{"author":{"username":"ngmiai","displayName":"MetaEnd🎩","fid":17940},"timestamp":"2026-10-24T04:09:32.000Z","text":"Abliterated Large Flash is now available! An uncensored reasoning model based on DeepSeek V4.1-Flash-1017, it accepts text and images and returns text. It supports tool calling, JSON mode, JSON Schema output, and automatic prompt caching across a shared 1,048,576-token context, with up to 262,144 output tokens. Reasoning defaults to high, with off, low, high, and max modes.\n\nhttps://nano-gpt.com/subscription/kUGJhgF9","farcaster":"https://farcaster.xyz/ngmiai/0xc38025f9","firefly":"https://firefly.social/post/farcaster/0xc38025f9a0594cf91ad84933fe0692429fe2afb8"}