Geração de texto

A API Gemini pode gerar saída de texto com base em entradas de texto, imagens, vídeo e áudio.

Confira um exemplo básico:

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How does AI work?"
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How does AI work?",
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "How does AI work?"
  }'

Pensando com o Gemini

Os modelos do Gemini geralmente têm o "pensamento" ativado por padrão, o que permite que o modelo raciocine antes de responder a uma solicitação.

Cada modelo oferece suporte a diferentes configurações de pensamento, o que permite controlar o custo, a latência e a inteligência. Para mais detalhes, consulte o guia de pensamento.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How does AI work?",
    generation_config={
        "thinking_level": "low"
    }
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How does AI work?",
    generation_config: {
      thinking_level: "low",
    },
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "How does AI work?",
    "generation_config": {
      "thinking_level": "low"
    }
  }'

Instruções do sistema e outras configurações

Você pode orientar o comportamento dos modelos do Gemini com instruções do sistema. Transmita um parâmetro system_instruction para configurar o comportamento do modelo.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    system_instruction="You are a cat. Your name is Neko.",
    input="Hello there"
)

print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Hello there",
    system_instruction: "You are a cat. Your name is Neko.",
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "system_instruction": "You are a cat. Your name is Neko.",
    "input": "Hello there"
  }'

Também é possível substituir os parâmetros de geração padrão, como a temperatura, usando o parâmetro generation_config.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain how AI works",
    generation_config={
        "temperature": 0.1
    }
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Explain how AI works",
    generation_config: {
      temperature: 0.1,
    },
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "Explain how AI works",
    "generation_config": {
      "temperature": 0.1
    }
  }'

Consulte a referência da API Interactions para conferir uma lista completa de parâmetros configuráveis e as descrições deles.

Entradas multimodais

A API Gemini oferece suporte a entradas multimodais, permitindo combinar texto com arquivos de mídia. O exemplo a seguir demonstra como fornecer uma imagem:

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Tell me about this instrument"},
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

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

  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
      {type: "text", text: "Tell me about this instrument"},
      {
        type: "image",
        uri: uploadedFile.uri,
        mime_type: uploadedFile.mimeType
      }
    ],
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# First upload the file using the Files API, then use the URI:
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {"type": "text", "text": "Tell me about this instrument"},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Para métodos alternativos de fornecimento de imagens e processamento de imagens mais avançado, consulte nosso guia de compreensão de imagens. A API também oferece suporte a documentos, vídeos, e áudios entradas e compreensão.

Respostas de streaming

Por padrão, o modelo retorna uma resposta somente após a conclusão de todo o processo de geração.

Para interações mais fluidas, use o streaming para processar blocos de resposta à medida que eles são gerados.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain how AI works",
    stream=True
)
for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="")

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const stream = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Explain how AI works",
    stream: true,
  });

  for await (const event of stream) {
    if (event.event_type === "step.delta") {
      if (event.delta.type === "text") {
        process.stdout.write(event.delta.text);
      }
    }
  }
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  --no-buffer \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "Explain how AI works",
    "stream": true
  }'

Conversas com vários turnos

A API Interactions oferece suporte a conversas multiturno encadeando interações usando previous_interaction_id. Cada turno é uma interação separada, e a API gerencia automaticamente o histórico de conversas.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="I have 2 dogs in my house.",
)
print(interaction1.steps[-1].content[0].text)

interaction2 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How many paws are in my house?",
    previous_interaction_id=interaction1.id,
)
print(interaction2.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "I have 2 dogs in my house.",
  });
  console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

  const interaction2 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How many paws are in my house?",
    previous_interaction_id: interaction1.id,
  });
  console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have 2 dogs in my house."
  }')

INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have two dogs in my house. How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'"
  }'

O streaming também pode ser usado para conversas multiturno combinando previous_interaction_id com os métodos de streaming.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="I have 2 dogs in my house.",
)
print(interaction1.steps[-1].content[0].text)

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How many paws are in my house?",
    previous_interaction_id=interaction1.id,
    stream=True
)
for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="")

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "I have 2 dogs in my house.",
  });
  console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

  const stream = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How many paws are in my house?",
    previous_interaction_id: interaction1.id,
    stream: true,
  });
  for await (const event of stream) {
    if (event.event_type === "step.delta") {
      if (event.delta.type === "text") {
        process.stdout.write(event.delta.text);
      }
    }
  }
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have 2 dogs in my house."
  }')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  --no-buffer \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'",
    "stream": true
  }'

Conversas sem estado

Por padrão, a API Interactions gerencia o estado da conversa no lado do servidor quando você usa previous_interaction_id. No entanto, também é possível operar no modo sem estado gerenciando o histórico de conversas no lado do cliente.

Para usar o modo sem estado: 1. Defina store=false na solicitação para desativar o armazenamento no lado do servidor. 2. Mantenha o histórico de conversas como uma matriz de etapas no lado do cliente. 3. Em solicitações subsequentes, transmita as etapas acumuladas no campo input e anexe o novo turno como uma etapa user_input.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

# Initialize history with the first user turn
history = [
    {
        "type": "user_input",
        "content": [{"type": "text", "text": "I have 2 dogs in my house."}]
    }
]

# Turn 1: Send request with store=False
interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    store=False,
    input=history
)
print("Response 1:", interaction1.steps[-1].content[0].text)

# Append the model's response steps to history
for step in interaction1.steps:
    # Convert the SDK Step object to a dictionary
    history.append(step.model_dump())

# Append the next user turn as a user_input step
history.append({
    "type": "user_input",
    "content": [{"type": "text", "text": "How many paws are in my house?"}]
})

# Turn 2: Send full history with store=False
interaction2 = client.interactions.create(
    model="gemini-3-flash-preview",
    store=False,
    input=history
)
print("Response 2:", interaction2.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  // Initialize history with the first user turn
  const history = [
    {
      type: "user_input",
      content: [{ type: "text", text: "I have 2 dogs in my house." }]
    }
  ];

  // Turn 1: Send request with store: false
  const interaction1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    store: false,
    input: history
  });
  console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

  // Append model response steps to history
  history.push(...interaction1.steps);

  // Append the next user turn
  history.push({
    type: "user_input",
    content: [{ type: "text", text: "How many paws are in my house?" }]
  });

  // Turn 2: Send full history with store: false
  const interaction2 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    store: false,
    input: history
  });
  console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
}

await main();

REST

# Turn 1: Send request with store: false
# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "store": false,
    "input": [
      {
        "type": "user_input",
        "content": [{"type": "text", "text": "I have 2 dogs in my house."}]
      }
    ]
  }')

# Extract the steps from response
MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')

# Reconstruct the full history for Turn 2 by combining:
# 1. First user input
# 2. Model response steps
# 3. Second user input
HISTORY=$(jq -n \
  --argjson first_input '[{"type": "user_input", "content": [{"type": "text", "text": "I have 2 dogs in my house."}]}]' \
  --argjson model_steps "$MODEL_STEPS" \
  --argjson second_input '[{"type": "user_input", "content": [{"type": "text", "text": "How many paws are in my house?"}]}]' \
  "'"'"'$first_input + $model_steps + $second_input'"'"'")

# Turn 2: Send the full history
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d "{
    \"model\": \"gemini-3-flash-preview\",
    \"store\": false,
    \"input\": $HISTORY
  }"

Dicas de comandos

Consulte nosso guia de engenharia de comandos para sugestões sobre como aproveitar ao máximo o Gemini.

A seguir