Skip to content
DeepIntShield DeepIntShield

Integrations

What are Integrations?

Section titled “What are Integrations?”

Integrations expose compatibility routes for supported OpenAI, Anthropic, Google GenAI, Bedrock, LiteLLM, LangChain, and PydanticAI operations. Point the client at the matching route and authenticate with a DeepIntShield virtual key:

  • Keep native response types for operations supported by both the client and gateway route.
  • Use route-specific configuration for URL, key, and required headers.
  • Add gateway features according to the workspace policy and route capability.

Compatibility is not an assertion that every upstream SDK version, beta header, endpoint, streaming mode, or error class is identical. Pin versions and run contract tests for the features your application uses.

Quick Example

Section titled “Quick Example”

Before (Direct Provider)

Section titled “Before (Direct Provider)”
import openai


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

After (DeepIntShield Integration)

Section titled “After (DeepIntShield Integration)”
import openai


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

The request now traverses the OpenAI compatibility route. Features such as fallbacks, guardrails, caching, and monitoring apply only when enabled and supported for that route and workspace.

Available Integrations

Section titled “Available Integrations”

DeepIntShield provides complete compatibility with these popular AI SDKs:

Learn More

Section titled “Learn More”

For detailed setup guides, compatibility information, and advanced usage:

➜ Complete Integration Documentation

Next Steps

Section titled “Next Steps”

Now that you understand integrations, explore these related topics:

Essential Topics

Section titled “Essential Topics”

Advanced Topics

Section titled “Advanced Topics”