- base_url = "https://api.openai.com/v1"+ base_url = "https://lowkeyai.top/api/v1"
Drop-in for the OpenAI SDK
Your code, your libraries, your streaming. Change the URL and the key.
every frontier model · one endpoint
Cheap AI.Every model.
One OpenAI-compatible endpoint for GPT, Claude, Gemini, DeepSeek, Grok and more. Built for people who ship with AI. Pay in crypto.
$ export OPENAI_BASE_URL=https://lowkeyai.top/api/v1zsh — lowkey
It's live. Click the terminal and try help models chat hello
// why lowkey
Swap one URL. Keep everything else.
Priced to the token
Every request is metered and logged. Sample traffic, live.
USDCBTCETHUSDTSOL
Pay in crypto
No card, no billing form.
$0.06/ 1M tokens
Cheap by default
Lowest input price on the list, shown up front.
model = "gpt-6-luna"
No lock-in
Switching models is a string.
// how it works
Three steps. About a minute.
Get a key
Sign up with an email and create an API key.
lk_xxxxxxxxxxxxxxxxSwap the base URL
Point the OpenAI SDK at LowKeyAI. Nothing else changes.
base_url="https://lowkeyai.top/api/v1"Pick any model
Use any model ID from the list. Switch whenever you like.
model="gpt-6-luna"// billing
Every call leaves a receipt.
Simulated stream for this demo. Your real receipts show up in the dashboard, logged per request.
// models
Find a model. Copy the ID.
loading…
| MODEL | PROVIDER | INPUT / 1M | OUTPUT / 1M |
|---|
no models match that search
Live prices. Click a row to copy its model ID.
// pricing
Know your bill before you build.
loading models…
Pay as you go
All models. Top up from $5.
Team
Shared balance, multiple API keys.
// docs
Two lines. That's the migration.
Use the SDK you already have. Pick any model by name.
from openai import OpenAI client = OpenAI( base_url="https://lowkeyai.top/api/v1", # changed api_key="lk_...", # changed) r = client.chat.completions.create( model="gpt-6-luna", messages=[{"role": "user", "content": "Hello"}],)
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://lowkeyai.top/api/v1", // changed apiKey: "lk_...", // changed}); const r = await client.chat.completions.create({ model: "gpt-6-luna", messages: [{ role: "user", content: "Hello" }],});
curl https://lowkeyai.top/api/v1/chat/completions \ -H "Authorization: Bearer lk_..." \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-6-luna", "messages": [{"role": "user", "content": "Hello"}] }'
// faq
Quick answers.
Is it OpenAI-compatible?
Yes. It uses the same chat completions format, so the official SDKs work after you change the base URL and the key.
Does streaming work?
Streaming responses work the same way they do with the OpenAI API.
How do I pay?
Top up your balance in the dashboard with crypto (USDT, ETH, BTC…). Usage is deducted per token.
Can I switch models without changing code?
Yes. The model is just a string in your request.
Is there a minimum?
No platform fee and no seats. You can top up from $5.
Ship it cheap.
No card. Add crypto balance when you're ready.