What is an integration?

Overview

An integration lets you keep using an existing provider SDK (OpenAI, Anthropic, Google GenAI, and more) while routing supported endpoints through DeepIntShield. For a supported SDK version and route, migration usually means changing the base URL and supplying a DeepIntShield Virtual Key.

Compatibility is route-specific: provider preview features, uploads, batches, stream events, and provider-specific headers may need a documented adapter or passthrough route. Test the exact endpoints and SDK version your application uses. If you want explicit guardrail, RAG, MCP, or Agentic APIs in addition to native provider clients, use the DeepIntShield Python SDK.

---

Quick Migration

Before (Direct Provider)

import openai

client = openai.OpenAI(
    api_key="your-openai-key"
)

After (DeepIntShield)

import openai

client = openai.OpenAI(
    base_url="https://app.deepintshield.com/openai",  # Point to DeepIntShield
    api_key="sk-ds-your-virtual-key"
)

Run your ordinary integration and error-path tests after the change. Features apply according to the selected Virtual Key, workspace policy, route, and plan.

---

Supported Integrations

1. OpenAI
2. Anthropic
3. Google GenAI
4. LiteLLM
5. Langchain
6. AWS Bedrock

---

Provider-Prefixed Models

Use multiple providers seamlessly by prefixing model names with the provider:

OpenAI

import openai

# Single client, multiple providers
client = openai.OpenAI(
    base_url="https://app.deepintshield.com/openai",
    api_key="dummy"  # API keys configured in DeepIntShield
)

# OpenAI models
response1 = client.chat.completions.create(
    model="gpt-4o-mini", # (default OpenAI since it's OpenAI's SDK)
    messages=[{"role": "user", "content": "Hello!"}]
)

Anthropic

import openai

# Anthropic models using OpenAI SDK format
response2 = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet",
    messages=[{"role": "user", "content": "Hello!"}]
)

Azure

import openai

# Azure models
response4 = client.chat.completions.create(
    model="azure/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

Vertex

import openai

# Google Vertex models
response3 = client.chat.completions.create(
    model="vertex/gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)

Ollama

import openai

# Local Ollama models
response5 = client.chat.completions.create(
    model="ollama/llama3.1:8b",
    messages=[{"role": "user", "content": "Hello!"}]
)

---

Direct API Usage

For custom HTTP clients or when you have existing provider-specific setup and want to use DeepIntShield gateway without restructuring your codebase:

import requests

# OpenAI-compatible chat endpoint
response = requests.post(
    "https://app.deepintshield.com/openai/v1/chat/completions",
    headers={
        "Authorization": "Bearer sk-ds-your-virtual-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "gpt-4o-mini",
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)

# Anthropic-compatible messages endpoint
response = requests.post(
    "https://app.deepintshield.com/anthropic/v1/messages",
    headers={
        "Content-Type": "application/json",
        "x-deepintshield-vk": "sk-ds-your-virtual-key"
    },
    json={
        "model": "claude-3-5-sonnet",
        "max_tokens": 1000,
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)

# Google GenAI-compatible endpoint
response = requests.post(
    "https://app.deepintshield.com/genai/v1beta/models/gemini-2.5-flash/generateContent",
    headers={
        "Content-Type": "application/json",
        "x-deepintshield-vk": "sk-ds-your-virtual-key"
    },
    json={
        "contents": [
            {"parts": [{"text": "Hello!"}]}
        ],
        "generation_config": {
            "max_output_tokens": 1000,
            "temperature": 1
        }
    }
)

---

Listing Models

All integrations support listing available models through their respective list models endpoints (e.g., /openai/v1/models, /anthropic/v1/models). By default, list models requests return models from all configured providers in DeepIntShield.

Filtering by Provider

You can control which provider’s models to list using the x-deepintshield-list-models-provider header:

Python

import openai

client = openai.OpenAI(
    base_url="https://app.deepintshield.com/openai",
    api_key="dummy-key"
)

# List models from all providers (default behavior)
all_models = client.models.list()

# List models from a specific provider only
openai_models = client.models.list(
    extra_headers={
        "x-deepintshield-list-models-provider": "openai"
    }
)

anthropic_models = client.models.list(
    extra_headers={
        "x-deepintshield-list-models-provider": "anthropic"
    }
)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://app.deepintshield.com/openai",
  apiKey: "dummy-key",
});

// List models from all providers (default behavior)
const allModels = await openai.models.list();

// List models from a specific provider only
const openaiModels = await openai.models.list({
  headers: {
    "x-deepintshield-list-models-provider": "openai",
  },
});

const anthropicModels = await openai.models.list({
  headers: {
    "x-deepintshield-list-models-provider": "anthropic",
  },
});

cURL

# List models from all providers (default)
curl https://app.deepintshield.com/openai/v1/models \
  -H "Authorization: Bearer sk-ds-your-virtual-key"

# List models from specific provider
curl https://app.deepintshield.com/openai/v1/models \
  -H "Authorization: Bearer sk-ds-your-virtual-key" \
  -H "x-deepintshield-list-models-provider: openai"

# Explicitly request all providers
curl https://app.deepintshield.com/openai/v1/models \
  -H "Authorization: Bearer sk-ds-your-virtual-key" \
  -H "x-deepintshield-list-models-provider: all"

Header Behavior

Header Value	Behavior
Not set (default)	Lists models from all configured providers
all	Lists models from all configured providers
openai	Lists models from OpenAI provider only
anthropic	Lists models from Anthropic provider only
vertex	Lists models from Vertex AI provider only
Any valid provider	Lists models from that specific provider

Response Fields

When listing models from all providers, some provider-specific fields may be empty or contain default values if the information is not available from all providers. This is normal behavior as different providers expose different model metadata.

---

Migration Strategies

Gradual Migration

1. Start with development - Test DeepIntShield in dev environment
2. Canary deployment - Route 5% of traffic through DeepIntShield
3. Feature-by-feature - Migrate specific endpoints gradually
4. Full migration - Switch all traffic to DeepIntShield

Blue-Green Migration

import os
import random

# Route traffic based on feature flag
def get_base_url(provider: str) -> str:
    if os.getenv("USE_DEEPINTSHIELD", "false") == "true":
        return f"https://app.deepintshield.com/{provider}"
    else:
        return f"https://api.{provider}.com"

# Gradual rollout
def should_use_deepintshield() -> bool:
    rollout_percentage = int(os.getenv("DEEPINTSHIELD_ROLLOUT", "0"))
    return random.randint(1, 100) <= rollout_percentage

Feature Flag Integration

# Using feature flags for safe migration
import openai
from feature_flags import get_flag

def create_client():
    if get_flag("use_deepintshield_openai"):
        base_url = "https://app.deepintshield.com/openai"
    else:
        base_url = "https://api.openai.com"

    return openai.OpenAI(
        base_url=base_url,
        api_key=os.getenv("OPENAI_API_KEY")
    )

---

Next Steps

• Gateway Setup - Get the gateway running
• Provider Configuration - Provider setup and config
• Governance - Virtual keys and team management