Lunar SDK Overview

Python SDK for PureAI LLM Inference API with intelligent fallbacks and built-in evaluations

Lunar SDK

Lunar is a Python SDK that provides a simple, OpenAI-compatible interface to access multiple LLM providers through the PureAI API. It features intelligent fallback mechanisms, per-request cost tracking, and a built-in evaluation framework.

Key Features

OpenAI-Compatible

Drop-in replacement for OpenAI SDK. Migrate existing code with minimal changes.

Intelligent Fallbacks

Automatic retry with fallback models when providers experience issues.

Cost Tracking

Real-time cost tracking for every request with token-level granularity.

Built-in Evals

Comprehensive evaluation framework with 15+ built-in scorers.

Clients

The SDK provides two client classes:

Client	Description
Lunar	Synchronous client for standard applications
AsyncLunar	Asynchronous client for high-performance applications

Quick Example

from lunar import Lunar

client = Lunar(api_key="your-api-key")

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)
print(f"Cost: ${response.usage.total_cost_usd}")

Resources

The SDK exposes these resources:

Resource	Description
client.chat.completions	Chat completion API (messages-based)
client.completions	Text completion API (prompt-based)
client.models	List available models
client.providers	List available providers
client.evals	Run evaluations
client.datasets	Manage evaluation datasets

Next Steps

Quickstart

Get started in 5 minutes

Installation

Full installation guide

Chat Completions

Learn the Chat API

Evaluations

Test your LLM outputs