import { OpenAI } from "openai";
const client = new OpenAI({
baseURL: "https://ai-gateway.helicone.ai",
apiKey: process.env.HELICONE_API_KEY
});
const response = await client.chat.completions.create({
model: "claude-4.5-haiku", // Or 100+ other models - helicone.ai/models
messages: [{ role: "user", content: "Hello, world!" }],
});
- Single line integration (just change the
baseUrl)
- Observability by default - trace, monitor, and observe every LLM
- Automatic failover (no more 429s!)
- Always pick the cheapest provider
- Model management, response caching, rate limits, and model routing
- Prompt management, versioning, and playground
- Export to Pothog for custom dashboards
- Enterprise compliant
