On November 19, 2026, UberLLM served 2 uncensored DeepSeek models through an OpenAI-compatible API; DeepSeek V4.1 Flash Uncensored cost $0.1774 per million input tokens and $0.7095 per million output tokens. Set the base URL to https://api.uberllm.dev/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 19, 2026, 08:00 UTC. This page is rebuilt every hour.
Yes. SillyTavern connects through Chat Completion → Custom (OpenAI-compatible) with base URL https://api.uberllm.dev/v1; Janitor AI uses a proxy configuration with https://api.uberllm.dev/v1/chat/completions. Both guides are at uberllm.dev/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.