Overview

Overview

DeepintShield is Google GenAI API-compatible: point your existing Google GenAI SDK at the DeepintShield endpoint and your requests, responses, and errors work unchanged.

You keep your Google GenAI SDK-based architecture while gaining DeepintShield features like governance, load balancing, semantic caching, and multi-provider support.

Endpoint: /genai

---

Setup

Python (DeepintShield SDK)

Install with the GenAI extra:

pip install "deepintshield[genai]"

from deepintshield import DeepintShield

shield = DeepintShield(virtual_key="sk-bf-your-virtual-key")
client = shield.genai()  # pre-wired google.genai.Client

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Hello!",
)

print(response.text)

Python (native SDK)

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(
    api_key="sk-bf-your-virtual-key",
    http_options=HttpOptions(
        base_url="https://app.deepintshield.com/genai",
        headers={"x-bf-vk": "sk-bf-your-virtual-key"},
    ),
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Hello!",
)

print(response.text)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("sk-bf-your-virtual-key", {
  baseUrl: "https://app.deepintshield.com/genai",
  customHeaders: { "x-bf-vk": "sk-bf-your-virtual-key" },
});

const model = genAI.getGenerativeModel({ model: "gemini-2.5-flash" });
const response = await model.generateContent("Hello!");

console.log(response.response.text());

---

Provider/Model Usage Examples

Use multiple providers through the same GenAI SDK format by prefixing model names with the provider:

Python

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(
    api_key="sk-bf-your-virtual-key",
    http_options=HttpOptions(
        base_url="https://app.deepintshield.com/genai",
        headers={"x-bf-vk": "sk-bf-your-virtual-key"},
    ),
)

# Google Vertex models (default)
vertex_response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Hello from Gemini!"
)

# OpenAI models via GenAI SDK format
openai_response = client.models.generate_content(
    model="openai/gpt-4o-mini",
    contents="Hello from OpenAI!"
)

# Anthropic models via GenAI SDK format
anthropic_response = client.models.generate_content(
    model="anthropic/claude-3-5-sonnet",
    contents="Hello from Claude!"
)

# Azure models
azure_response = client.models.generate_content(
    model="azure/gpt-4o",
    contents="Hello from Azure!"
)

# Local Ollama models
ollama_response = client.models.generate_content(
    model="ollama/llama3.1:8b",
    contents="Hello from Ollama!"
)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("sk-bf-your-virtual-key", {
  baseUrl: "https://app.deepintshield.com/genai",
  customHeaders: { "x-bf-vk": "sk-bf-your-virtual-key" },
});

// Google Vertex models (default)
const geminiModel = genAI.getGenerativeModel({ model: "gemini-2.5-flash" });
const vertexResponse = await geminiModel.generateContent("Hello from Gemini!");

// OpenAI models via GenAI SDK format
const openaiModel = genAI.getGenerativeModel({ model: "openai/gpt-4o-mini" });
const openaiResponse = await openaiModel.generateContent("Hello from OpenAI!");

// Anthropic models via GenAI SDK format
const anthropicModel = genAI.getGenerativeModel({ model: "anthropic/claude-3-5-sonnet" });
const anthropicResponse = await anthropicModel.generateContent("Hello from Claude!");

// Azure models
const azureModel = genAI.getGenerativeModel({ model: "azure/gpt-4o" });
const azureResponse = await azureModel.generateContent("Hello from Azure!");

// Local Ollama models
const ollamaModel = genAI.getGenerativeModel({ model: "ollama/llama3.1:8b" });
const ollamaResponse = await ollamaModel.generateContent("Hello from Ollama!");

---

Adding Custom Headers

Pass custom headers required by DeepintShield plugins (like governance, telemetry, etc.):

Python

from google import genai
from google.genai.types import HttpOptions

# Configure client with custom headers
client = genai.Client(
    api_key="dummy-key",
    http_options=HttpOptions(
        base_url="https://app.deepintshield.com/genai",
        headers={
            "x-bf-vk": "vk_12345",  # Virtual key for governance
        }
    )
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Hello with custom headers!"
)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

// Configure client with custom headers
const genAI = new GoogleGenerativeAI("dummy-key", {
  baseUrl: "https://app.deepintshield.com/genai",
  customHeaders: {
    "x-bf-vk": "vk_12345", // Virtual key for governance
  },
});

const model = genAI.getGenerativeModel({ model: "gemini-2.5-flash" });
const response = await model.generateContent("Hello with custom headers!");

---

Using Direct Keys

Pass API keys directly in requests to bypass DeepintShield’s load balancing. You can pass any provider’s API key (OpenAI, Anthropic, Mistral, etc.) since DeepintShield only looks for Authorization, x-api-key and x-goog-api-key headers. This requires the Allow Direct API keys option to be enabled in DeepintShield configuration.

Learn more: See Key Management for enabling direct API key usage.

Python

from google import genai
from google.genai.types import HttpOptions

# Pass different provider keys per request using headers
client = genai.Client(
    api_key="gemini-key",
    http_options=HttpOptions(base_url="https://app.deepintshield.com/genai")
)

# Use Gemini key directly
gemini_response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Hello Gemini!"
)

# Use Anthropic key for Claude models
anthropic_response = client.models.generate_content(
    model="anthropic/claude-3-5-sonnet",
    contents="Hello Claude!",
    request_options={
        "headers": {"x-api-key": "your-anthropic-api-key"}
    }
)

# Use OpenAI key for GPT models
openai_response = client.models.generate_content(
    model="openai/gpt-4o-mini",
    contents="Hello GPT!",
    request_options={
        "headers": {"Authorization": "Bearer sk-your-openai-key"}
    }
)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

// Pass different provider keys per request using headers
const genAI = new GoogleGenerativeAI("gemini-key", {
  baseUrl: "https://app.deepintshield.com/genai",
});

// Use Gemini key directly
const geminiModel = genAI.getGenerativeModel({
  model: "gemini-2.5-flash"
});
const geminiResponse = await geminiModel.generateContent("Hello Gemini!");

// Use Anthropic key for Claude models
const anthropicModel = genAI.getGenerativeModel({
  model: "anthropic/claude-3-5-sonnet",
  requestOptions: {
    customHeaders: { "x-api-key": "your-anthropic-api-key" }
  }
});
const anthropicResponse = await anthropicModel.generateContent("Hello Claude!");

// Use OpenAI key for GPT models
const gptModel = genAI.getGenerativeModel({
  model: "openai/gpt-4o-mini",
  requestOptions: {
    customHeaders: { "Authorization": "Bearer sk-your-openai-key" }
  }
});
const gptResponse = await gptModel.generateContent("Hello GPT!");

---

Dynamic Thinking Budget

Set thinkingConfig.thinkingBudget to -1 to request dynamic thinking. The effect depends on the model you target:

• Gemini: dynamic thinking is used natively.
• Anthropic, Bedrock, Cohere: maps to the minimum reasoning budget (1024 tokens).
• OpenAI: maps to medium reasoning effort.

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Complex reasoning task",
    config={
        "thinking_config": {
            "include_thoughts": True,
            "thinking_budget": -1  # Dynamic thinking
        }
    }
)

---

Supported Features

The Google GenAI integration supports all features that are available in both the Google GenAI SDK and DeepintShield core functionality. If the Google GenAI SDK supports a feature and DeepintShield supports it, the integration will work seamlessly.

---

Next Steps

• Files and Batch API - File uploads and batch processing
• OpenAI SDK - GPT integration patterns
• Provider Configuration - DeepintShield setup and configuration
• Semantic Caching - Advanced DeepintShield capabilities