NewHow we catch a seller listing the wrong model, and refund you if one does.

Where can I use an uncensored DeepSeek API?

On November 20, 2026, MartLLM served 2 uncensored DeepSeek models through an OpenAI-compatible API; DeepSeek V4.1 Flash 1017 Uncensored cost $0.2145 per million input tokens and $0.858 per million output tokens. Set the base URL to https://api.martllm.com/v1 and put the model id in the request. There is no ID or KYC check: sign up with an email code or with Google, then add prepaid credit by card or PayPal, from $5. A request that fails is not billed.

Prices as of November 20, 2026, 11:00 UTC. This page is rebuilt every hour.

ModelInput / 1M tokensOutput / 1M tokensBelow list price
DeepSeek V4.1 Flash 1017 Uncensored$0.2145$0.85835%
DeepSeek V4.1 Flash Uncensored$0.2244$0.897632%

MartLLM adds no fee to these prices · every model and price →

More questions

Does it work in SillyTavern and Janitor AI?

Yes. SillyTavern connects through Chat Completion → Custom (OpenAI-compatible) with base URL https://api.martllm.com/v1; Janitor AI uses a proxy configuration with https://api.martllm.com/v1/chat/completions. Both guides are at martllm.com/guides.

Is it the same model as DeepSeek’s own API?

No. Uncensored builds are separate models with their own ids and prices; the regular DeepSeek models are listed next to them and are called the same way.