1. Create a key

Sign in with Google or an email magic link, open API Keys, and create a key. Store the complete value immediately because only its SHA-256 hash is retained.

2. Send a request

Use Auto for the first request. The response follows the familiar chat completion shape.

cURL

curl https://api.inferencepass.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCEPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

3. Switch your SDK

Existing OpenAI SDK integrations usually need only a new API key, base URL, and model selector.

Python

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFERENCEPASS_API_KEY"],
    base_url="https://api.inferencepass.com/v1",
)

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Explain vector databases."}],
)