Run DeepSeek V4.1 Flash Abliterated Fast without a GPU.

Abliterated by DeepSeek, on Unrestrictable as deepseek-v4.1-flash-abliterated-fast.

DeepSeek V4.1 Flash Abliterated Fast is DeepSeek V4.1 Flash with its refusal direction removed. It costs $1.75 per million input tokens and $3.50 per million output tokens, prepaid, with a 1,000,000-token context window. Call it at https://api.unrestrictable.ai/v1/chat/completions with model "deepseek-v4.1-flash-abliterated-fast" and an Unrestrictable key, from any OpenAI SDK or client that takes a base URL.

Chat with DeepSeek V4.1 Flash Abliterated Fast in the browser, no key: open the chat.

Get a key

Price per million tokens

Input
$1.75
Cached input
$0.40
Output
$3.50
Daily check
Steady since Oct 25
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": "deepseek-v4.1-flash-abliterated-fast", "messages": [{"role": "user", "content": "Hello"}]}'

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

DeepSeek V4.1 Flash Abliterated Fast settings for SillyTavern and Janitor AI

SillyTavern API
Chat Completion
Source
Custom (OpenAI-compatible)
Custom endpoint
https://api.unrestrictable.ai/v1
Model
deepseek-v4.1-flash-abliterated-fast
Context Size
1,000,000 tokens
Max response length
65,536 tokens
Janitor AI proxy URL
https://api.unrestrictable.ai/v1/chat/completions
Key prefix
sk-unr-

DeepSeek V4.1 Flash Abliterated Fast specs

Kind
Abliterated
Developer
DeepSeek
Base model
DeepSeek V4.1 Flash
Context window
1,000,000 tokens
Max output
65,536 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 deepseek-v4.1-flash-abliterated-fast as the model. The same key calls every model on Unrestrictable.

What DeepSeek V4.1 Flash Abliterated Fast is

Base parameters
552B backbone, 8B active per token at prefill and 16B at decode
Base context, per the card
up to one million tokens
License of the base, read 2026-10-26
MIT
Kind
abliterated: refusal direction removed from the weights
Context window here
1,000,000 tokens
Max output
65,536 tokens
Input
text and image

From deepseek-ai/DeepSeek-V4.1-Flash on Hugging Face (read 2026-10-26) and the live catalog.

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="deepseek-v4.1-flash-abliterated-fast",
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: 'deepseek-v4.1-flash-abliterated-fast',
7 messages: [{ role: 'user', content: 'Hello' }],
8});
9console.log(completion.choices[0].message.content);

Guides: SillyTavern, Janitor AI, SDKs.

What changed from stock DeepSeek V4.1 Flash

DeepSeek V4.1 Flash Abliterated Fast 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 25”.

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 DeepSeek

What DeepSeek V4.1 Flash Abliterated Fast costs, worked

A chat turn of 2,000 input and 500 output tokens at $1.75 input and $3.50 output per million tokens is $0.0053; 1,000 turns are $5.25. A long chat session of 100 replies of 300 tokens costs $0.805 at 4,000 tokens of context and $2.905 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
DeepSeek V4.1 Flash 1017 Abliterated Fast1000K$1.75 / $3.50$5.25
DeepSeek V4.1 Flash Abliterated Fast1000K$1.75 / $3.50$5.25
GLM-4.6 Derestricted v5131K$1.40 / $5.25$5.43

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.

DeepSeek V4.1 Flash Abliterated Fast 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.

  • Same weights and the same reasoning switch as DeepSeek V4.1 Flash Abliterated: reasoning effort none for a direct reply, or Max Response Length of 1,000 or more.
  • The catalog lists a one-million-token window; a Context Size of 16,000 to 32,000 is enough for a card and a long chat and keeps the per-message cost down.
  • 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 DeepSeek V4.1 Flash Abliterated Fast 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$0.805
The same evening on a long chat100 replies of 300 tokens on 16,000 tokens of context$2.905
A month of short turns1,000 turns of 2,000 input and 500 output tokens$5.25
One long document, summarised once100,000 input and 1,000 output tokens in one request$0.1785

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.

DeepSeek V4.1 Flash Abliterated Fast questions

DeepSeek V4.1 Flash Abliterated Fast is an abliterated build of DeepSeek V4.1 Flash from DeepSeek, with a 1,000,000-token context window, taking text and image input. On Unrestrictable it answers as deepseek-v4.1-flash-abliterated-fast.

DeepSeek V4.1 Flash Abliterated Fast 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 $1.75 and output $3.50 per million tokens, cached input $0.40.

About $0.0035 for 1,000 tokens in and 500 tokens out, at $1.75 in and $3.50 out per million tokens.

Up to 1,000,000 tokens, the context window the catalog lists for DeepSeek V4.1 Flash Abliterated Fast; Max Response Length can go up to 65,536 tokens.

Yes. Send deepseek-v4.1-flash-abliterated-fast 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 deepseek-v4.1-flash-abliterated-fast 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 deepseek-v4.1-flash-abliterated-fast 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. DeepSeek V4.1 Flash Abliterated Fast’s latest result, from Nov 16: steady since Oct 25. See the daily check.

DeepSeek's DeepSeek V4.1 Flash: 552B backbone, 8B active per token at prefill and 16B at decode, up to one million tokens of context, open weights under MIT (deepseek-ai/DeepSeek-V4.1-Flash, read 2026-10-26). This build has the refusal direction removed from those weights.

The stock DeepSeek V4.1 Flash is released under MIT (deepseek-ai/DeepSeek-V4.1-Flash on Hugging Face, read 2026-10-26). DeepSeek V4.1 Flash Abliterated Fast is a build of those weights; sending deepseek-v4.1-flash-abliterated-fast here needs no copy of them.

Yes: deepseek-v4.1-flash-abliterated-fast at https://api.unrestrictable.ai/v1 on the OpenAI format, $1.75 / $3.50 per million tokens in / out, from prepaid credit with no subscription. DeepSeek V4.1 Flash Abliterated is the other DeepSeek V4.1 Flash build on the same key, at $0.8488 / $1.6975 per million tokens in / out. Point SillyTavern, Janitor AI or the OpenAI SDK at that base URL with your key and this model id. See DeepSeek V4.1 Flash Abliterated.

Unrestrictable does: deepseek-v4.1-flash-abliterated-fast at https://api.unrestrictable.ai/v1 on the OpenAI format, $1.75 / $3.50 per million tokens in / out. Point SillyTavern, Janitor AI or the OpenAI SDK at that base URL with your key and this model id.

Same abliterated weights, two routes: Fast is the lower-latency route. DeepSeek V4.1 Flash Abliterated Fast is $1.75 / $3.50 per million tokens in / out; DeepSeek V4.1 Flash Abliterated is $0.8488 / $1.6975 per million tokens in / out. Both answer the same base URL and key, so a tool switches between them by model id. See DeepSeek V4.1 Flash Abliterated.

Neither: it is prepaid credit from $10, billed per token, with no monthly fee. One reply of 300 tokens on 4,000 tokens of context costs about $0.0081 at the live price, and 100 such replies $0.805.

The stock DeepSeek V4.1 Flash is open weights (552B backbone, 8B active per token at prefill and 16B at decode, MIT on deepseek-ai/DeepSeek-V4.1-Flash, read 2026-10-26), and community uncensored conversions are published on Hugging Face at the same size. Sending deepseek-v4.1-flash-abliterated-fast to https://api.unrestrictable.ai/v1 needs no download and no GPU: 100 replies cost $0.805 at the live price.

$0.525 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.75 input and $3.50 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 deepseek-v4.1-flash-abliterated-fast as the model in Janitor AI. See the SillyTavern guide.

Read next

Join on Telegram