One base URL change.

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-ablit-...",
    base_url="https://api.ablitai.com/v1",
)

response = client.chat.completions.create(
    model="qwen3.8-27b-abliterated",
    messages=[{"role": "user", "content": "Your prompt"}],
)
print(response.choices[0].message.content)

cURL

curl https://api.ablitai.com/v1/chat/completions \
  -H "Authorization: Bearer $ABLITAI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.8-27b-abliterated","messages":[{"role":"user","content":"Your prompt"}]}'

Models

• qwen3.8-27b-abliterated — flagship; text-only at launch.
• qwen3-32b-abliterated — established alternative.

Call GET /v1/models to discover the currently available model IDs. Context limits and measured throughput will be published after hardware burn-in.

Authentication

Send the API key as a bearer token. Never put it in a URL, query string, client-side source repository, or support message.

Errors

• 401 — missing or invalid API key.
• 402 — insufficient token credits.
• 413 — request exceeds the configured context limit.
• 429 — rate limit reached.
• 503 — inference capacity temporarily unavailable.

Retention

AblitAI does not intentionally retain prompts or generated responses. Requests are processed in memory by the gateway and inference service. See the privacy notice for infrastructure-provider boundaries.