Quickstart

Get a key#

Sign in to the console and create an API key. Each key belongs to a workspace, so its usage and budget are that workspace's. You can revoke a key at any time. See API keys.

When you first sign in, you land in your personal space, which has a default workspace. Requests are paid from the wallet of the space the key belongs to, so add credits before your first call (Credits).

Swap base_url#

Where you create the OpenAI client, set base_url to https://api.lune.io/v1. The SDK version, request shape, and response shape stay the same.

diff

  from openai import OpenAI

  client = OpenAI(
      api_key=os.environ["OPENAI_API_KEY"],
    - base_url="https://api.openai.com/v1",
    + base_url="https://api.lune.io/v1",
  )

The Anthropic and Gemini SDKs work the same way. Point each SDK at its base URL below. Each SDK's native auth header works (Authorization: Bearer, x-api-key, or x-goog-api-key), and all three take the same sk- key.

SDK	base_url	Endpoint
OpenAI	`https://api.lune.io/v1`	`/chat/completions` · `/embeddings` · `/images/generations` · `/responses`
Anthropic	`https://api.lune.io/v1`	`/messages`
Gemini	`https://api.lune.io/v1beta`	`/models/{model}:generateContent`

First request#

Set API_KEY in your environment and send a request. The response has the same shape as OpenAI's.

bash

curl https://api.lune.io/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [
      {"role": "user", "content": "Say hello in five words."}
    ]
  }'

python

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["API_KEY"],
    base_url="https://api.lune.io/v1",
)

resp = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Say hello in five words."}],
)

print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.API_KEY,
  baseURL: "https://api.lune.io/v1",
});

const resp = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-pro",
  messages: [{ role: "user", content: "Say hello in five words." }],
});

console.log(resp.choices[0].message.content);

package main

import (
    "context"
    "fmt"
    "os"

    "github.com/sashabaranov/go-openai"
)

func main() {
    cfg := openai.DefaultConfig(os.Getenv("API_KEY"))
    cfg.BaseURL = "https://api.lune.io/v1"
    client := openai.NewClientWithConfig(cfg)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "deepseek/deepseek-v4-pro",
            Messages: []openai.ChatCompletionMessage{
                {Role: "user", Content: "Say hello in five words."},
            },
        },
    )
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

Models use a vendor/slug id, for example deepseek/deepseek-v4-pro. Every id is listed on Models. For tags, see Endpoints & models.

Where to go next#

Calling more than chat: Endpoints & models, Streaming.
Something failed: Errors & rate limits.
Control where requests go and what upstream providers may keep: Provider routing, Data policy.
Working with a team: Organizations, Workspaces, Budgets.