Run Llama 3.3 70B Abliterated without a GPU.

Abliterated by huihui-ai, on Unrestrictable as llama-3.3-70b-abliterated.

Llama 3.3 70B Abliterated is an abliterated build. It costs $2.80 per million input tokens and $2.80 per million output tokens, prepaid, with a 32,768-token context window. Call it at https://api.unrestrictable.ai/v1/chat/completions with model "llama-3.3-70b-abliterated" and an Unrestrictable key, from any OpenAI SDK or client that takes a base URL.

Chat with Llama 3.3 70B Abliterated in the browser, no key: open the chat.

Get a key

Price per million tokens

Input
$2.80
Cached input
$2.80 (input rate)
Output
$2.80
Daily check
Steady since Oct 29
As of
2026-11-16

First request

curl
1curl https://api.unrestrictable.ai/v1/chat/completions \
2 -H "Authorization: Bearer sk-unr-live-…" \
3 -H "Content-Type: application/json" \
4 -d '{"model": "llama-3.3-70b-abliterated", "messages": [{"role": "user", "content": "Hello"}]}'

Base URL https://api.unrestrictable.ai/v1. The key comes from the console; prices settle per token.

Llama 3.3 70B Abliterated settings for SillyTavern and Janitor AI

SillyTavern API
Chat Completion
Source
Custom (OpenAI-compatible)
Custom endpoint
https://api.unrestrictable.ai/v1
Model
llama-3.3-70b-abliterated
Context Size
32,768 tokens
Janitor AI proxy URL
https://api.unrestrictable.ai/v1/chat/completions
Key prefix
sk-unr-

Llama 3.3 70B Abliterated specs

Kind
Abliterated
Developer
huihui-ai
Context window
32,768 tokens
Input
text
Wire formats
openai

Get a key

  1. Create a key in the console. Credit is prepaid from $10, with no subscription.
  2. Set OPENAI_BASE_URL to https://api.unrestrictable.ai/v1 and send your sk-unr- key as the bearer token.
  3. Send llama-3.3-70b-abliterated as the model. The same key calls every model on Unrestrictable.

What Llama 3.3 70B Abliterated is

Made by
huihui-ai
Method
Abliteration, no retraining
License on the card
llama3.3
Downloads, 30 days to 2026-10-20
21,795
Context window here
32,768 tokens
Input
text

From the Hugging Face card and its API record, read 2026-10-20.

From the SDK

openai.py
1from openai import OpenAI
2
3client = OpenAI(base_url="https://api.unrestrictable.ai/v1", api_key="sk-unr-live-…")
4
5completion = client.chat.completions.create(
6 model="llama-3.3-70b-abliterated",
7 messages=[{"role": "user", "content": "Hello"}],
8)
9print(completion.choices[0].message.content)
openai.ts
1import OpenAI from 'openai';
2
3const client = new OpenAI({ baseURL: 'https://api.unrestrictable.ai/v1', apiKey: 'sk-unr-live-…' });
4
5const completion = await client.chat.completions.create({
6 model: 'llama-3.3-70b-abliterated',
7 messages: [{ role: 'user', content: 'Hello' }],
8});
9console.log(completion.choices[0].message.content);

Guides: SillyTavern, Janitor AI, SDKs.

What Llama 3.3 70B Abliterated answers

Llama 3.3 70B Abliterated is an abliterated build: the refusal direction was removed from the weights, so it answers prompts the stock model declines. There is no system prompt trick to maintain and nothing the model has to be talked into.

Every request is routed to the build’s live route and settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Steady since Oct 29”.

Use it from the OpenAI SDK, from SillyTavern or Janitor, or from a coding agent. Keys and top-ups live in the console.

Also try

More from huihui-ai

What Llama 3.3 70B Abliterated costs, worked

A chat turn of 2,000 input and 500 output tokens at $2.80 input and $2.80 output per million tokens is $0.007; 1,000 turns are $7.00. A long chat session of 100 replies of 300 tokens costs $1.204 at 4,000 tokens of context and $4.564 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.

Abliterated buildsContextIn / out per 1M1,000 chat turns
Gemma 4 31B GemBrain Heretic262K$0.40 / $1.76$1.68
Gemma 4 26B-A4B ChimeraX Heretic262K$0.484 / $1.52$1.73
GLM-5.3 Flash Abliterated—$0.4656 / $1.94$1.90
Apex Flash 1 Abliterated262K$0.68 / $2.32$2.52
DeepSeek V4.1 Flash Abliterated—$0.8488 / $1.6975$2.55
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted262K$1.0389 / $1.0389$2.60
Qwen3.5 27B Blossom V6.4 Derestricted262K$1.071 / $1.071$2.68
Qwen3.5 27B BlueStar v3 Derestricted262K$1.071 / $1.071$2.68
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite262K$1.071 / $1.071$2.68
Qwen3.5 27B Queen Derestricted262K$1.071 / $1.071$2.68
DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic33K$1.12 / $1.12$2.80
DeepSeek V4.1 Flash 1017 Abliterated1000K$0.7275 / $3.0313$2.97
Gemma 4 31B Gembrain Heretic262K$1.224 / $1.224$3.06
Llama 3 70B Abliterated v3.58K$2.80 / $2.80$7.00
Llama 3.3 70B Abliterated33K$2.80 / $2.80$7.00
MiMo V2.6 Flash Abliterated1049K$2.00 / $6.00$7.00

Live from the catalog on 2026-11-16, ordered by the cost of 1,000 turns of 2,000 input and 500 output tokens. Every model.

Llama 3.3 70B Abliterated in SillyTavern and Janitor AI: what to set

The three fields are the base URL, the key and the model id, as in the settings above. What differs by build is the reply length, the reasoning switch and the context size, and those decide both whether a reply arrives whole and what each message costs.

  • Context Size up to 32,768 tokens, the window the catalog lists for llama-3.3-70b-abliterated. Every message resends the context, so set it to what the chat needs rather than the maximum.
  • No jailbreak preamble is needed and none should be sent: a preamble is resent and billed on every message, and this build answers without one.

A request that fails before the model answers is not billed. A refusal written as ordinary text is billed like any answer, which is the reason to send this build rather than a stock model with a preamble: the build does not write one.

What Llama 3.3 70B Abliterated costs by client

SessionWhat is sentAt the live price
SillyTavern or Janitor AI, one evening100 replies of 300 tokens on 4,000 tokens of context$1.204
The same evening on a long chat100 replies of 300 tokens on 16,000 tokens of context$4.564
A month of short turns1,000 turns of 2,000 input and 500 output tokens$7.00

Input and output tokens at the price above, read from the catalog on 2026-11-16, with no prompt caching assumed; cached input bills at the cached rate, or at the input rate on a model without one. The balance is prepaid and each request settles at these rates.

Llama 3.3 70B Abliterated questions

Llama 3.3 70B Abliterated is an abliterated build from huihui-ai, with a 32,768-token context window, taking text input. On Unrestrictable it answers as llama-3.3-70b-abliterated.

Llama 3.3 70B Abliterated is an abliterated build: the refusal direction was removed from the weights, so it answers prompts the stock model declines. There is no system prompt trick to maintain and nothing the model has to be talked into.

No. Credit is prepaid from $10 and billed per token: input $2.80 and output $2.80 per million tokens, cached input $2.80 (input rate).

About $0.0042 for 1,000 tokens in and 500 tokens out, at $2.80 in and $2.80 out per million tokens.

Up to 32,768 tokens, the context window the catalog lists for Llama 3.3 70B Abliterated.

Yes. Send llama-3.3-70b-abliterated as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.unrestrictable.ai/v1.

In SillyTavern, set API to Chat Completion, Source to Custom (OpenAI-compatible) and the custom endpoint to https://api.unrestrictable.ai/v1, paste your key, then pick llama-3.3-70b-abliterated from the list it loads. In Janitor AI, choose Proxy, set the URL to https://api.unrestrictable.ai/v1/chat/completions, paste your key and type llama-3.3-70b-abliterated as the model. See the docs.

Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Llama 3.3 70B Abliterated’s latest result, from Nov 15: steady since Oct 29. See the daily check.

Meta’s Llama 3.3 70B Instruct, with the refusal direction removed by huihui-ai’s abliteration (no retraining), per its card.

The card lists the Llama 3.3 license, inherited from Meta’s Llama 3.3 70B Instruct.

Yes, the weights are on Hugging Face (huihui-ai/Llama-3.3-70B-Instruct-abliterated, llama3.3, read 2026-10-20). Sending llama-3.3-70b-abliterated to https://api.unrestrictable.ai/v1 needs no download and no GPU: 100 replies cost $1.204 at the live price.

$0.70 for 100 chat turns of 2,000 input and 500 output tokens each, at $2.80 input and $2.80 output per million tokens, from prepaid credit with no subscription.

Yes, with the settings above: Chat Completion with a Custom (OpenAI-compatible) source and https://api.unrestrictable.ai/v1 as the endpoint in SillyTavern; the proxy URL https://api.unrestrictable.ai/v1/chat/completions and llama-3.3-70b-abliterated as the model in Janitor AI. See the SillyTavern guide.

Read next

Join on Telegram