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.
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 https://api.unrestrictable.ai/v1/chat/completions \ -H "Authorization: Bearer sk-unr-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "llama-3.3-70b-abliterated", "messages": [{"role": "user", "content": "Hello"}]}'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
- Create a key in the console. Credit is prepaid from $10, with no subscription.
- Set OPENAI_BASE_URL to https://api.unrestrictable.ai/v1 and send your sk-unr- key as the bearer token.
- Send llama-3.3-70b-abliterated as the model. The same key calls every model on Unrestrictable.
What Llama 3.3 70B Abliterated is
- Base model
- 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 SDK
from openai import OpenAI client = OpenAI(base_url="https://api.unrestrictable.ai/v1", api_key="sk-unr-live-…") completion = client.chat.completions.create( model="llama-3.3-70b-abliterated", messages=[{"role": "user", "content": "Hello"}],)print(completion.choices[0].message.content)import OpenAI from 'openai'; const client = new OpenAI({ baseURL: 'https://api.unrestrictable.ai/v1', apiKey: 'sk-unr-live-…' }); const completion = await client.chat.completions.create({ model: 'llama-3.3-70b-abliterated', messages: [{ role: 'user', content: 'Hello' }],});console.log(completion.choices[0].message.content);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 builds | Context | In / out per 1M | 1,000 chat turns |
|---|---|---|---|
| Gemma 4 31B GemBrain Heretic | 262K | $0.40 / $1.76 | $1.68 |
| Gemma 4 26B-A4B ChimeraX Heretic | 262K | $0.484 / $1.52 | $1.73 |
| GLM-5.3 Flash Abliterated | — | $0.4656 / $1.94 | $1.90 |
| Apex Flash 1 Abliterated | 262K | $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 Derestricted | 262K | $1.0389 / $1.0389 | $2.60 |
| Qwen3.5 27B Blossom V6.4 Derestricted | 262K | $1.071 / $1.071 | $2.68 |
| Qwen3.5 27B BlueStar v3 Derestricted | 262K | $1.071 / $1.071 | $2.68 |
| Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite | 262K | $1.071 / $1.071 | $2.68 |
| Qwen3.5 27B Queen Derestricted | 262K | $1.071 / $1.071 | $2.68 |
| DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic | 33K | $1.12 / $1.12 | $2.80 |
| DeepSeek V4.1 Flash 1017 Abliterated | 1000K | $0.7275 / $3.0313 | $2.97 |
| Gemma 4 31B Gembrain Heretic | 262K | $1.224 / $1.224 | $3.06 |
| Llama 3 70B Abliterated v3.5 | 8K | $2.80 / $2.80 | $7.00 |
| Llama 3.3 70B Abliterated | 33K | $2.80 / $2.80 | $7.00 |
| MiMo V2.6 Flash Abliterated | 1049K | $2.00 / $6.00 | $7.00 |
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
| Session | What is sent | At the live price |
|---|---|---|
| SillyTavern or Janitor AI, one evening | 100 replies of 300 tokens on 4,000 tokens of context | $1.204 |
| The same evening on a long chat | 100 replies of 300 tokens on 16,000 tokens of context | $4.564 |
| A month of short turns | 1,000 turns of 2,000 input and 500 output tokens | $7.00 |
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.