Quickstart

Get started with AutoDo

AutoDo provides an OpenAI-compatible API that gives you access to ChatGPT, Claude, Gemini, and other frontier models through a single endpoint with unified billing and usage tracking.

There are three ways to integrate with AutoDo, depending on how much control you want:

Approach	Best for
API	Full control, any language, no extra SDK required
OpenAI SDK	Existing OpenAI SDK code where you only want to swap the base URL
Codex	Using AutoDo as a model provider inside Codex CLI

Create an API key in the dashboard first, and make sure your account has available credits. All examples use https://autodo.work/v1 as the base URL.

AutoDo returns OpenAI-compatible responses, so standard SDKs usually only need a new base URL and API key.

export BASE_URL="https://autodo.work/v1"
export API_KEY="sk-***"

# Compatible with standard OpenAI SDKs
curl "$BASE_URL/chat/completions" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.3-codex","messages":[{"role":"user","content":"Hello"}]}'

Using the AutoDo API

The most direct way to use AutoDo is to send standard HTTP requests to /v1/chat/completions.

fetch('https://autodo.work/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer sk-***',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-5.3-codex',
    messages: [
      { role: 'user', content: 'Write a one sentence product tagline.' },
    ],
  }),
});

import requests

response = requests.post(
    'https://autodo.work/v1/chat/completions',
    headers={
        'Authorization': 'Bearer sk-***',
        'Content-Type': 'application/json',
    },
    json={
        'model': 'gpt-5.3-codex',
        'messages': [
            {'role': 'user', 'content': 'Write a one sentence product tagline.'},
        ],
    },
)

print(response.json())

Using the OpenAI SDK

If you already have code built on the OpenAI SDK, point it at AutoDo as a drop-in replacement.

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://autodo.work/v1',
  apiKey: process.env.AUTODO_API_KEY,
});

const completion = await openai.chat.completions.create({
  model: 'gpt-5.3-codex',
  messages: [
    { role: 'user', content: 'Write a one sentence product tagline.' },
  ],
});

console.log(completion.choices[0]?.message);

import os
from openai import OpenAI

client = OpenAI(
    base_url='https://autodo.work/v1',
    api_key=os.environ['AUTODO_API_KEY'],
)

completion = client.chat.completions.create(
    model='gpt-5.3-codex',
    messages=[
        {'role': 'user', 'content': 'Write a one sentence product tagline.'},
    ],
)

print(completion.choices[0].message)

Codex setup

Using Codex CLI? Add this provider to ~/.codex/config.toml:

# ~/.codex/config.toml
model = "gpt-5.3-codex"
model_provider = "autodo"

[model_providers.autodo]
name = "AutoDo"
base_url = "https://autodo.work/v1"
env_key = "AUTODO_API_KEY"

# shell
export AUTODO_API_KEY="sk-***"

Then set AUTODO_API_KEY=sk-*** in your shell and restart Codex.