Integrations

Use Bifrost as a drop-in replacement for existing AI provider SDKs with zero code changes. Just change the base URL and unlock advanced features.

What are Integrations?

Integrations are protocol adapters that make Bifrost 100% compatible with existing AI provider SDKs. They translate between provider-specific API formats (OpenAI, Anthropic, Google GenAI) and Bifrost’s unified API, enabling you to:

• Drop-in replacement - Change only the base URL in your existing code
• Zero migration effort - Keep your current SDK and request/response handling
• Instant feature access - Get governance, caching, fallbacks, and monitoring without code changes

Quick Example

Before (Direct Provider)

import openai

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

After (Bifrost Integration)

import openai

client = openai.OpenAI(
    base_url="http://localhost:8080/openai",  # Point to Bifrost
    api_key="dummy-key"  # Keys handled by Bifrost
)

That’s it! Your application now has automatic fallbacks, governance, monitoring, and all Bifrost features.

Available Integrations

Bifrost provides complete compatibility with these popular AI SDKs:

• OpenAI SDK
• Anthropic SDK
• Google GenAI SDK
• LiteLLM
• LangChain
• Passthrough Endpoints

Learn More

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

➜ Complete Integration Documentation

Next Steps

Now that you understand integrations, explore these related topics:

Essential Topics

• Provider Configuration - Set up multiple AI providers for redundancy
• Tool Calling - Enable AI models to use external functions
• Streaming Responses - Real-time response generation
• Multimodal AI - Process images, audio, and multimedia content

Advanced Topics

• Core Features - Governance, caching, and observability
• Architecture - How Bifrost works internally
• Deployment - Production setup and scaling