What is an uncensored AI API?
An uncensored AI API provides hosted access to reduced-refusal models without running your own inference hardware. Authenticate with your RouterHub key and select a model by its exact API ID.
Set up your API key
- Create a RouterHub account and add prepaid credits in Billing.
- Create an API key in your dashboard and set
ROUTERHUB_API_KEYprivately in your terminal. - Choose the exact model ID and supported protocol from the catalogue below.
Keep the key out of browser JavaScript, public repositories and AI chats. Running an example sends a paid request.
Python and cURL examples
Example model: DeepSeek V4 Pro Uncensored (deepseek-v4-pro-uncensored). Install openai with pip install openai.
Python
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ROUTERHUB_API_KEY"],
base_url="https://routerhub.si/v1",
timeout=600.0,
max_retries=0,
)
response = client.chat.completions.create(
model="deepseek-v4-pro-uncensored",
messages=[{"role": "user", "content": "Write a short noir scene set in a lighthouse."}],
max_tokens=256,
)
print(response.choices[0].message.content)cURL
curl --connect-timeout 30 --max-time 600 https://routerhub.si/v1/chat/completions \
-H "Authorization: Bearer $ROUTERHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro-uncensored","messages":[{"role":"user","content":"Write a short noir scene set in a lighthouse."}],"max_tokens":256}'Streaming, retries and timeouts
For streaming Chat Completions, add stream=True in Python and read chunk.choices[0].delta.content when present. Streaming delivers incremental output. After a disconnect or timeout, check the request ID and Usage before resending a paid request.
The Python example sets a ten-minute client timeout and disables automatic retries. Intermediary timeouts are configured separately.
Instruction profiles
RouterHub’s prompt-profile uncensored variants use a server-managed instruction profile. Customer system/developer instructions can be replaced by that profile; put task-specific requirements in the user message.
