Does Abliterated Large v2 support zero data retention?

Yes. Abliterated Large v2 is available with zero data retention on abliteration.ai through the Opper gateway.

Where is Abliterated Large v2 hosted?

Abliterated Large v2 runs on US hosting routes through the Opper gateway.

Is Abliterated Large v2 trained on prompts and outputs?

No. Every hosting route for Abliterated Large v2 is configured so customer prompts and outputs are not used to train models by default.

Abliterated Large v2

by abliteration.ai

Abliterated Large v2 is abliteration.ai's refusal-removed version of Z.ai's GLM-5.3, released on August 29, 2026. It keeps GLM-5.3's coding and agentic strengths while following through on the vulnerability research, exploit development and red-team tasks that the original declines. abliteration.ai reports 84.5% pass@1 on CyberGym and 41.8% on Terminal-Bench 4.0. The model is text-only with a context window of about one million tokens. It supports tool calling and strict structured output, and a reasoning_effort parameter from none to max sets the thinking budget. It suits offensive security research, penetration-testing agents, red-team evaluation of other models and long-horizon agent testing where refusals would stall the run.

Call Abliterated Large v2 on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

—

Input price

$3.00 /1M$0.30 cache read

Output price

$5.00 /1M

US residency available
Zero data retention on pay-as-you-go
No training by default

Available routes

Abliterated Large v2 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
abliteration.ai	US		No	$3.00	$5.00	$0.30

Data handling per route

Each route hosting Abliterated Large v2 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

abliteration.ai — United States🇺🇸

Zero data retention: nothing is logged or used for training. No training on customer data. US; unknown.

Zero data retention: Yes. Nothing is logged or used for training.
Training: No training on customer data.
Logging: None
Caching: Content cached for replay
GDPR DPA: No DPA
Transfer mechanism: unknown

Get started

Call Abliterated Large v2 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Abliterated Large v2 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "abliteration/abliterated-model-large-v2",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);