Uncensored DeepSeek API

The uncensored DeepSeek model is a variant of DeepSeek V4.1 Flash with fewer response restrictions. On FlyRouter its model ID is deepseek-v4.1-flash-uncensored. It is a separate model with its own price, called through the OpenAI-compatible API.

FlyRouter team4 min readUpdated

Uncensored DeepSeek API

At a glance

ItemDetails
Model IDdeepseek-v4.1-flash-uncensored
FamilyDeepSeek V4.1 Flash
TypeText chat model
EndpointOpenAI-compatible Chat Completions (/v1/chat/completions), with streaming
BillingPer token; input, output and cache reads each have their own rate
Price and statusThe model page shows live prices, 24-hour success rate and latency

How it differs from the standard model

Uncensored means the model itself applies fewer response restrictions. It and the standard deepseek-v4.1-flash are two models, not one model with a switch.

StandardUncensored
Model IDdeepseek-v4.1-flashdeepseek-v4.1-flash-uncensored
Response restrictionsDeepSeek's default policyFewer
PriceIts own rateIts own rate, different from standard
How to callOpenAI compatibleOpenAI compatible, same request shape

The model ID is the only switch

No parameter or system prompt turns the standard model into the uncensored one. To use it, set model to deepseek-v4.1-flash-uncensored.

For everyday Q&A, code and summaries, the standard model is enough. Move to the uncensored variant only when the standard model's refusals get in your way, for example with fiction or screenwriting.

Model IDs in the DeepSeek family today:

Model IDNotes
deepseek-v4.1-flashStandard Flash
deepseek-v4.1-flash-uncensoredUncensored variant, the subject of this page
deepseek-v4.1-flash-1017October 17 snapshot of Flash
deepseek-v4-proPro

Live prices for each are on the pricing page. Prices follow upstream changes, so treat the page as the source of truth.

Call it

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"}]
  }'

Turn on streaming for long output; see streaming for reconnects and cancellation. No key yet? Follow the quickstart to sign up, add credit and create one. To test without writing code, open the playground with this model preselected.

Acceptable use

Uncensored does not make every use acceptable: the terms of service and applicable law still apply. Actual responses depend on the model, and this page makes no promise about what it will or will not answer.

FAQ

Do I need to enable it separately?

No. Create an API key and set model to deepseek-v4.1-flash-uncensored. If your key is limited to specific models, add this one to its allowed list first.

Which endpoints are supported?

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.

One key to a faster, more reliable enterprise AI gateway