O Gemini 3.8 Flash já está disponível. Faça um teste.

O Google usa tecnologia de IA na tradução de conteúdos para seu idioma de preferência. As traduções com IA podem ter erros.

Compreensão de imagens

Os modelos do Gemini foram desenvolvidos para serem multimodais desde o início, permitindo uma ampla variedade de tarefas de processamento de imagens e visão computacional, incluindo, entre outras, legendagem de imagens, classificação e Resposta visual a perguntas, sem precisar treinar modelos especializados de ML.

Além das funcionalidades multimodais gerais, os modelos do Gemini oferecem maior precisão para casos de uso específicos, como detecção de objetos e segmentação, por meio de treinamento adicional.

Enviar imagens para o Gemini

É possível fornecer imagens como entrada para o Gemini usando vários métodos:

Transmitir imagem usando URL: ideal para imagens acessíveis publicamente.
Transmissão de dados de imagem inline: para dados de imagem codificados em base64.
Fazer upload de imagens usando a API File: recomendado para arquivos maiores ou para reutilizar imagens em várias solicitações.

Transmitir imagem usando URL

É possível fazer upload de uma imagem usando a API Files e transmiti-la na solicitação:

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="path/to/organ.jpg")

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": "Caption this image."},
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const uploadedFile = await client.files.upload({
    file: "path/to/organ.jpg",
    config: { mimeType: "image/jpeg" }
});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: [
        {type: "text", text: "Caption this image."},
        {
            type: "image",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.output_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.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.File;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

File uploadedFile =
    client.files.upload(
        new java.io.File("path/to/organ.jpg"),
        UploadFileConfig.builder().mimeType("image/jpeg").build());

Content textContent = TextContent.builder().text("Caption this image.").build();
Content imageContent =
    ImageContent.builder()
        .uri(uploadedFile.uri().orElse(""))
        .mimeType(ImageContentMimeType.of(uploadedFile.mimeType().orElse("image/jpeg")))
        .build();

List<Content> contents = Arrays.asList(textContent, imageContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .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)
    }

    uploadedFile, err := client.Files.UploadFromPath(ctx, "path/to/organ.jpg", &genai.UploadFileConfig{
        MIMEType: "image/jpeg",
    })
    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([]interactions.Content{
                interactions.NewContent(interactions.TextContent{
                    Text: "Caption this image.",
                }),
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr(uploadedFile.URI),
                    MimeType: interactions.ImageContentMimeType(uploadedFile.MIMEType).ToPointer(),
                }),
            }),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

REST

# First upload the file using the Files API, then use the URI:
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": [
      {"type": "text", "text": "Caption this image."},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Como transmitir dados de imagem inline

É possível fornecer dados de imagem como strings codificadas em base64:

Python

import base64
from google import genai

with open('path/to/small-sample.jpg', 'rb') as f:
    image_bytes = f.read()

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": "Caption this image."},
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/jpeg"
        }
    ]
)
print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const client = new GoogleGenAI({});
const base64ImageFile = fs.readFileSync("path/to/small-sample.jpg", {
  encoding: "base64",
});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: [
        {type: "text", text: "Caption this image."},
        {
            type: "image",
            data: base64ImageFile,
            mime_type: "image/jpeg"
        }
    ]
});
console.log(interaction.output_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.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;
import java.util.List;

byte[] imageBytes = Files.readAllBytes(Paths.get("path/to/small-sample.jpg"));
String base64Image = Base64.getEncoder().encodeToString(imageBytes);

Client client = new Client();

Content textContent = TextContent.builder().text("Caption this image.").build();
Content imageContent =
    ImageContent.builder()
        .data(base64Image)
        .mimeType(ImageContentMimeType.IMAGE_JPEG)
        .build();

List<Content> contents = Arrays.asList(textContent, imageContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

Go

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)
    }

    imageBytes, err := os.ReadFile("path/to/small-sample.jpg")
    if err != nil {
        log.Fatal(err)
    }
    base64Image := base64.StdEncoding.EncodeToString(imageBytes)

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput([]interactions.Content{
                interactions.NewContent(interactions.TextContent{
                    Text: "Caption this image.",
                }),
                interactions.NewContent(interactions.ImageContent{
                    Data:     genai.Ptr(base64Image),
                    MimeType: interactions.ImageContentMimeTypeImageJpeg.ToPointer(),
                }),
            }),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

REST

IMG_PATH="/path/to/your/image1.jpg"

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {"type": "text", "text": "Caption this image."},
      {
        "type": "image",
        "data": "'"$(base64 $B64FLAGS $IMG_PATH)"'",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Como fazer upload de imagens usando a API File

Para arquivos grandes ou para usar o mesmo arquivo de imagem várias vezes, use a API Files. Consulte o guia da API Files.

Python

from google import genai

client = genai.Client()

my_file = client.files.upload(file="path/to/sample.jpg")

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": "Caption this image."},
        {
            "type": "image",
            "uri": my_file.uri,
            "mime_type": my_file.mime_type
        }
    ]
)
print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const myfile = await client.files.upload({
    file: "path/to/sample.jpg",
    config: { mimeType: "image/jpeg" },
});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: [
        {type: "text", text: "Caption this image."},
        {
            type: "image",
            uri: myfile.uri,
            mime_type: myfile.mimeType
        }
    ]
});
console.log(interaction.output_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.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.File;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

File myFile =
    client.files.upload(
        new java.io.File("path/to/sample.jpg"),
        UploadFileConfig.builder().mimeType("image/jpeg").build());

Content textContent = TextContent.builder().text("Caption this image.").build();
Content imageContent =
    ImageContent.builder()
        .uri(myFile.uri().orElse(""))
        .mimeType(ImageContentMimeType.of(myFile.mimeType().orElse("image/jpeg")))
        .build();

List<Content> contents = Arrays.asList(textContent, imageContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .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)
    }

    myFile, err := client.Files.UploadFromPath(ctx, "path/to/sample.jpg", &genai.UploadFileConfig{
        MIMEType: "image/jpeg",
    })
    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([]interactions.Content{
                interactions.NewContent(interactions.TextContent{
                    Text: "Caption this image.",
                }),
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr(myFile.URI),
                    MimeType: interactions.ImageContentMimeType(myFile.MIMEType).ToPointer(),
                }),
            }),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

REST

# First upload the file (see Files API guide for details)
# Then use the file URI in the request:

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": [
      {"type": "text", "text": "Caption this image."},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Comandos com várias imagens

É possível fornecer várias imagens em um único comando incluindo vários objetos de imagem na matriz input:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": "What is different between these two images?"},
        {
            "type": "image",
            "uri": "https://example.com/image1.jpg",
            "mime_type": "image/jpeg"
        },
        {
            "type": "image",
            "uri": "https://example.com/image2.jpg",
            "mime_type": "image/jpeg"
        }
    ]
)
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: [
        {type: "text", text: "What is different between these two images?"},
        {
            type: "image",
            uri: "https://example.com/image1.jpg",
            mime_type: "image/jpeg"
        },
        {
            type: "image",
            uri: "https://example.com/image2.jpg",
            mime_type: "image/jpeg"
        }
    ]
});
console.log(interaction.output_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.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.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent =
    TextContent.builder().text("What is different between these two images?").build();
Content image1 =
    ImageContent.builder()
        .uri("https://example.com/image1.jpg")
        .mimeType(ImageContentMimeType.IMAGE_JPEG)
        .build();
Content image2 =
    ImageContent.builder()
        .uri("https://example.com/image2.jpg")
        .mimeType(ImageContentMimeType.IMAGE_JPEG)
        .build();

List<Content> contents = Arrays.asList(textContent, image1, image2);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .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([]interactions.Content{
                interactions.NewContent(interactions.TextContent{
                    Text: "What is different between these two images?",
                }),
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr("https://example.com/image1.jpg"),
                    MimeType: interactions.ImageContentMimeTypeImageJpeg.ToPointer(),
                }),
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr("https://example.com/image2.jpg"),
                    MimeType: interactions.ImageContentMimeTypeImageJpeg.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": [
      {"type": "text", "text": "What is different between these two images?"},
      {
        "type": "image",
        "uri": "https://example.com/image1.jpg",
        "mime_type": "image/jpeg"
      },
      {
        "type": "image",
        "uri": "https://example.com/image2.jpg",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Detecção de objetos

Os modelos são treinados para detectar objetos em uma imagem e receber as coordenadas da caixa delimitadora. As coordenadas, relativas às dimensões da imagem, são dimensionadas para [0, 1000]. É preciso reduzir a escala dessas coordenadas com base no tamanho da imagem original.

Python

from google import genai
from pydantic import BaseModel, Field
from typing import List
import json

client = genai.Client()
prompt = "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."

class BoundingBox(BaseModel):
    box_2d: List[int] = Field(description="The 2D bounding box of the item as [ymin, xmin, ymax, xmax] normalized to 0-1000.")
    mask: List[List[int]] = Field(description="The segmentation mask of the item as a polygon of [x,y] coordinates, normalized to 0-1000.")
    label: str = Field(description="A descriptive label for the item.")

class BoundingBoxes(BaseModel):
    boxes: List[BoundingBox]

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": prompt},
        {
            "type": "image",
            "uri": "https://example.com/image.png",
            "mime_type": "image/png"
        }
    ],
    response_format={
        "type": "text",
        "mime_type": "application/json",
        "schema": BoundingBoxes.model_json_schema()
    }
)

bounding_boxes = BoundingBoxes.model_validate_json(interaction.output_text)
print(bounding_boxes)

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as z from "zod";

const client = new GoogleGenAI({});
const prompt = "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000.";

const boundingBoxesSchema = z.object({
  boxes: z.array(z.object({
    box_2d: z.array(z.number()),
    mask: z.array(z.array(z.number())),
    label: z.string()
  }))
});

const interaction = await client.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    { type: "text", text: prompt },
    {
      type: "image",
      uri: "https://example.com/image.png",
      mime_type: "image/png"
    }
  ],
  response_format: {
    type: 'text',
    mime_type: 'application/json',
    schema: z.toJSONSchema(boundingBoxesSchema)
  },
});

const result = boundingBoxesSchema.parse(JSON.parse(interaction.output_text));
console.log(result);

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.CreateModelInteractionResponseFormat;
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.ResponseFormat;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.interactions.TextResponseFormat;
import com.google.genai.gaos.models.interactions.TextResponseFormatMimeType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;
import java.util.Map;

Client client = new Client();
String prompt =
    "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000.";

Map<String, Object> boundingBoxSchema =
    Map.of(
        "type", "object",
        "properties",
            Map.of(
                "box_2d",
                    Map.of(
                        "type", "array",
                        "items", Map.of("type", "integer"),
                        "description",
                            "The 2D bounding box of the item as [ymin, xmin, ymax, xmax] normalized to 0-1000."),
                "mask",
                    Map.of(
                        "type", "array",
                        "items", Map.of("type", "array", "items", Map.of("type", "integer")),
                        "description",
                            "The segmentation mask of the item as a polygon of [x,y] coordinates, normalized to 0-1000."),
                "label",
                    Map.of("type", "string", "description", "A descriptive label for the item.")),
        "required", List.of("box_2d", "mask", "label"));

Map<String, Object> boundingBoxesSchema =
    Map.of(
        "type", "object",
        "properties", Map.of("boxes", Map.of("type", "array", "items", boundingBoxSchema)),
        "required", List.of("boxes"));

CreateModelInteractionResponseFormat format =
    CreateModelInteractionResponseFormat.of(
        ResponseFormat.of(
            TextResponseFormat.builder()
                .mimeType(TextResponseFormatMimeType.APPLICATION_JSON)
                .schema(boundingBoxesSchema)
                .build()));

Content textContent = TextContent.builder().text(prompt).build();
Content imageContent =
    ImageContent.builder()
        .uri("https://example.com/image.png")
        .mimeType(ImageContentMimeType.IMAGE_PNG)
        .build();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(Arrays.asList(textContent, imageContent)))
        .responseFormat(format)
        .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)
    }

    prompt := "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."

    boundingBoxSchema := map[string]any{
        "type": "object",
        "properties": map[string]any{
            "box_2d": map[string]any{
                "type":        "array",
                "items":       map[string]any{"type": "integer"},
                "description": "The 2D bounding box of the item as [ymin, xmin, ymax, xmax] normalized to 0-1000.",
            },
            "mask": map[string]any{
                "type":        "array",
                "items":       map[string]any{"type": "array", "items": map[string]any{"type": "integer"}},
                "description": "The segmentation mask of the item as a polygon of [x,y] coordinates, normalized to 0-1000.",
            },
            "label": map[string]any{
                "type":        "string",
                "description": "A descriptive label for the item.",
            },
        },
        "required": []string{"box_2d", "mask", "label"},
    }

    boundingBoxesSchema := map[string]any{
        "type": "object",
        "properties": map[string]any{
            "boxes": map[string]any{
                "type":  "array",
                "items": boundingBoxSchema,
            },
        },
        "required": []string{"boxes"},
    }

    format := interactions.NewCreateModelInteractionResponseFormat(
        interactions.NewResponseFormat(interactions.TextResponseFormat{
            MimeType: interactions.TextResponseFormatMimeTypeApplicationJSON.ToPointer(),
            Schema:   boundingBoxesSchema,
        }),
    )

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput([]interactions.Content{
                interactions.NewContent(interactions.TextContent{
                    Text: prompt,
                }),
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr("https://example.com/image.png"),
                    MimeType: interactions.ImageContentMimeTypeImagePng.ToPointer(),
                }),
            }),
            ResponseFormat: genai.Ptr(format),
        }),
    })
    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": [
      {"type": "text", "text": "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."},
      {
        "type": "image",
        "uri": "https://example.com/image.png",
        "mime_type": "image/png"
      }
    ],
    "response_format": {
      "type": "text",
      "mime_type": "application/json",
      "schema": {
        "type": "object",
        "properties": {
          "boxes": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "box_2d": { "type": "array", "items": { "type": "integer" } },
                "mask": { "type": "array", "items": { "type": "array", "items": { "type": "integer" } } },
                "label": { "type": "string" }
              },
              "required": ["box_2d", "mask", "label"]
            }
          }
        },
        "required": ["boxes"]
      }
    }
  }'

Para mais exemplos, acesse o manual do Gemini.

Segmentação

Os modelos do Gemini não apenas detectam itens, mas também os segmentam e fornecem as máscaras de contorno.

O modelo prevê uma lista JSON, em que cada item representa uma máscara de segmentação. Cada item tem uma caixa delimitadora ("box_2d") no formato [ymin, xmin, ymax, xmax] com coordenadas normalizadas entre 0 e 1.000, um rótulo ("label") que identifica o objeto e, por fim, a máscara de segmentação dentro da caixa delimitadora como um polígono de coordenadas [x, y] normalizadas para 0 a 1.000.

Python

from google import genai
from pydantic import BaseModel, Field
from typing import List
import json

client = genai.Client()

prompt = """
Give the segmentation masks for the wooden and glass items.
Output a JSON list of segmentation masks where each entry contains the 2D
bounding box in the key "box_2d", the segmentation mask in key "mask", and
the text label in the key "label". Use descriptive labels.
"""

class BoundingBox(BaseModel):
    box_2d: List[int] = Field(description="The 2D bounding box of the item as [ymin, xmin, ymax, xmax] normalized to 0-1000.")
    mask: List[List[int]] = Field(description="The segmentation mask of the item as a polygon of [x,y] coordinates, normalized to 0-1000.")
    label: str = Field(description="A descriptive label for the item.")

class BoundingBoxes(BaseModel):
    boxes: List[BoundingBox]

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": prompt},
        {
            "type": "image",
            "uri": "https://example.com/image.png",
            "mime_type": "image/png"
        }
    ],
    response_format={
        "type": "text",
        "mime_type": "application/json",
        "schema": BoundingBoxes.model_json_schema()
    },
    generation_config={
        "thinking_level": "minimal"
    }
)

items = BoundingBoxes.model_validate_json(interaction.output_text)
print("Segmentation results:", items)

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as z from "zod";

const client = new GoogleGenAI({});
const prompt = `
Give the segmentation masks for the wooden and glass items.
Output a JSON list of segmentation masks where each entry contains the 2D
bounding box in the key "box_2d", the segmentation mask in key "mask", and
the text label in the key "label". Use descriptive labels.
`;

const boundingBoxesSchema = z.object({
  boxes: z.array(z.object({
    box_2d: z.array(z.number()),
    mask: z.array(z.array(z.number())),
    label: z.string()
  }))
});

const interaction = await client.interactions.create({
  model: "gemini-3.8-flash",
  input: [
    { type: "text", text: prompt },
    {
      type: "image",
      uri: "https://example.com/image.png",
      mime_type: "image/png"
    }
  ],
  response_format: {
    type: 'text',
    mime_type: 'application/json',
    schema: z.toJSONSchema(boundingBoxesSchema)
  },
  generation_config: {
    thinking_level: "minimal"
  }
});

const result = boundingBoxesSchema.parse(JSON.parse(interaction.output_text));
console.log(result);

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.CreateModelInteractionResponseFormat;
import com.google.genai.gaos.models.interactions.GenerationConfig;
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.ResponseFormat;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.interactions.TextResponseFormat;
import com.google.genai.gaos.models.interactions.TextResponseFormatMimeType;
import com.google.genai.gaos.models.interactions.ThinkingLevel;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;
import java.util.Map;

Client client = new Client();

String prompt =
    "Give the segmentation masks for the wooden and glass items.\n"
        + "Output a JSON list of segmentation masks where each entry contains the 2D\n"
        + "bounding box in the key \"box_2d\", the segmentation mask in key \"mask\", and\n"
        + "the text label in the key \"label\". Use descriptive labels.";

Map<String, Object> boundingBoxSchema =
    Map.of(
        "type", "object",
        "properties",
            Map.of(
                "box_2d",
                    Map.of(
                        "type", "array",
                        "items", Map.of("type", "integer"),
                        "description",
                            "The 2D bounding box of the item as [ymin, xmin, ymax, xmax] normalized to 0-1000."),
                "mask",
                    Map.of(
                        "type", "array",
                        "items", Map.of("type", "array", "items", Map.of("type", "integer")),
                        "description",
                            "The segmentation mask of the item as a polygon of [x,y] coordinates, normalized to 0-1000."),
                "label",
                    Map.of("type", "string", "description", "A descriptive label for the item.")),
        "required", List.of("box_2d", "mask", "label"));

Map<String, Object> boundingBoxesSchema =
    Map.of(
        "type", "object",
        "properties", Map.of("boxes", Map.of("type", "array", "items", boundingBoxSchema)),
        "required", List.of("boxes"));

CreateModelInteractionResponseFormat format =
    CreateModelInteractionResponseFormat.of(
        ResponseFormat.of(
            TextResponseFormat.builder()
                .mimeType(TextResponseFormatMimeType.APPLICATION_JSON)
                .schema(boundingBoxesSchema)
                .build()));

Content textContent = TextContent.builder().text(prompt).build();
Content imageContent =
    ImageContent.builder()
        .uri("https://example.com/image.png")
        .mimeType(ImageContentMimeType.IMAGE_PNG)
        .build();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(Arrays.asList(textContent, imageContent)))
        .responseFormat(format)
        .generationConfig(GenerationConfig.builder().thinkingLevel(ThinkingLevel.MINIMAL).build())
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println("Segmentation results: " + 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)
    }

    prompt := "Give the segmentation masks for the wooden and glass items.\n" +
        "Output a JSON list of segmentation masks where each entry contains the 2D\n" +
        "bounding box in the key \"box_2d\", the segmentation mask in key \"mask\", and\n" +
        "the text label in the key \"label\". Use descriptive labels."

    boundingBoxSchema := map[string]any{
        "type": "object",
        "properties": map[string]any{
            "box_2d": map[string]any{
                "type":        "array",
                "items":       map[string]any{"type": "integer"},
                "description": "The 2D bounding box of the item as [ymin, xmin, ymax, xmax] normalized to 0-1000.",
            },
            "mask": map[string]any{
                "type":        "array",
                "items":       map[string]any{"type": "array", "items": map[string]any{"type": "integer"}},
                "description": "The segmentation mask of the item as a polygon of [x,y] coordinates, normalized to 0-1000.",
            },
            "label": map[string]any{
                "type":        "string",
                "description": "A descriptive label for the item.",
            },
        },
        "required": []string{"box_2d", "mask", "label"},
    }

    boundingBoxesSchema := map[string]any{
        "type": "object",
        "properties": map[string]any{
            "boxes": map[string]any{
                "type":  "array",
                "items": boundingBoxSchema,
            },
        },
        "required": []string{"boxes"},
    }

    format := interactions.NewCreateModelInteractionResponseFormat(
        interactions.NewResponseFormat(interactions.TextResponseFormat{
            MimeType: interactions.TextResponseFormatMimeTypeApplicationJSON.ToPointer(),
            Schema:   boundingBoxesSchema,
        }),
    )

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput([]interactions.Content{
                interactions.NewContent(interactions.TextContent{
                    Text: prompt,
                }),
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr("https://example.com/image.png"),
                    MimeType: interactions.ImageContentMimeTypeImagePng.ToPointer(),
                }),
            }),
            ResponseFormat: genai.Ptr(format),
            GenerationConfig: &interactions.GenerationConfig{
                ThinkingLevel: interactions.ThinkingLevelMinimal.ToPointer(),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println("Segmentation results: " + *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": [
      {"type": "text", "text": "Give the segmentation masks for the wooden and glass items.\nOutput a JSON list of segmentation masks where each entry contains the 2D\nbounding box in the key \"box_2d\", the segmentation mask in key \"mask\", and\nthe text label in the key \"label\". Use descriptive labels."},
      {
        "type": "image",
        "uri": "https://example.com/image.png",
        "mime_type": "image/png"
      }
    ],
    "response_format": {
      "type": "text",
      "mime_type": "application/json",
      "schema": {
        "type": "object",
        "properties": {
          "boxes": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "box_2d": { "type": "array", "items": { "type": "integer" } },
                "mask": { "type": "array", "items": { "type": "array", "items": { "type": "integer" } } },
                "label": { "type": "string" }
              },
              "required": ["box_2d", "mask", "label"]
            }
          }
        },
        "required": ["boxes"]
      }
    },
    "generation_config": {
      "thinking_level": "minimal"
    }
  }'

Uma mesa com cupcakes, com os objetos de madeira e vidro destacados — Um exemplo de saída de segmentação com objetos e máscaras de segmentação

Formatos de imagem compatíveis

O Gemini é compatível com os seguintes tipos MIME de formato de imagem:

PNG - image/png
JPEG - image/jpeg
WEBP - image/webp
HEIC - image/heic
HEIF - image/heif

Para saber mais sobre outros métodos de entrada de arquivos, consulte o guia Métodos de entrada de arquivos.

Recursos

Todas as versões do modelo do Gemini são multimodais e podem ser usadas em uma ampla variedade de tarefas de processamento de imagens e visão computacional, incluindo, mas não se limitando a, legendagem de imagens, perguntas e respostas visuais, classificação de imagens, detecção de objeto e segmentação.

O Gemini pode reduzir a necessidade de usar modelos especializados de ML, dependendo dos seus requisitos de qualidade e desempenho.

As versões mais recentes do modelo são treinadas especificamente para melhorar a acurácia de tarefas especializadas, além de recursos genéricos, como detecção de objetos e segmentação aprimoradas.

Limitações e principais informações técnicas

Limite de arquivos

Os modelos do Gemini aceitam no máximo 3.600 arquivos de imagem por solicitação.

Cálculo de tokens

258 tokens se as duas dimensões forem menores ou iguais a 384 pixels. Imagens maiores são divididas em blocos de 768 x 768 pixels, cada um custando 258 tokens.

Uma fórmula aproximada para calcular o número de blocos é a seguinte:

Calcule o tamanho da unidade de corte, que é aproximadamente: floor(min(width, height) / 1,5.
Divida cada dimensão pelo tamanho da unidade de corte e multiplique para obter o número de blocos.

Por exemplo, uma imagem de dimensões 960 x 540 teria um tamanho de unidade de corte de 360. Divida cada dimensão por 360. O número de blocos é 3 * 2 = 6.

Resolução de mídia

O Gemini 3 apresenta controle granular sobre o processamento de visão multimodal com o parâmetro media_resolution. O parâmetro media_resolution determina o número máximo de tokens alocados por imagem de entrada ou frame de vídeo. Resoluções mais altas melhoram a capacidade do modelo de ler textos pequenos ou identificar detalhes pequenos, mas aumentam o uso de tokens e a latência.

Dicas e práticas recomendadas

Verifique se as imagens estão giradas corretamente.
Use imagens nítidas e sem desfoque.
Ao usar uma única imagem com texto, coloque o comando de texto antes da imagem na matriz input.

A seguir

Este guia mostra como fazer upload de arquivos de imagem e gerar saídas de texto com base em entradas de imagem. Para saber mais, consulte os seguintes recursos:

API Files: saiba mais sobre como enviar e gerenciar arquivos para uso com o Gemini.
Instruções do sistema: Com elas, é possível orientar o comportamento do modelo com base nas suas necessidades e casos de uso específicos.
Estratégias de comandos de arquivo: a API Gemini aceita comandos com dados de texto, imagem, áudio e vídeo, também conhecidas como comandos multimodais.
Orientações de segurança: às vezes, os modelos de IA generativa produzem resultados inesperados, como imprecisos, tendenciosos ou ofensivos. O pós-processamento e a avaliação humana são essenciais para limitar o risco de danos causados por essas saídas.