Skip to content

DeepSeek · Chat

DeepSeek V4.1 Flash Uncensored

DeepSeek 🇨🇳ChatDeepSeek familyOne of its sources says the weights aren't publicly available.
From Venice's listing:
DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
Market median price
$0.5775 blended / 1M
Max context
1M
Listings
11
Providers
6

Evidence and sources

🤗 dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8 Model architecture, as its sources state it Released 10 Sep 2026Maker HQ: CN (according to DeepSeek's own website)
All rankings: #21 on NanoGPT recentlySources: Venice.ai data, Models.dev data, Morpheus Inference Marketplace data, llminfo researchPrimary data from Venice.ai from Models.dev: weights availability from Morpheus Inference Marketplace: architecture from llminfo research: release date

Advantages and trade-offs

Compared with 10 representative chat models

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Llmgatewaydeepseek-v4.1-flash-uncensoredSource: LLMGateway data1M$0.18cache read $0.005$0.65——
 NanoGPTdeepseek/deepseek-v4.1-flash-uncensoredSources: Models.dev data, NanoGPT1M$0.33cache read $0.0083$1.32——
 NanoGPTdeepseek/deepseek-v4.1-flash-uncensored:thinking · thinkingSources: Models.dev data, NanoGPT1M$0.33cache read $0.0083$1.32——
 NanoGPTInference by VeniceRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-uncensored · fp8Source: NanoGPTNot published by the provider$0.3465cache read $0.0087$1.386——
 NanoGPTInference by VeniceRegions: 🇺🇸 USdeepseek/deepseek-v4.1-flash-uncensored:thinking · thinking · fp8Source: NanoGPTNot published by the provider$0.3465cache read $0.0087$1.386——
 NanoGPTInference by HeabsyRegions: GLBdeepseek/deepseek-v4.1-flash-uncensored · fp8Source: NanoGPTNot published by the provider$0.42cache read $0.042$1.47254.7579ms
 NanoGPTInference by HeabsyRegions: GLBdeepseek/deepseek-v4.1-flash-uncensored:thinking · thinking · fp8Source: NanoGPTNot published by the provider$0.42cache read $0.042$1.47413.42,769ms
 Nokeepdeepseek-v4.1-flash-uncensoredSource: Models.dev data1M$0.45cache read $0.011$1.75——
 Unrestricteddeepseek-v4.1-flash-uncensoredSource: Models.dev data1M$0.15cache read $0.05$0.60——
 Venicedeepseek-v4-1-flash-uncensored · fp8Source: Venice.ai data1M$0.33cache read $0.0083$1.32——

1 listing without a price is hidden.

Benchmarks

No benchmark scores yet.

Also known as: deepseek v4.1 flash uncensored, deepseek-v4-1-flash-uncensored, deepseek/deepseek-v4.1-flash-uncensored, deepseek/deepseek-v4.1-flash-uncensored:thinking

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works