api reference

OpenAI-compatible

Use any OpenAI SDK. Set the base URL, set your key, choose a model id from the directory.

Base URL

https://abliteratly.beer/v1

Authentication

Send Authorization: Bearer YOUR_KEY. Create keys in the dashboard. Keys are shown once.

Chat completions

# curl
curl https://abliteratly.beer/v1/chat/completions \
  -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"model":"magnum-v4-72b","messages":[{"role":"user","content":"Hello"}],"stream":true}'

# python
from openai import OpenAI
client = OpenAI(base_url="https://abliteratly.beer/v1", api_key="YOUR_KEY")
r = client.chat.completions.create(model="magnum-v4-72b", messages=[{"role":"user","content":"Hello"}])
print(r.choices[0].message.content)

# node
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://abliteratly.beer/v1", apiKey: process.env.KEY });

Supported

POST /v1/chat/completions (streaming, tools, JSON mode, vision where the model supports it) and GET /v1/models. Responses, embeddings, audio and image endpoints are not offered.

Errors

Status	code	Meaning
401	invalid_api_key	Missing or revoked key
402	insufficient_credits	Balance too low for the maximum cost of this request. Lower `max_tokens` or top up
404	model_not_found	Unknown or disabled model id
429	rate_limit_exceeded	Per-account request limit. Honour `Retry-After`
502/503	upstream_error	Provider failure. Not charged. Retry

Billing notes

Set max_tokens to what you need: we hold the worst-case cost up front, so a huge limit on a small balance returns 402. Streaming responses include a final usage chunk with the charge in usage.cost (USD).