GenerativeModel` instance.
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "GEMINI_MODEL_NAME",
                  /* generationConfig */ generationConfig
                );
);

// Handle the response that includes thought summaries.
ListenableFuture responseFuture = model.generateContent("solve x^2 + 4x + 4 = 0");
Futures.addCallback(responseFuture, new FutureCallback() {
    @Override
    public void onSuccess(GenerateContentResponse response) {
        if (response.getThoughtSummary() != null) {
            System.out.println("Thought Summary: " + response.getThoughtSummary());
        }
        if (response.getText() != null) {
            System.out.println("Answer: " + response.getText());
        }
    }

    @Override
    public void onFailure(Throwable t) {
        // Handle error
    }
}, MoreExecutors.directExecutor());

Web

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
const generationConfig = {
  thinkingConfig: {
    includeThoughts: true
  }
};

// Specify the config as part of creating the `GenerativeModel` instance.
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", generationConfig });

const result = await model.generateContent("solve x^2 + 4x + 4 = 0");
const response = result.response;

// Handle the response that includes thought summaries.
if (response.thoughtSummary()) {
    console.log(`Thought Summary: ${response.thoughtSummary()}`);
}
const text = response.text();
console.log(`Answer: ${text}`);

Dart

在建立 GenerativeModel 執行個體時，於 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
final thinkingConfig = ThinkingConfig(includeThoughts: true);

final generationConfig = GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  generationConfig: generationConfig,
);

final response = await model.generateContent([Content.text('solve x^2 + 4x + 4 = 0')]);

// Handle the response that includes thought summaries.
if (response.thoughtSummary != null) {
  print('Thought Summary: ${response.thoughtSummary}');
}
if (response.text != null) {
  print('Answer: ${response.text}');
}

Unity

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
var thinkingConfig = new ThinkingConfig(includeThoughts: true);

var generationConfig = new GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  generationConfig: generationConfig
);

var response = await model.GenerateContentAsync("solve x^2 + 4x + 4 = 0");

// Handle the response that includes thought summaries.
if (response.ThoughtSummary != null) {
    Debug.Log($"Thought Summary: {response.ThoughtSummary}");
}
if (response.Text != null) {
    Debug.Log($"Answer: {response.Text}");
}

查看回覆和想法摘要

# 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).

# Example Thought Summary:
#     **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.

串流想法重點摘要

如果選擇使用 generateContentStream 串流回覆，也可以查看思考摘要。系統會在生成回覆時，傳回滾動式遞增摘要。

Swift

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
let generationConfig = GenerationConfig(
  thinkingConfig: ThinkingConfig(includeThoughts: true)
)

// Specify the config as part of creating the `GenerativeModel` instance.
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  generationConfig: generationConfig
)

let stream = try model.generateContentStream("solve x^2 + 4x + 4 = 0")

// Handle the streamed response that includes thought summaries.
var thoughts = ""
var answer = ""
for try await response in stream {
  if let thought = response.thoughtSummary {
    if thoughts.isEmpty {
      print("--- Thoughts Summary ---")
    }
    print(thought)
    thoughts += thought
  }

  if let text = response.text {
    if answer.isEmpty {
      print("--- Answer ---")
    }
    print(text)
    answer += text
  }
}

Kotlin

在建立 GenerativeModel 執行個體時，於 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
val generationConfig = generationConfig {
  thinkingConfig = thinkingConfig {
      includeThoughts = true
  }
}

// Specify the config as part of creating the `GenerativeModel` instance.
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
  modelName = "GEMINI_MODEL_NAME",
  generationConfig,
)

// Handle the streamed response that includes thought summaries.
var thoughts = ""
var answer = ""
model.generateContentStream("solve x^2 + 4x + 4 = 0").collect { response ->
    response.thoughtSummary?.let {
        if (thoughts.isEmpty()) {
            println("--- Thoughts Summary ---")
        }
        print(it)
        thoughts += it
    }
    response.text?.let {
        if (answer.isEmpty()) {
            println("--- Answer ---")
        }
        print(it)
        answer += it
    }
}

Java

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
ThinkingConfig thinkingConfig = new ThinkingConfig.Builder()
    .setIncludeThoughts(true)
    .build();

GenerationConfig generationConfig = GenerationConfig.builder()
    .setThinkingConfig(thinkingConfig)
    .build();

// Specify the config as part of creating the `GenerativeModel` instance.
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "GEMINI_MODEL_NAME",
                  /* generationConfig */ generationConfig
                );
);

// Streaming with Java is complex and depends on the async library used.
// This is a conceptual example using a reactive stream.
Flowable responseStream = model.generateContentStream("solve x^2 + 4x + 4 = 0");

// Handle the streamed response that includes thought summaries
StringBuilder thoughts = new StringBuilder();
StringBuilder answer = new StringBuilder();

responseStream.subscribe(response -> {
    if (response.getThoughtSummary() != null) {
        if (thoughts.length() == 0) {
            System.out.println("--- Thoughts Summary ---");
        }
        System.out.print(response.getThoughtSummary());
        thoughts.append(response.getThoughtSummary());
    }
    if (response.getText() != null) {
        if (answer.length() == 0) {
            System.out.println("--- Answer ---");
        }
        System.out.print(response.getText());
        answer.append(response.getText());
    }
}, throwable -> {
    // Handle error
});

Web

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
const generationConfig = {
  thinkingConfig: {
    includeThoughts: true
  }
};

// Specify the config as part of creating the `GenerativeModel` instance.
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", generationConfig });

const result = await model.generateContentStream("solve x^2 + 4x + 4 = 0");

// Handle the streamed response that includes thought summaries.
let thoughts = "";
let answer = "";
for await (const chunk of result.stream) {
  if (chunk.thoughtSummary()) {
    if (thoughts === "") {
      console.log("--- Thoughts Summary ---");
    }
    // In Node.js, process.stdout.write(chunk.thoughtSummary()) could be used
    // to avoid extra newlines.
    console.log(chunk.thoughtSummary());
    thoughts += chunk.thoughtSummary();
  }

  const text = chunk.text();
  if (text) {
    if (answer === "") {
      console.log("--- Answer ---");
    }
    // In Node.js, process.stdout.write(text) could be used.
    console.log(text);
    answer += text;
  }
}

Dart

在建立 GenerativeModel 執行個體時，於 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
final thinkingConfig = ThinkingConfig(includeThoughts: true);

final generationConfig = GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  generationConfig: generationConfig,
);

final responses = model.generateContentStream([Content.text('solve x^2 + 4x + 4 = 0')]);

// Handle the streamed response that includes thought summaries.
var thoughts = '';
var answer = '';
await for (final response in responses) {
  if (response.thoughtSummary != null) {
    if (thoughts.isEmpty) {
      print('--- Thoughts Summary ---');
    }
    thoughts += response.thoughtSummary!;
  }
  if (response.text != null) {
    if (answer.isEmpty) {
      print('--- Answer ---');
    }
    answer += response.text!;
  }
}

Unity

建立 GenerativeModel 執行個體時，在 GenerationConfig 中啟用思考摘要。


// ...

// Set the thinking configuration.
// Optionally enable thought summaries in the generated response (default is false).
var thinkingConfig = new ThinkingConfig(includeThoughts: true);

var generationConfig = new GenerationConfig(
  thinkingConfig: thinkingConfig
);

// Specify the config as part of creating the `GenerativeModel` instance.
var model = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  generationConfig: generationConfig
);

var stream = model.GenerateContentStreamAsync("solve x^2 + 4x + 4 = 0");

// Handle the streamed response that includes thought summaries.
var thoughts = "";
var answer = "";
await foreach (var response in stream)
{
    if (response.ThoughtSummary != null)
    {
        if (string.IsNullOrEmpty(thoughts))
        {
            Debug.Log("--- Thoughts Summary ---");
        }
        Debug.Log(response.ThoughtSummary);
        thoughts += response.ThoughtSummary;
    }
    if (response.Text != null)
    {
        if (string.IsNullOrEmpty(answer))
        {
            Debug.Log("--- Answer ---");
        }
        Debug.Log(response.Text);
        answer += response.Text;
    }
}

想法簽名

在多輪互動中使用思考功能時，模型無法存取先前對話的思考內容。不過，如果使用呼叫函式，可以利用思考簽章，在不同對話輪次之間保留思考脈絡。思考簽章是模型內部思考過程的加密表示法，在使用思考和呼叫函式時可用。具體來說，系統會在下列情況產生思考簽章：

思考功能已啟用，且已生成思考內容。
要求包含函式宣告。

如要使用思考簽章，請照常呼叫函式。Firebase AI Logic SDK 會管理狀態，並自動處理思考簽章，簡化流程。SDK 會在 Chat 工作階段中，自動將產生的思考簽章傳遞至後續的 sendMessage 或 sendMessageStream 呼叫。

思考詞元的計價和計算方式

思考詞元的定價與文字輸出詞元相同。如果啟用思考摘要，系統會將其視為思考詞元，並據此計費。

您可以在 Firebase 控制台啟用 AI monitoring，監控已啟用思考功能的要求，查看思考詞元數量。

您可以從回應 usageMetadata 屬性的 thoughtsTokenCount 欄位，取得思考詞元總數：

Swift

// ...

let response = try await model.generateContent("Why is the sky blue?")

if let usageMetadata = response.usageMetadata {
  print("Thoughts Token Count: \(usageMetadata.thoughtsTokenCount)")
}

Kotlin

// ...

val response = model.generateContent("Why is the sky blue?")

response.usageMetadata?.let { usageMetadata ->
    println("Thoughts Token Count: ${usageMetadata.thoughtsTokenCount}")
}

Java

// ...

ListenableFuture<GenerateContentResponse> response =
    model.generateContent("Why is the sky blue?");

Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        String usageMetadata = result.getUsageMetadata();
        if (usageMetadata != null) {
            System.out.println("Thoughts Token Count: " +
                usageMetadata.getThoughtsTokenCount());
        }
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

Web

// ...

const response = await model.generateContent("Why is the sky blue?");

if (response?.usageMetadata?.thoughtsTokenCount != null) {
    console.log(`Thoughts Token Count: ${response.usageMetadata.thoughtsTokenCount}`);
}

Dart

// ...

final response = await model.generateContent(
  Content.text("Why is the sky blue?"),
]);

if (response?.usageMetadata case final usageMetadata?) {
  print("Thoughts Token Count: ${usageMetadata.thoughtsTokenCount}");
}

Unity

// ...

var response = await model.GenerateContentAsync("Why is the sky blue?");

if (response.UsageMetadata != null)
{
    UnityEngine.Debug.Log($"Thoughts Token Count: {response.UsageMetadata?.ThoughtsTokenCount}");
}

如要進一步瞭解權杖，請參閱計算權杖指南。

思考型 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

使用思考模型的最佳做法和提示指南

控管思考量

思考程度

設定思考程度

Swift

Kotlin

Java

Web

Dart

Unity

支援的思考程度值

思考預算 (Gemini 2.5 模型)

設定思考預算 (Gemini 2.5 模型)

Swift

Kotlin

Java

Web

Dart

Unity

支援的思考預算值 (Gemini 2.5 模型)

停用思考功能 (Gemini 2.5 模型)

啟用動態思考功能 (Gemini 2.5 模型)

所有思考模型的工作複雜度

想法重點摘要

啟用思考過程摘要

Swift

Kotlin

Java

Web

Dart

Unity

串流想法重點摘要

Swift

Kotlin

Java

Web

Dart

Unity

想法簽名

思考詞元的計價和計算方式

Swift

Kotlin

Java

Web

Dart

Unity

思考型