DeepSeek · Open weights
DeepSeek V4.1 Flash Uncensored Thinking
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.
| DeepSeek V4.1 Flash Uncensored ThinkingDeepSeekThis model | DeepSeek V4 Flash 0423 (Thinking)DeepSeekRemove | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Discovery tier | Open weights | Open weights |
| Added | Oct 1, 2026 | Oct 7, 2026 |
| Limits | ||
| Context window | 1.05M | 1.05M |
| Max output | 65.54K | — |
| Average output | 797 tokens | 1.1K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.33 | $0.14Best |
| Output | $1.32 | $0.28Best |
| Cache read | $0.0083Best | $0.028 |
| Performance | ||
| Throughput | 442.5 tok/sBest | 89.6 tok/s |
| Time to first token | 5.8 s | 1.9 sBest |
| Request success (24h) | 93.1% | 96.8%Best |
| Benchmark indexes | ||
| Intelligence Index | — | 24.4 |
| Coding Index | — | 52.0 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Structured output | No | Yes |
| Reasoning effort | none, low, medium, high | none, low, high, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- DeepSeek V4.1 Flash Uncensored Thinking
- DeepSeek V4 Flash 0423 (Thinking)
Intelligence Index
- DeepSeek V4.1 Flash Uncensored Thinking—
- DeepSeek V4 Flash 0423 (Thinking)24.4
Indexes
Coding Index
Composite of the coding evaluations
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 52.0
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 28.5%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 8.7%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 1,041 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 1,000 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 10.4%
AA-LCRv1.1
Reasoning across long documents
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 72.0%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 30.3%
GPQA Diamond
Graduate-level science questions
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 86.7%
IFBench
Following precise output instructions
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 73.5%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 3.0%
SciCode
Scientific computing in Python
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 40.2%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 38.6%
τ²-Bench Telecom
Tool use in a customer-support simulation
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 95.6%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- DeepSeek V4.1 Flash Uncensored Thinking: —
- DeepSeek V4 Flash 0423 (Thinking): 72.0%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
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.
- 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.
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
Related models
Other DeepSeek models, starting with the same family.