Models / Uncensored / DeepSeek
DeepSeek V4.1 Flash 1017 Heretic Thinking API pricing
$0.825 in, $3.30 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | DeepSeek list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.825 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $3.30 | — |
DeepSeek V4.1 Flash 1017 Heretic Thinking specs
- Context window
- 512,000 tokens
- Max output
- 128,000 tokens
- Input
- text and image
DeepSeek V4.1 Flash 1017 Heretic Thinking: DeepSeek V4.1 Flash with its refusals removed · DeepSeek's open weights, changed to answer
DeepSeek V4.1 Flash 1017 Heretic Thinking is an abliterated build: the refusal direction was removed from the weights, so it answers prompts the stock model declines, with nothing added to your prompt. The stock DeepSeek V4.1 Flash is 552B backbone, 8B active per token at prefill and 16B at decode, with up to one million tokens of context, released by DeepSeek under MIT (card read 2026-10-26). It is served as deepseek-v4.1-flash-1017-heretic-uncensored-thinking at $0.825 input and $3.30 output per million tokens, one of 161 builds in the uncensored LLM API, on the same key as every other model.
| DeepSeek V4.1 Flash 1017 Heretic Thinking | |
|---|---|
| Developer | DeepSeek |
| Kind | abliterated (refusal direction removed from the weights) |
| Base model | DeepSeek V4.1 Flash |
| 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 |
| Context window here | 512,000 tokens |
| Max output | 128,000 tokens |
| Input | text and image |
From deepseek-ai/DeepSeek-V4.1-Flash on Hugging Face (read 2026-10-26) and the live catalog.
The stock DeepSeek V4.1 Flash 1017 runs on the same key at $0.2425 / $1.164 per million tokens, so a tool switches between the two by model id. The other build of the same model here is DeepSeek V4.1 Flash 1017 Heretic at $0.825 / $3.30.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"deepseek-v4.1-flash-1017-heretic-uncensored-thinking","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'What abliterated means for DeepSeek V4.1 Flash 1017 Heretic Thinking · the daily real-model check is the live evidence
The direction in the model’s activations that makes it refuse was found and projected out of the weights, with no retraining: the model keeps what the stock build knows and stops declining. Nothing rides along with your prompt and no jailbreak preamble is billed. What it does with your prompts is the model's own call, so run them through it in your tool.
The daily real-model check is the live evidence: it confirms the model answering deepseek-v4.1-flash-1017-heretic-uncensored-thinking is the one we serve, checked every day.
DeepSeek V4.1 Flash 1017 Heretic Thinking next to the other uncensored models · per million tokens, live
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for DeepSeek V4.1 Flash 1017 Heretic Thinking: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.825 input and $3.30 output per million tokens, that is $1.65 + $1.65 = $3.30, paid from prepaid credit with no subscription.
DeepSeek V4.1 Flash 1017 Heretic Thinking API key · base URL and setup
- Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
- Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
- Send deepseek-v4.1-flash-1017-heretic-uncensored-thinking as the model. The same key calls every other model in the catalog.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="deepseek-v4.1-flash-1017-heretic-uncensored-thinking",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'deepseek-v4.1-flash-1017-heretic-uncensored-thinking',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"deepseek-v4.1-flash-1017-heretic-uncensored-thinking","messages":[{"role":"user","content":"Hello"}]}'DeepSeek V4.1 Flash 1017 Heretic Thinking settings for SillyTavern and Janitor AI · from the catalog row
- SillyTavern API
- Chat Completion
- Chat Completion Source
- Custom (OpenAI-compatible)
- Custom Endpoint (Base URL)
- https://api.uplinkswitch.com/v1
- Model ID
- deepseek-v4.1-flash-1017-heretic-uncensored-thinking
- Context (tokens)
- 512,000 tokens
- Max Response Length
- 128,000 tokens
- Janitor AI proxy URL
- https://api.uplinkswitch.com/v1/chat/completions
- Janitor AI model
- deepseek-v4.1-flash-1017-heretic-uncensored-thinking
- API key
- your sk-uplink- key
SillyTavern API Chat Completion
Chat Completion Source Custom (OpenAI-compatible)
Custom Endpoint (Base URL) https://api.uplinkswitch.com/v1
Model ID deepseek-v4.1-flash-1017-heretic-uncensored-thinking
Context (tokens) 512,000 tokens
Max Response Length 128,000 tokens
Janitor AI proxy URL https://api.uplinkswitch.com/v1/chat/completions
Janitor AI model deepseek-v4.1-flash-1017-heretic-uncensored-thinking
API key your sk-uplink- keyWhat would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from DeepSeek
DeepSeek V4 Pro 0813
$0.792 in · $1.188 out
DeepSeek V4.1 Flash
$0.0564 in · $0.1692 out
DeepSeek V4.1 Flash 0910 Uncensored
$0.825 in · $3.30 out
DeepSeek V4.1 Flash 0910 Uncensored Thinking
$0.825 in · $3.30 out
DeepSeek V4.1 Flash 1017
$0.2425 in · $1.164 out
DeepSeek V4.1 Flash 1017 Abliterated
$0.7275 in · $3.0313 out