DeepSeek · Open weights

DeepSeek V4.1 Flash Uncensored Thinking

Added Oct 1, 2026Open weights

A lower-refusal finetune of DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. Supports a context window of up to 1M tokens.

Reasoning
Tools

Input: Text
Output: Text
Reasoning effort: none · low · medium · high
Discovery tier: Open weights

Pricing

USD per 1M tokens

Input: $0.33
Output: $1.32
Cache read: $0.0083

Reference prices as published by the model provider. API example

Specifications

Context window: 1M
Max output: 65.5K
Average output (7 days): 797 tokens; Longer than 65% of 468 models

Side by side

DeepSeek V4.1 Flash Uncensored Thinking compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Limits
	DeepSeek V4.1 Flash Uncensored ThinkingDeepSeekThis model	Gemma 4 31B Agares v1GoogleRemove
Provider	DeepSeek	Google
Discovery tier	Open weights	Open weights
Added	Oct 1, 2026	May 15, 2026
Context window	1.05MBest	262.14K
Max output	65.54K	—
Average output	797 tokens	129 tokens
Pricing, USD per 1M tokens
Input	$0.33	$0.31Best
Output	$1.32	$0.31Best
Cache read	$0.0083	—
Performance
Throughput	442.5 tok/s	—
Time to first token	5.8 s	—
Request success (24h)	93.1%	—
Capabilities
Reasoning	Yes	Yes
Tools	Yes	Yes
Vision	No	Yes
Reasoning effort	none, low, medium, high	none, high

Public evaluations

Benchmarks

There are no public benchmark results for these models yet.

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput: 442.5 tok/s; Faster than 97% of 254 models
Time to first token: 5.8 s; Quicker than 29% of 254 models
Prompt cache hits: 96.4%; About $0.0198 per 1M input tokens with caching
Request success (24h): 93.1%; Unstable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 27.1%

Healthy (98% or more)
Degraded (90–98%)
Down (under 90%)
No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart

curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash-uncensored:thinking",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash-uncensored:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.