Quickstart

This page takes you from zero to a working API call.

1. Get an API key

Sign in to the console and create a key under API Keys. Keys look like sk-ablatic-.... The key is shown once, so copy it now. We store only a hash of it and cannot recover it later. Keep it server-side.

export ABLATIC_API_KEY="sk-ablatic-..."

Ablatic activates every account. To request access, use the contact form on ablatic.ai or email [email protected]. Once activated, you receive an email and a temporary password, set a new password on first login, then create your key.

2. Call the API

The endpoint is OpenAI-compatible, so the official OpenAI SDKs work unchanged. Only the base URL, key, and model differ.

cURL

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

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ablatic.ai/v1",
    api_key="sk-ablatic-...",
)

resp = client.chat.completions.create(
    model="talos",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

The model id is talos. By default it runs in thinking mode. For the lowest latency set reasoning_effort to none. See Models for the modes.

3. Stream the response

Set stream: true to receive tokens as they are generated over Server-Sent Events. The stream ends with a data: [DONE] line.

stream = client.chat.completions.create(
    model="talos",
    messages=[{"role": "user", "content": "Write a haiku about Linz"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")