Uncensored DeepSeek API

What it is#

The uncensored variant is a separate model ID with its own price. It is not the same model as the standard deepseek-v4.1-flash, and no parameter or system prompt turns the standard model into it. Set model to deepseek-v4.1-flash-uncensored.

Live prices, 24-hour success rates and latency for every model are public on the pricing page; the uncensored variant has its own model page. Prices follow upstream changes, so treat the page as the source of truth.

Call it through the API#

Set the Base URL to https://api.flyrouter.ai/v1 and model to deepseek-v4.1-flash-uncensored. Everything else matches other OpenAI-compatible models:

curl https://api.flyrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash-uncensored",
    "messages": [{"role": "user", "content": "Describe a narrow alley on a rainy night"}]
  }'

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["FLYROUTER_API_KEY"], base_url="https://api.flyrouter.ai/v1")
response = client.chat.completions.create(
    model="deepseek-v4.1-flash-uncensored",
    messages=[{"role": "user", "content": "Describe a narrow alley on a rainy night"}],
)
print(response.choices[0].message.content)

No key yet? Follow the quickstart to sign up, add credit and create one.

Streaming#

Turn on streaming for chat and long-form output by adding "stream": true to the request body:

stream = client.chat.completions.create(
    model="deepseek-v4.1-flash-uncensored",
    messages=[{"role": "user", "content": "Describe a narrow alley on a rainy night"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

See streaming for reconnects and cancellation.

Use it in SillyTavern#

SillyTavern accepts custom OpenAI-compatible endpoints. Connect in five steps:

1. Open the API Connections panel and set API to Chat Completion.
2. Set Chat Completion Source to Custom (OpenAI-compatible).
3. Enter https://api.flyrouter.ai/v1 as the Custom Endpoint (Base URL).
4. Paste your FlyRouter API key into Custom API Key.
5. Type deepseek-v4.1-flash-uncensored into Enter a Model ID and click Connect.

Send one message after connecting, then check the model ID and charge in your console request log. Other clients with a custom OpenAI endpoint take the same three values; for Cherry Studio see the integration guide.

Try it first#

To test without writing code, open the playground with this model preselected.

Acceptable use#

Uncensored means the model itself applies fewer response restrictions. It does not make every use acceptable: the terms of service and applicable law still apply. Actual responses depend on the model, and this guide makes no promise about what it will or will not answer.

FAQ#

Can I turn the standard model into the uncensored one?#

No. They are different model IDs. Parameters and system prompts do not change the standard model's response policy.

Which endpoints are supported?#

The examples here use the OpenAI-compatible /v1/chat/completions endpoint with optional streaming. For other protocols, check the endpoint formats listed on the model page.

How is it billed?#

Input and output tokens are billed separately, and cache reads have their own rate. See live prices on the model page and estimate spend with the API cost calculator.