How to beginner · 3 min read

Langfuse pricing

Quick answer

Langfuse offers a free tier with limited usage for AI API observability and tracing. Paid plans scale based on usage, including the number of tracked requests and data retention, with detailed pricing available on the official Langfuse website. Use the Langfuse Python SDK to integrate and monitor costs effectively.

PREREQUISITES

Python 3.8+
Langfuse API key
pip install langfuse

Setup

Install the langfuse Python package and set your API keys as environment variables to start tracking AI API usage and costs.

bash

pip install langfuse

Step by step

Use the Langfuse client to initialize with your API keys and start tracing your AI API calls. This example shows basic initialization and a traced function call.

python

import os
from langfuse import Langfuse
from langfuse.decorators import observe

langfuse = Langfuse(
    public_key=os.environ["LANGFUSE_PUBLIC_KEY"],
    secret_key=os.environ["LANGFUSE_SECRET_KEY"],
    host="https://cloud.langfuse.com"
)

@observe()
def call_ai_model(prompt: str) -> str:
    # Simulate AI call
    return f"Response to: {prompt}"

result = call_ai_model("Hello Langfuse pricing")
print(result)

output

Response to: Hello Langfuse pricing

Common variations

You can customize Langfuse usage by enabling auto-tracing for OpenAI calls or integrating with other AI SDKs. Adjust your plan based on volume and retention needs.

python

from langfuse.openai import openai  # drop-in replacement for OpenAI SDK

client = openai.OpenAI(api_key=os.environ["OPENAI_API_KEY"])
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

output

Hello

Troubleshooting

If you see authentication errors, verify your LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY environment variables are set correctly.
For unexpected missing traces, ensure your functions are decorated with @observe() or that auto-tracing is enabled.
Check Langfuse dashboard for usage limits to avoid hitting free tier caps.

✅

Key Takeaways

Langfuse provides a free tier with usage-based paid plans for AI API observability.
Use the Langfuse Python SDK with environment variables for secure API key management.
Decorate functions with @observe() to trace AI calls and monitor costs effectively.

Verified 2026-04 · gpt-4o-mini

Verify ↗