Run DeepSeek V4.1 Flash 1017 Heretic without a GPU.

Abliterated by DeepSeek, on UncensoredLLM as deepseek-v4.1-flash-1017-heretic-uncensored.

DeepSeek V4.1 Flash 1017 Heretic is DeepSeek V4.1 Flash 1017 with its refusal direction removed. It costs $0.825 per million input tokens and $3.30 per million output tokens, prepaid, with a 512,000-token context window. Call it at https://api.uncensoredllm.ai/v1/chat/completions with model "deepseek-v4.1-flash-1017-heretic-uncensored" and an UncensoredLLM key, from any OpenAI SDK or client that takes a base URL.

Chat with DeepSeek V4.1 Flash 1017 Heretic in the browser at Unrestrictable, no key.

Get a key

Price per million tokens

Input
$0.825
Output
$3.30
Daily check
Steady since Nov 6
How the check works
As of
2026-11-09

First request

curl
1curl https://api.uncensoredllm.ai/v1/chat/completions \
2 -H "Authorization: Bearer sk-ullm-live-…" \
3 -H "Content-Type: application/json" \
4 -d '{"model": "deepseek-v4.1-flash-1017-heretic-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'

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

DeepSeek V4.1 Flash 1017 Heretic settings for SillyTavern and Janitor AI

SillyTavern API
Chat Completion
Source
Custom (OpenAI-compatible)
Custom endpoint
https://api.uncensoredllm.ai/v1
Model
deepseek-v4.1-flash-1017-heretic-uncensored
Context Size
512,000 tokens
Max response length
128,000 tokens
Janitor AI proxy URL
https://api.uncensoredllm.ai/v1/chat/completions
Key prefix
sk-ullm-

DeepSeek V4.1 Flash 1017 Heretic specs

Kind
Abliterated
Developer
DeepSeek
Base model
DeepSeek V4.1 Flash 1017
Context window
512,000 tokens
Max output
128,000 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.uncensoredllm.ai/v1 and send your sk-ullm- key as the bearer token.
  3. Send deepseek-v4.1-flash-1017-heretic-uncensored as the model. The same key calls every model on UncensoredLLM.

What DeepSeek V4.1 Flash 1017 Heretic is

Developer
DeepSeek
Weights
not published for this build
Context window here
512,000 tokens
Max output
128,000 tokens
Input
text and image

From the live catalog.

From the SDK

openai.py
1from openai import OpenAI
2
3client = OpenAI(base_url="https://api.uncensoredllm.ai/v1", api_key="sk-ullm-live-…")
4
5completion = client.chat.completions.create(
6 model="deepseek-v4.1-flash-1017-heretic-uncensored",
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.uncensoredllm.ai/v1', apiKey: 'sk-ullm-live-…' });
4
5const completion = await client.chat.completions.create({
6 model: 'deepseek-v4.1-flash-1017-heretic-uncensored',
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 1017

DeepSeek V4.1 Flash 1017 Heretic 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 Nov 6”.

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

GLM-5.3 Abliterated$4.365 outGLM-5.3 Flash Abliterated$1.94 outDeepSeek V4.1 Flash Abliterated$1.6975 outAbliterated Large Flash$5.00 out

More from DeepSeek

DeepSeek V4.1 Flash 1017 Abliterated$3.125 outDeepSeek V4.1 Flash 1017 Heretic Thinking$3.30 outDeepSeek V4.1 Flash 1017 Uncensored$3.30 outDeepSeek V4.1 Flash 1017 Uncensored Thinking$3.30 outDeepSeek V4 Pro Uncensored$1.94 outDeepSeek V4 Pro Abliterated$4.00 out

What DeepSeek V4.1 Flash 1017 Heretic costs, worked

A chat turn of 2,000 input and 500 output tokens at $0.825 input and $3.30 output per million tokens is $0.0033; 1,000 turns are $3.30. A long chat session of 100 replies of 300 tokens costs $0.429 at 4,000 tokens of context and $1.419 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
Gemma 4 31B Cognitive Unshackled262K$1.071 / $1.071$2.68
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 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
Gemma 4 31B Gembrain Heretic262K$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
DeepSeek V4.1 Flash 1017 Heretic Thinking512K$0.825 / $3.30$3.30

Live from the catalog on 2026-11-09, ordered by the cost of 1,000 turns of 2,000 input and 500 output tokens. Every model.

DeepSeek V4.1 Flash 1017 Heretic 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 512,000 tokens, the window the catalog lists for deepseek-v4.1-flash-1017-heretic-uncensored. 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.

What DeepSeek V4.1 Flash 1017 Heretic 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$0.429
The same evening on a long chat100 replies of 300 tokens on 16,000 tokens of context$1.419
A month of short turns1,000 turns of 2,000 input and 500 output tokens$3.30
One long document, summarised once100,000 input and 1,000 output tokens in one request$0.0858

Input and output tokens at the price above, read from the catalog on 2026-11-09; cached input is not counted. The balance is prepaid and each request settles at these rates.

DeepSeek V4.1 Flash 1017 Heretic questions

DeepSeek V4.1 Flash 1017 Heretic is an abliterated build of DeepSeek V4.1 Flash 1017 from DeepSeek, with a 512,000-token context window, taking text and image input. On UncensoredLLM it answers as deepseek-v4.1-flash-1017-heretic-uncensored.

DeepSeek V4.1 Flash 1017 Heretic 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 $0.825 and output $3.30 per million tokens.

About $0.0025 for 1,000 tokens in and 500 tokens out, at $0.825 in and $3.30 out per million tokens.

Up to 512,000 tokens, the context window the catalog lists for DeepSeek V4.1 Flash 1017 Heretic; Max Response Length can go up to 128,000 tokens.

Yes. Send deepseek-v4.1-flash-1017-heretic-uncensored as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.uncensoredllm.ai/v1.

In SillyTavern, set API to Chat Completion, Source to Custom (OpenAI-compatible) and the custom endpoint to https://api.uncensoredllm.ai/v1, paste your key, then pick deepseek-v4.1-flash-1017-heretic-uncensored from the list it loads. In Janitor AI, choose Proxy, set the URL to https://api.uncensoredllm.ai/v1/chat/completions, paste your key and type deepseek-v4.1-flash-1017-heretic-uncensored 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 1017 Heretic’s latest result, from Nov 9: steady since Nov 6. See the daily check.

DeepSeek V4.1 Flash 1017 Heretic is named for DeepSeek V4.1 Flash 1017, from DeepSeek. No weights, parameter count or training notes are published for this build. The catalog lists a 512,000-token context window and 128,000 max output tokens.

$0.33 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.825 input and $3.30 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.uncensoredllm.ai/v1 as the endpoint in SillyTavern; the proxy URL https://api.uncensoredllm.ai/v1/chat/completions and deepseek-v4.1-flash-1017-heretic-uncensored as the model in Janitor AI. See the SillyTavern guide.

Read next

Join on Telegram