Run Qwen3.5 27B Blossom V6.4 Derestricted without a GPU.

Abliterated by Qwen (community tune), on Unrestrictable as qwen3.5-27b-blossom-v6.4-derestricted.

Qwen3.5 27B Blossom V6.4 Derestricted is Qwen3.5 27B with its refusal direction removed. It costs $1.071 per million input tokens and $1.071 per million output tokens, prepaid, with a 262,144-token context window. Call it at https://api.unrestrictable.ai/v1/chat/completions with model "qwen3.5-27b-blossom-v6.4-derestricted" and an Unrestrictable key, from any OpenAI SDK or client that takes a base URL.

Chat with Qwen3.5 27B Blossom V6.4 Derestricted in the browser, no key: open the chat.

Get a key

Price per million tokens

Input
$1.071
Cached input
$1.071 (input rate)
Output
$1.071
Daily check
Steady since Oct 23
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": "qwen3.5-27b-blossom-v6.4-derestricted", "messages": [{"role": "user", "content": "Hello"}]}'

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

Qwen3.5 27B Blossom V6.4 Derestricted settings for SillyTavern and Janitor AI

SillyTavern API
Chat Completion
Source
Custom (OpenAI-compatible)
Custom endpoint
https://api.unrestrictable.ai/v1
Model
qwen3.5-27b-blossom-v6.4-derestricted
Context Size
262,144 tokens
Janitor AI proxy URL
https://api.unrestrictable.ai/v1/chat/completions
Key prefix
sk-unr-

Qwen3.5 27B Blossom V6.4 Derestricted specs

Kind
Abliterated
Developer
Qwen (community tune)
Base model
Qwen3.5 27B
Context window
262,144 tokens
Input
text and image
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 qwen3.5-27b-blossom-v6.4-derestricted as the model. The same key calls every model on Unrestrictable.

What Qwen3.5 27B Blossom V6.4 Derestricted is

Made by
Azure99 (Blossom)
Method
Derestricted build of Blossom V6.4 (no card published)
License on the card
apache-2.0 (Blossom V6.4 27B)
Context window here
262,144 tokens
Input
text and image

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="qwen3.5-27b-blossom-v6.4-derestricted",
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: 'qwen3.5-27b-blossom-v6.4-derestricted',
7 messages: [{ role: 'user', content: 'Hello' }],
8});
9console.log(completion.choices[0].message.content);

Guides: SillyTavern, Janitor AI, SDKs.

What changed from stock Qwen3.5 27B

Qwen3.5 27B Blossom V6.4 Derestricted 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 23”.

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 Qwen (community tune)

What Qwen3.5 27B Blossom V6.4 Derestricted costs, worked

A chat turn of 2,000 input and 500 output tokens at $1.071 input and $1.071 output per million tokens is $0.0027; 1,000 turns are $2.68. A long chat session of 100 replies of 300 tokens costs $0.4605 at 4,000 tokens of context and $1.7457 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
Gemma 4 31B SDFT Heretic RP262K$1.224 / $1.224$3.06
GLM-5.3 Flash Apex Abliterated1049K$0.80 / $3.20$3.20
DeepSeek V4.1 Flash 1017 Heretic512K$0.825 / $3.30$3.30

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.

Qwen3.5 27B Blossom V6.4 Derestricted 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 262,144 tokens, the window the catalog lists for qwen3.5-27b-blossom-v6.4-derestricted. 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 Qwen3.5 27B Blossom V6.4 Derestricted 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$0.4605
The same evening on a long chat100 replies of 300 tokens on 16,000 tokens of context$1.7457
A month of short turns1,000 turns of 2,000 input and 500 output tokens$2.6775
One long document, summarised once100,000 input and 1,000 output tokens in one request$0.1082

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.

Qwen3.5 27B Blossom V6.4 Derestricted questions

Qwen3.5 27B Blossom V6.4 Derestricted is an abliterated build of Qwen3.5 27B from Qwen (community tune), with a 262,144-token context window, taking text and image input. On Unrestrictable it answers as qwen3.5-27b-blossom-v6.4-derestricted.

Qwen3.5 27B Blossom V6.4 Derestricted 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 $1.071 and output $1.071 per million tokens, cached input $1.071 (input rate).

About $0.0016 for 1,000 tokens in and 500 tokens out, at $1.071 in and $1.071 out per million tokens.

Up to 262,144 tokens, the context window the catalog lists for Qwen3.5 27B Blossom V6.4 Derestricted.

Yes. Send qwen3.5-27b-blossom-v6.4-derestricted 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 qwen3.5-27b-blossom-v6.4-derestricted 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 qwen3.5-27b-blossom-v6.4-derestricted 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. Qwen3.5 27B Blossom V6.4 Derestricted’s latest result, from Nov 16: steady since Oct 23. See the daily check.

Azure99’s Blossom V6.4 27B, itself Qwen’s Qwen3.5 27B post-trained in two SFT stages on the published Blossom V6.3 data, per its card. No card for the Derestricted build is published.

No card for the Derestricted build is published. Blossom V6.4 27B, the tune it is made from, lists Apache-2.0, as does Qwen3.5 27B.

Yes, the weights are on Hugging Face (Azure99/Blossom-V6.4-27B, apache-2.0 (Blossom V6.4 27B), read 2026-10-20). Sending qwen3.5-27b-blossom-v6.4-derestricted to https://api.unrestrictable.ai/v1 needs no download and no GPU: 100 replies cost $0.4605 at the live price.

$0.2678 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.071 input and $1.071 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 qwen3.5-27b-blossom-v6.4-derestricted as the model in Janitor AI. See the SillyTavern guide.

Read next

Join on Telegram