DeepSeek V4.1 Flash Uncensored Thinking 1017 API pricing

What is DeepSeek V4.1 Flash Uncensored Thinking 1017?

DeepSeek V4.1 Flash Uncensored Thinking 1017 is a text model in the Outrun catalog. Intended for general tasks that standard models may decline, including security research and red teaming. The base model is DeepSeek V4.1 Flash. The standard rate is $0.66 in / $2.64 out per 1M tokens.

What does uncensored mean?

Uncensored models are tuned or configured to refuse far less than mainstream chat models. Behaviour and quality differ by model, so test the one you choose.

Use of DeepSeek V4.1 Flash Uncensored Thinking 1017 is subject to the acceptable use terms in the Outrun Terms of Service.

What are the DeepSeek V4.1 Flash Uncensored Thinking 1017 model details?

How do I call DeepSeek V4.1 Flash Uncensored Thinking 1017?

Use your Outrun key and the exact model ID. Requests use prepaid USD credit.

curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4.1-flash-1017-uncensored-thinking-3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 8192
}'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.outrun.to/v1",
    api_key=os.environ["OUTRUN_API_KEY"],
)
reply = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-uncensored-thinking-3",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=8192,
)
print(reply.choices[0].message.content)

Which tools work with DeepSeek V4.1 Flash Uncensored Thinking 1017?

Any client that accepts an OpenAI-compatible base URL and a model ID can use deepseek-v4.1-flash-1017-uncensored-thinking-3. Setup guides: Roo Code for uncensored models, Cline (OpenAI Compatible), OpenCode, SillyTavern, LiteLLM.

Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.

How does DeepSeek V4.1 Flash Uncensored Thinking 1017 compare on cost?

Assumes 1,000 input + 300 output tokens per turn, repeated 1,000 times, at standard-tier rates without caching. Input / output shown per 1M tokens, rounded up to the cent.

Which similar models can I try?

Common questions about DeepSeek V4.1 Flash Uncensored Thinking 1017

Where can I find more models?