Skip to Content
Launching the open-source gateway

Tracing quickstart

Install the Respan SDK and see your first trace in Logs.

Tracing records each step of your AI app, such as LLM calls, tool runs, and agent steps, as a tree of spans, so you can debug failures and see where time and cost go. The Respan SDK traces the major LLM SDKs automatically once you initialize it.

Set up with your coding agent

Paste this prompt into Claude Code, Cursor, Codex, or any coding agent:

Help me set up Respan tracing: fetch and follow https://respan.ai/docs/agent-setup.md
Logs listing traced LLM calls such as openai.chat and anthropic.chat, with span counts, error rates over time, and each call's model, system prompt, and user message

To set it up yourself, follow the steps below.

Step by step

Create an API key

In the platform , go to Gateway › API keys and click New key. Pick Production or Test, keep the default permissions, and click Create.

The Create new key dialog with Name, Environment (Production or Test), and Permissions: Read, Write, Gateway, and Admin

Click Copy, then Done. You won’t see the key again, so save it now:

export RESPAN_API_KEY="your-respan-api-key"

Install and initialize the SDK

Install the Respan SDK alongside your LLM SDK. Initialize Respan once, before your first model call. Your model calls are then traced with no other changes.

Requires Python 3.11 to 3.13.

pip install respan-ai openai
app.py
from openai import OpenAI from respan import Respan respan = Respan() # reads RESPAN_API_KEY client = OpenAI() # reads OPENAI_API_KEY response = client.chat.completions.create( model="gpt-5.5", messages=[{"role": "user", "content": "How do I rotate my API key?"}], ) print(response.choices[0].message.content)

Calls made with the OpenAI, Anthropic, AWS Bedrock, Vertex AI, and Together AI SDKs are traced automatically, plus Google GenAI and Ollama in Python, and Cohere, OpenRouter, and Writer in TypeScript.

Using an agent framework such as OpenAI Agents, LangChain, or the Vercel AI SDK? Find its guide in Integrations.

Run your app

export OPENAI_API_KEY="your-openai-api-key" python app.py # TypeScript: npx tsx app.mts

The SDK sends spans in the background and flushes them when the process exits. In serverless functions, call respan.flush() (await respan.flush() in TypeScript) before you return.

See the call in Logs

Go to Observability › Logs. Your openai.chat span is at the top, with its model, duration, tokens, and cost. Click it to see the input and output.

Don’t see it? Widen the time range. Traces sent with a Test key show under Test, so set the environment switch to Test or All environments. See Inspect spans and traces.

Key terms

The grouping menu in Logs switches between these views.

TermWhat it is
SpanOne recorded operation, such as an LLM call, a tool run, or a function you wrapped
TraceAll the spans from one request, linked into a tree
ThreadSpans that share a thread ID, such as the turns of one conversation