Tool Configuration

Onlist is compatible with any tool that supports the OpenAI API. You only need to change two settings: the base URL and the API key. This page shows the exact configuration for the most popular AI development tools.

What you need

1. An Onlist API token from your dashboard.
2. The base URL: https://onlist.io/v1.

That's it. Or, if you prefer, install the Onlist SDK for zero-config Python or JS/TS usage.

Claude Code

Set the environment variables before launching Claude Code:

export ANTHROPIC_BASE_URL=https://onlist.io
export ANTHROPIC_AUTH_TOKEN=YOUR_ONLIST_TOKEN

Or add them to your shell profile (~/.zshrc, ~/.bashrc):

echo 'export ANTHROPIC_BASE_URL=https://onlist.io' >> ~/.zshrc
echo 'export ANTHROPIC_AUTH_TOKEN=YOUR_ONLIST_TOKEN' >> ~/.zshrc
source ~/.zshrc

Claude Code uses the Anthropic Messages API (/v1/messages) under the hood. ANTHROPIC_AUTH_TOKEN sends the standard Authorization: Bearer header. ANTHROPIC_API_KEY (which sends x-api-key) also works, because Onlist normalizes both headers to the same account, but AUTH_TOKEN is the variable meant for third-party endpoints.

Cursor

Open Settings > Models > OpenAI API Key and enter:

Cursor sends requests through the OpenAI-compatible surface. After saving, select any model from the Onlist catalog (e.g. openai/gpt-4o, anthropic/claude-sonnet-4-20250514).

OpenAI SDK (Python)

from openai import OpenAI

client = OpenAI(
    base_url="https://onlist.io/v1",
    api_key="YOUR_ONLIST_TOKEN",
)

resp = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

OpenAI SDK (Node.js)

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://onlist.io/v1',
  apiKey: 'YOUR_ONLIST_TOKEN',
})

const resp = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Hello' }],
})
console.log(resp.choices[0].message.content)

Anthropic SDK

from anthropic import Anthropic

client = Anthropic(
    base_url="https://onlist.io",
    api_key="YOUR_ONLIST_TOKEN",
)

resp = client.messages.create(
    model="anthropic/claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.content[0].text)

Environment variables

For tools that read standard environment variables, set:

export OPENAI_API_KEY=YOUR_ONLIST_TOKEN
export OPENAI_BASE_URL=https://onlist.io/v1

This works with any OpenAI-compatible client, including litellm, langchain, and custom scripts.