Skip to main content
These integration methods are maintained but no longer actively developed. For new projects and the best experience, use our AI Gateway with unified API access to 100+ models.

​
What Are Alternative Integrations?

Legacy proxy-based integrations that add Helicone observability by changing your base URL:
  • OpenAI: api.openai.com → oai.helicone.ai
  • Anthropic: api.anthropic.com → anthropic.helicone.ai
  • Others: Provider-specific proxy endpoints
You keep using your existing SDK and code—just point to our proxy URL and add a Helicone-Auth header.

​
Why We Built the AI Gateway

These provider-specific proxies have limitations:
  • No automatic fallbacks - If OpenAI goes down, your app goes down
  • Can’t switch providers easily - Each provider needs different code
  • Multiple endpoints to manage - Different proxy for each provider
  • No unified routing - Can’t optimize for cost or latency across providers
The AI Gateway solves these problems with one unified API that routes to 100+ models with automatic fallbacks, intelligent routing, and zero markup.

​
When to Use Alternative Integrations

Only use these if:
  • Existing production code - You have a large codebase built with provider-specific SDKs and refactoring would be costly
  • Native SDK features - You need specific features only available in the native SDK (rare)
Otherwise, use the AI Gateway for better reliability, flexibility, and features.

​
Available Integrations

If you need provider-specific integrations, see the navigation menu on the left under “References > Alternative Integrations” for all available providers.

​
How to Migrate to AI Gateway

Ready to switch to the unified API? It’s simple: 
// Before: Provider-specific proxy
const client = new OpenAI({
  baseURL: "https://oai.helicone.ai/v1",
  apiKey: process.env.OPENAI_API_KEY,
  defaultHeaders: { "Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}` }
});

// After: AI Gateway
const client = new OpenAI({
  baseURL: "https://ai-gateway.helicone.ai",
  apiKey: process.env.HELICONE_API_KEY, // Just your Helicone key
});

// Now access any model: gpt-4o, claude-sonnet-4, gemini-2.0-flash, etc.
See the AI Gateway migration guide for full details.