DeepSeek v4.1 Flash 1017 Uncensored
deepseek-v4.1-flash-uncensoreddealignai's uncensored DeepSeek-V4.1-Flash-1017 (FP8), served by Our Cloud on our own GPUs. Multimodel 1M context, thinking off by default. Speed Up to 250 tok/s
Best for
Characteristics
Modalities
Use cases
Anthropic
Yes
Chat Completions
Responses Api
Yes
Provider
DeepSeek
Context Window
1M
Prices shown per 1M tokens.
Input
Rp. 3.875
$0.21 USD
Output
Rp. 13.763
$0.76 USD
Cache
Rp. 490
$0.03 USD
All prices are estimates and subject to change.
Similar Models
Related models selected by the catalog administrator.
deepseek-v4.1-flash-fastDeepSeek V4.1 Flash 1017 Fast, powered by FENRIR's high-performance inference infrastructure. Delivers up to 350 tokens/sec with up to 95% cache hit rate. Optimized for fast coding, complex reasoning, AI agents, and high-throughput applications.
deepseek-v4.1-flashIntroducing the smallest model in DeepSeek new architecture family, with native visual understanding. Designed for greater capability, faster inference, higher throughput, and scaling to larger models