Getting started

The API is OpenAI-compatible. If your code already calls OpenAI, two settings are all that change.

1. 1

   Create a key

   Sign in, open API keys, and create one. The secret is shown once — we store only a hash, so it cannot be recovered afterwards.

2. 2

   Point your client at us

   from openai import OpenAI
   
   client = OpenAI(
       base_url="https://api.aiomodels.dev/v1",
       api_key="sk_live_...",
   )

3. 3

   Make a request

   completion = client.chat.completions.create(
       model="claude-haiku-4-5",
       messages=[{"role": "user", "content": "Hello"}],
   )
   
   print(completion.choices[0].message.content)

   Set stream=True for server-sent events. Token usage arrives in the final frame.