Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.inference.net/llms.txt

Use this file to discover all available pages before exploring further.

This quickstart uses OpenAI because it is the smallest end-to-end trace. The same setup pattern applies to Anthropic, LangChain, LangGraph, LangSmith, OpenAI Agents, LiveKit Agents, ElevenLabs Agents, Cursor SDK, Claude Agent SDK, Pydantic AI, and manual spans.

​
1. Install

bun add @inference/tracing openai

​
2. Configure Export

Set the Catalyst traces endpoint and token before your app starts. 
export CATALYST_OTLP_ENDPOINT="https://telemetry.inference.net"
# Get your API key from https://inference.net/dashboard/api-keys/
export CATALYST_OTLP_TOKEN="<your-token>"
export CATALYST_SERVICE_NAME="checkout-agent"
export CATALYST_SERVICE_VERSION="2026.04.28"
Use a stable CATALYST_SERVICE_NAME per deployed service. It makes traces easier to filter and compare across environments.

​
3. Initialize Tracing Early

Call setup() before constructing clients from instrumented SDKs. 
import { setup } from "@inference/tracing";
import OpenAI from "openai";

const tracing = await setup({
  modules: { openai: OpenAI },
});

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Reply with just the word hello." }],
  max_tokens: 16,
});

console.log(response.choices[0]?.message.content);
await tracing.shutdown();

​
4. Verify

Open the Catalyst dashboard and filter for your CATALYST_SERVICE_NAME. The trace should include an OpenAI LLM span with input messages, output messages, model name, invocation parameters, finish reason, and token counts. If the process is short-lived, always call shutdown() before exit so batched spans are flushed.

​
Next Steps

OpenAI tracing

Add tool calls, structured outputs, and Responses API examples.

Manual spans

Wrap custom agents, CLI calls, and unsupported SDKs.