Respan

Observability, prompt management, and evals for LLM engineering teams.

Respan Tracing

Respan's library for sending telemetries of LLM applications in OpenLLMetry format.

Integrations

Configuration

1. Install

Python

pip install respan respan-tracing respan-instrumentation-openai

TypeScript/JavaScript

npm install @respan/respan @respan/tracing @respan/instrumentation-openai openai @traceloop/instrumentation-openai

2. Set Environment Variables

Variable	Required	Description
RESPAN_API_KEY	Yes	Your Respan API key. Authenticates both proxy and tracing. Get it from the platform.
RESPAN_BASE_URL	No	Defaults to https://api.respan.ai/api.

The Respan API key is used for both LLM inference (proxy) and telemetry export (tracing). Vendor-specific keys (OPENAI_API_KEY, etc.) are derived from the Respan key in code.

Quickstart

3. Run Script

Python

import os
from openai import OpenAI
from respan import Respan
from respan_instrumentation_openai import OpenAIInstrumentor

respan = Respan(instrumentations=[OpenAIInstrumentor()])

# Respan API key authenticates both proxy and tracing
respan_api_key = os.environ["RESPAN_API_KEY"]
respan_base_url = os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api")

client = OpenAI(api_key=respan_api_key, base_url=respan_base_url)

response = client.chat.completions.create(
    model="gpt-4.1-nano",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)
respan.flush()

TypeScript/JavaScript

import OpenAI from "openai";
import { Respan } from "@respan/respan";
import { OpenAIInstrumentor } from "@respan/instrumentation-openai";

// Respan API key authenticates both proxy and tracing
const respan = new Respan({
  apiKey: process.env.RESPAN_API_KEY,
  baseURL: process.env.RESPAN_BASE_URL,
  instrumentations: [new OpenAIInstrumentor()],
});
await respan.initialize();

const client = new OpenAI({
  apiKey: process.env.RESPAN_API_KEY,
  baseURL: process.env.RESPAN_BASE_URL,
});

const response = await client.chat.completions.create({
  model: "gpt-4.1-nano",
  messages: [{ role: "user", content: "Say hello in three languages." }],
});
console.log(response.choices[0].message.content);
await respan.flush();

4. View Dashboard

See your traces in the Respan platform.