Skip to main content

Lunar Platform

Lunar offers a complete set of tools for developers who want to distill, route, and deploy AI models. Our platform provides:

Platform Features

Access 12+ LLM providers through a single API. Features smart routing with AI task classification, automatic fallbacks, per-request cost tracking, and a comprehensive evaluation framework with 15+ built-in scorers.
Run open-source models like LLaMA, Qwen, DeepSeek, and more on dedicated GPU instances. Choose from 6 tiers ranging from NVIDIA L4 (24GB) to H200 clusters (1128GB).

Get Started

1

Install the SDK

pip install lunar-sdk
2

Set your API key

export LUNAR_API_KEY="pk_live_your_key"
3

Make your first request

from lunar import Lunar

client = Lunar()
response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Full Quickstart Guide

Learn more about the Lunar SDK

Pricing

TierGPUVRAMPriceBest For
XS1x L424GB~$0.20/h7B-13B models
S1x L40S48GB~$0.60/h13B-34B models
M4x A10G96GB~$1.80/h70B INT4
L4x L40S192GB~$3.50/h70B FP16
XL8x A100320-640GB~$12/h180B models
XXL8x H100/H200640-1128GB~$20-30/h405B models

Full Pricing Details

View complete pricing information

Community and Support