理解与统计 token
Gemini 和其他生成式 AI 模型以称为“粒度”的粒度处理输入和输出 token.
对于 Gemini 型号,一个 token 相当于大约 4 字符。 100 token 大约等于 60-80 英文单词。
关于token #
token可以是单个字符,例如 z 或整个单词,如 cat。长字被分成几个token。模型使用的所有token的集合称为词汇表,将文本拆分为token的过程称为 代币化.
启用计费后, 呼叫 Gemini API 的费用 部分由输入和输出 token 的数量决定,因此了解如何计算 token 会很有帮助。
计数 token #
Gemini API 的所有输入和输出均被标记化,包括文本、图像文件和其他非文本模式。
您可以通过以下方式统计token:
致电
count_tokens与请求的输入。 返回token的总数 仅输入。在发送输入之前进行此调用以检查请求的大小。使用
usage关于交互响应。 返回输入的 token 计数(total_input_tokens),输出(total_output_tokens),思考(total_thought_tokens), 缓存内容 (total_cached_tokens)、工具使用(total_tool_use_tokens) 和总计 (total_tokens).
计数文本 token #
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
prompt = "The quick brown fox jumps over the lazy dog."
# Count tokens before sending
total_tokens = client.models.count_tokens(
model="gemini-4-hydrogen",
contents=prompt
)
print("total_tokens:", total_tokens.total_tokens)
# Get usage from interaction
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input=prompt
)
print(interaction.usage)
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from '@google/genai';
const client = new GoogleGenAI({});
const prompt = "The quick brown fox jumps over the lazy dog.";
// Count tokens before sending
const countResponse = await client.models.countTokens({
model: "gemini-4-hydrogen",
contents: prompt,
});
console.log(countResponse.totalTokens);
// Get usage from interaction
const interaction = await client.interactions.create({
model: "gemini-4-hydrogen",
input: prompt,
});
console.log(interaction.usage);
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;
import com.google.genai.types.CountTokensResponse;
Client client = new Client();
String prompt = "The quick brown fox jumps over the lazy dog.";
// Count tokens before sending
CountTokensResponse countResponse =
client.models.countTokens("gemini-4-hydrogen", prompt, null);
System.out.println("total_tokens: " + countResponse.totalTokens().orElse(0));
// Get usage from interaction
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(InteractionsInput.of(prompt))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.usage().orElse(null));
package main
import (
"context"
"fmt"
"log"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, nil)
if err != nil {
log.Fatal(err)
}
modelInfo, err := client.Models.Get(ctx, "gemini-4-hydrogen", nil)
if err != nil {
log.Fatal(err)
}
fmt.Printf("Input token limit: %d\n", modelInfo.InputTokenLimit)
fmt.Printf("Output token limit: %d\n", modelInfo.OutputTokenLimit)
}
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-4-hydrogen:countTokens" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-H "Api-Revision: 2026-05-20" \
-d '{"contents": [{"parts": [{"text": "The quick brown fox."}]}]}'
计数多圈token #
使用以下方法对对话历史记录中的 token 进行计数 previous_interaction_id:
# This will only work for SDK newer than 2.0.0
# First interaction
interaction1 = client.interactions.create(
model="gemini-4-hydrogen",
input="Hi, my name is Bob"
)
# Second interaction continues the conversation
interaction2 = client.interactions.create(
model="gemini-4-hydrogen",
input="What's my name?",
previous_interaction_id=interaction1.id
)
# Usage includes tokens from both turns
print(f"Input tokens: {interaction2.usage.total_input_tokens}")
print(f"Output tokens: {interaction2.usage.total_output_tokens}")
print(f"Total tokens: {interaction2.usage.total_tokens}")
// This will only work for SDK newer than 2.0.0
// First interaction
const interaction1 = await client.interactions.create({
model: "gemini-4-hydrogen",
input: "Hi, my name is Bob"
});
// Second interaction continues the conversation
const interaction2 = await client.interactions.create({
model: "gemini-4-hydrogen",
input: "What's my name?",
previous_interaction_id: interaction1.id
});
console.log(`Input tokens: ${interaction2.usage.total_input_tokens}`);
console.log(`Output tokens: ${interaction2.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();
// First interaction
CreateModelInteraction params1 =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(InteractionsInput.of("Hi, my name is Bob"))
.build();
Interaction interaction1 =
client.interactions.create(CreateInteractionRequestBody.of(params1)).interaction().get();
// Second interaction continues the conversation
CreateModelInteraction params2 =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(InteractionsInput.of("What's my name?"))
.previousInteractionId(interaction1.id().orElse(""))
.build();
Interaction interaction2 =
client.interactions.create(CreateInteractionRequestBody.of(params2)).interaction().get();
// Usage includes tokens from both turns
if (interaction2.usage().isPresent()) {
Usage usage = interaction2.usage().get();
System.out.println("Input tokens: " + usage.totalInputTokens().orElse(0));
System.out.println("Output tokens: " + usage.totalOutputTokens().orElse(0));
System.out.println("Total tokens: " + usage.totalTokens().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)
}
prompt := "The quick brown fox jumps over the lazy dog."
// Count input tokens before sending
totalTokens, err := client.Models.CountTokens(ctx, "gemini-4-hydrogen", genai.Text(prompt), nil)
if err != nil {
log.Fatal(err)
}
fmt.Printf("total_tokens: %d\n", totalTokens.TotalTokens)
// Create the interaction and inspect the returned usage metadata
res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
Model: interactions.Model("gemini-4-hydrogen"),
Input: interactions.NewInteractionsInput(prompt),
}),
})
if err != nil {
log.Fatal(err)
}
interaction := res.Interaction
if interaction.OutputText != nil {
fmt.Println(*interaction.OutputText)
}
if interaction.Usage != nil {
if interaction.Usage.TotalInputTokens != nil {
fmt.Printf("Input tokens: %d\n", *interaction.Usage.TotalInputTokens)
}
if interaction.Usage.TotalOutputTokens != nil {
fmt.Printf("Output tokens: %d\n", *interaction.Usage.TotalOutputTokens)
}
if interaction.Usage.TotalThoughtTokens != nil {
fmt.Printf("Thought tokens: %d\n", *interaction.Usage.TotalThoughtTokens)
}
if interaction.Usage.TotalTokens != nil {
fmt.Printf("Total tokens: %d\n", *interaction.Usage.TotalTokens)
}
}
}
计数多式联运 token #
Gemini API 的所有输入均被标记化,包括图像、视频和音频。关于标记化的要点:
图片:两个维度上≤384 像素的图像计为258 token。较大的图像平铺为 768x768 像素图块,每个图块均计为 258 token。
视频:每秒263 token(适用于静态处理)。对于智能体处理,token 的用法有所不同。参见 视频 token 按处理模式的使用情况.
音频:每秒 32 token
图像 token #
# This will only work for SDK newer than 2.0.0
uploaded_file = client.files.upload(file="path/to/image.jpg")
# Count tokens for image + text
total_tokens = client.models.count_tokens(
model="gemini-4-hydrogen",
contents=["Tell me about this image", uploaded_file]
)
print(f"Total tokens: {total_tokens}")
# Generate with image
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input=[
{"type": "text", "text": "Tell me about this image"},
{"type": "image", "uri": uploaded_file.uri, "mime_type": uploaded_file.mime_type}
]
)
print(interaction.usage)
// This will only work for SDK newer than 2.0.0
const uploadedFile = await client.files.upload({
file: "path/to/image.jpg",
config: { mimeType: "image/jpeg" }
});
// Count tokens
const countResponse = await client.models.countTokens({
model: "gemini-4-hydrogen",
contents: [
{ text: "Tell me about this image" },
{ fileData: { fileUri: uploadedFile.uri, mimeType: uploadedFile.mimeType } }
]
});
console.log(countResponse.totalTokens);
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
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.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.Content;
import com.google.genai.types.CountTokensResponse;
import com.google.genai.types.File;
import com.google.genai.types.Part;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;
Client client = new Client();
File uploadedFile =
client.files.upload(
new java.io.File("path/to/image.jpg"),
UploadFileConfig.builder().mimeType("image/jpeg").build());
// Count tokens for image + text
CountTokensResponse countResponse =
client.models.countTokens(
"gemini-4-hydrogen",
Arrays.asList(
Content.fromParts(
Part.fromText("Tell me about this image"),
Part.fromUri(
uploadedFile.uri().orElse(""), uploadedFile.mimeType().orElse("image/jpeg")))),
null);
System.out.println("Total tokens: " + countResponse.totalTokens().orElse(0));
// Generate with image
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(
InteractionsInput.ofContent(
Arrays.asList(
TextContent.builder().text("Tell me about this image").build(),
ImageContent.builder()
.uri(uploadedFile.uri().orElse(""))
.mimeType(
ImageContentMimeType.of(uploadedFile.mimeType().orElse("image/jpeg")))
.build())))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.usage().orElse(null));
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-4-hydrogen"),
Input: interactions.NewInteractionsInput("Explain the history of the internet in 3 paragraphs."),
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 textDelta := stepDelta.GetDeltaText(); textDelta != nil {
fmt.Print(textDelta.GetText())
}
}
if completed := event.GetDataInteractionCompleted(); completed != nil {
usage := completed.Interaction.Usage
if usage != nil && usage.TotalTokens != nil {
fmt.Printf("\nTotal tokens: %d\n", *usage.TotalTokens)
}
}
}
if err := stream.Err(); err != nil {
log.Fatal(err)
}
}
内联数据示例:
# This will only work for SDK newer than 2.0.0
import base64
with open('image.jpg', 'rb') as f:
image_bytes = f.read()
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input=[
{"type": "text", "text": "Describe this image"},
{
"type": "image",
"data": base64.b64encode(image_bytes).decode('utf-8'),
"mime_type": "image/jpeg"
}
]
)
print(interaction.usage)
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
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.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.Base64;
Client client = new Client();
byte[] imageBytes = Files.readAllBytes(Paths.get("image.jpg"));
String base64Image = Base64.getEncoder().encodeToString(imageBytes);
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(
InteractionsInput.ofContent(
Arrays.asList(
TextContent.builder().text("Describe this image").build(),
ImageContent.builder()
.data(base64Image)
.mimeType(ImageContentMimeType.IMAGE_JPEG)
.build())))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.usage().orElse(null));
视频 token #
视频的Token计算取决于处理模式:
| 加工方式 | 采样帧数 | 每秒token数 | 60 年代视频的代币 |
|---|---|---|---|
| 静止的 (默认) | 1 FPS(所有帧) | ~100(默认低分辨率)/~300(高分辨率) | ~6,000(默认)/~18,000(高) |
| 智能体 | 动态(按需) | 变量(最多减少 88%) | 通常为 1,500 至 3,000 |
有关设置处理模式的详细信息,请参见 智能体视频理解.
要检查请求的实际 token 使用情况,请检查 interaction.usage。智能体视频 token 通过以下字段进行报告:
- 初始提示 (视频参考+用户提示):
total_input_tokens - 导航思维:
total_thought_tokens - 按需加载文字记录、帧和音频:
total_tool_use_tokens - 最终答案:
total_output_tokens
# This will only work for SDK newer than 2.0.0
import time
video_file = client.files.upload(file="path/to/video.mp4")
while not video_file.state or video_file.state.name != "ACTIVE":
print("Processing video...")
time.sleep(5)
video_file = client.files.get(name=video_file.name)
# A 60-second video is approximately 100 * 60 = 6,000 tokens
total_tokens = client.models.count_tokens(
model="gemini-4-hydrogen",
contents=["Summarize this video", video_file]
)
print(f"Total tokens: {total_tokens}")
# Generate with video
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input=[
{"type": "text", "text": "Summarize this video"},
{"type": "video", "uri": video_file.uri, "mime_type": video_file.mime_type}
]
)
print(interaction.usage)
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.TextContent;
import com.google.genai.gaos.models.interactions.VideoContent;
import com.google.genai.gaos.models.interactions.VideoContentMimeType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.Content;
import com.google.genai.types.CountTokensResponse;
import com.google.genai.types.File;
import com.google.genai.types.FileState;
import com.google.genai.types.Part;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;
Client client = new Client();
File videoFile =
client.files.upload(
new java.io.File("path/to/video.mp4"),
UploadFileConfig.builder().mimeType("video/mp4").build());
// Wait for processing
while (videoFile.state().isPresent()
&& videoFile.state().get().knownEnum() == FileState.Known.PROCESSING) {
Thread.sleep(5000);
videoFile = client.files.get(videoFile.name().orElse(""), null);
}
// A 60-second video is approximately 100 * 60 = 6,000 tokens
CountTokensResponse countResponse =
client.models.countTokens(
"gemini-4-hydrogen",
Arrays.asList(
Content.fromParts(
Part.fromText("Summarize this video"),
Part.fromUri(
videoFile.uri().orElse(""), videoFile.mimeType().orElse("video/mp4")))),
null);
System.out.println("Total tokens: " + countResponse.totalTokens().orElse(0));
// Generate with video
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(
InteractionsInput.ofContent(
Arrays.asList(
TextContent.builder().text("Summarize this video").build(),
VideoContent.builder()
.uri(videoFile.uri().orElse(""))
.mimeType(VideoContentMimeType.of(videoFile.mimeType().orElse("video/mp4")))
.build())))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.usage().orElse(null));
音频 token #
# This will only work for SDK newer than 2.0.0
audio_file = client.files.upload(file="path/to/audio.mp3")
# A 60-second audio clip is approximately 32 * 60 = 1,920 tokens
total_tokens = client.models.count_tokens(
model="gemini-4-hydrogen",
contents=["Transcribe this audio", audio_file]
)
print(f"Total tokens: {total_tokens}")
# Generate with audio
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input=[
{"type": "text", "text": "Transcribe this audio"},
{"type": "audio", "uri": audio_file.uri, "mime_type": audio_file.mime_type}
]
)
print(interaction.usage)
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AudioContent;
import com.google.genai.gaos.models.interactions.AudioContentMimeType;
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.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.Content;
import com.google.genai.types.CountTokensResponse;
import com.google.genai.types.File;
import com.google.genai.types.Part;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;
Client client = new Client();
File audioFile =
client.files.upload(
new java.io.File("path/to/audio.mp3"),
UploadFileConfig.builder().mimeType("audio/mp3").build());
// A 60-second audio clip is approximately 32 * 60 = 1,920 tokens
CountTokensResponse countResponse =
client.models.countTokens(
"gemini-4-hydrogen",
Arrays.asList(
Content.fromParts(
Part.fromText("Transcribe this audio"),
Part.fromUri(
audioFile.uri().orElse(""), audioFile.mimeType().orElse("audio/mp3")))),
null);
System.out.println("Total tokens: " + countResponse.totalTokens().orElse(0));
// Generate with audio
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(
InteractionsInput.ofContent(
Arrays.asList(
TextContent.builder().text("Transcribe this audio").build(),
AudioContent.builder()
.uri(audioFile.uri().orElse(""))
.mimeType(AudioContentMimeType.of(audioFile.mimeType().orElse("audio/mp3")))
.build())))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.usage().orElse(null));
计数系统指令 token #
系统指令被计为输入 token 的一部分:
# This will only work for SDK newer than 2.0.0
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input="Hello!",
system_instruction="You are a helpful assistant who speaks like a pirate."
)
# system_instruction tokens included in total_input_tokens
print(f"Input tokens: {interaction.usage.total_input_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.operations.CreateInteractionRequestBody;
Client client = new Client();
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(InteractionsInput.of("Hello!"))
.systemInstruction("You are a helpful assistant who speaks like a pirate.")
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
// system_instruction tokens included in total_input_tokens
if (interaction.usage().isPresent()) {
System.out.println(
"Input tokens: " + interaction.usage().get().totalInputTokens().orElse(0));
}
计数工具token #
工具(函数、代码执行、Google 搜索)也被计算在内:
# This will only work for SDK newer than 2.0.0
tools = [
{
"type": "function",
"name": "get_weather",
"description": "Get current weather",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string"}
}
}
}
]
interaction = client.interactions.create(
model="gemini-4-hydrogen",
input="What's the weather in Tokyo?",
tools=tools
)
print(f"Input tokens: {interaction.usage.total_input_tokens}")
print(f"Tool use tokens: {interaction.usage.total_tool_use_tokens}")
import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Function;
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.Tool;
import com.google.genai.gaos.models.interactions.Usage;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Map;
Client client = new Client();
Map<String, Object> locationProp = new HashMap<>();
locationProp.put("type", "string");
Map<String, Object> properties = new HashMap<>();
properties.put("location", locationProp);
Map<String, Object> schema = new HashMap<>();
schema.put("type", "object");
schema.put("properties", properties);
Tool weatherTool =
Function.builder()
.name("get_weather")
.description("Get current weather")
.parameters(schema)
.build();
CreateModelInteraction params =
CreateModelInteraction.builder()
.model(Model.of("gemini-4-hydrogen"))
.input(InteractionsInput.of("What's the weather in Tokyo?"))
.tools(Arrays.asList(weatherTool))
.build();
Interaction interaction =
client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
if (interaction.usage().isPresent()) {
Usage usage = interaction.usage().get();
System.out.println("Input tokens: " + usage.totalInputTokens().orElse(0));
System.out.println("Tool use tokens: " + usage.totalToolUseTokens().orElse(0));
}
上下文窗口 #
每个 Gemini 型号都有其可以处理的 token 的最大数量。
- Gemini 4 型号(
gemini-4-carbon,gemini-4-argon, 和gemini-4-hydrogen): 共享单个 1M-token 上下文窗口 (1,048,576token)跨越输入、思维和输出 token。默认情况下,同步响应(background=False、流式或非流式)的上限为65,536输出 token,或者您可以生成最多1,048,576token 使用 长解码。如果你输入token加上max_output_tokens超过 1,048,576 token 时,API 自动将输出限制限制为上下文窗口中的剩余空间(1,048,576减去您的输入 token)。 - Gemini 3 和 2.5 型号: 使用单独的输入(
1,048,576token)和输出(65,536token) 预算。
以编程方式获取上下文窗口大小 #
# This will only work for SDK newer than 2.0.0
model_info = client.models.get(model="gemini-4-hydrogen")
print(f"Input token limit: {model_info.input_token_limit}")
print(f"Output token limit: {model_info.output_token_limit}")
// This will only work for SDK newer than 2.0.0
const modelInfo = await client.models.get({ model: "gemini-4-hydrogen" });
console.log(`Input token limit: ${modelInfo.inputTokenLimit}`);
console.log(`Output token limit: ${modelInfo.outputTokenLimit}`);
import com.google.genai.Client;
import com.google.genai.types.Model;
Client client = new Client();
Model modelInfo = client.models.get("gemini-4-hydrogen", null);
System.out.println("Input token limit: " + modelInfo.inputTokenLimit().orElse(0));
System.out.println("Output token limit: " + modelInfo.outputTokenLimit().orElse(0));
package main
import (
"context"
"encoding/base64"
"fmt"
"log"
"os"
"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)
}
prompt := "Tell me about this instrument"
imageBytes, err := os.ReadFile("/path/to/organ.jpg")
if err != nil {
log.Fatal(err)
}
base64Image := base64.StdEncoding.EncodeToString(imageBytes)
// Count tokens before creating the interaction
parts := []*genai.Part{
genai.NewPartFromText(prompt),
genai.NewPartFromBytes(imageBytes, "image/jpeg"),
}
totalTokens, err := client.Models.CountTokens(ctx, "gemini-4-hydrogen", []*genai.Content{
genai.NewContentFromParts(parts, genai.RoleUser),
}, nil)
if err != nil {
log.Fatal(err)
}
fmt.Printf("Estimated input tokens: %d\n", totalTokens.TotalTokens)
// Create the multimodal interaction and inspect the usage metadata
res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
Model: interactions.Model("gemini-4-hydrogen"),
Input: interactions.NewInteractionsInput([]interactions.Content{
interactions.NewContent(interactions.TextContent{
Text: prompt,
}),
interactions.NewContent(interactions.ImageContent{
Data: genai.Ptr(base64Image),
MimeType: interactions.ImageContentMimeTypeImageJpeg.ToPointer(),
}),
}),
}),
})
if err != nil {
log.Fatal(err)
}
interaction := res.Interaction
if interaction.OutputText != nil {
fmt.Println(*interaction.OutputText)
}
if interaction.Usage != nil && interaction.Usage.TotalTokens != nil {
fmt.Printf("Total tokens billed: %d\n", *interaction.Usage.TotalTokens)
}
}
在上查找上下文窗口尺寸 模型 页。