PageSourceSearch

https://lobe-chat-eight-virid-32.vercel.app/_next/static/chunks/10111.168de554494c5d0d.js

js lobe-chat-eight-virid-32.vercel.app collected 2026-10-03 07:17:03 UTC 1,364 bytes, 1 lines download raw bytes

1"use strict";(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[10111,32492],{32492:(e,i,t)=>{t.d(i,{default:()=>n});let n=[{abilities:{functionCall:!0,vision:!0},contextWindowTokens:1000192,description:"在 MiniMax-01系列模型中,我们做了大胆创新:首次大规模实现线性注意力机制,传统 Transformer架构不再是唯一的选择。这个模型的参数量高达4560亿,其中单次激活459亿。模型综合性能比肩海外顶尖模型,同时能够高效处理全球最长400万token的上下文,是GPT-4o的32倍,Claude-3.5-Sonnet的20倍。",displayName:"MiniMax-Text-01",enabled:!0,id:"MiniMax-Text-01",maxOutput:1000192,pricing:{currency:"CNY",input:1,output:8},releasedAt:"2025-01-15",type:"chat"},{abilities:{functionCall:!0,vision:!0},contextWindowTokens:245760,description:"适用于广泛的自然语言处理任务,包括文本生成、对话系统等。",displayName:"abab6.5s",enabled:!0,id:"abab6.5s-chat",maxOutput:245760,pricing:{currency:"CNY",input:1,output:1},type:"chat"},{abilities:{reasoning:!0},contextWindowTokens:64e3,description:"DeepSeek 推出的推理模型。在输出最终回答之前,模型会先输出一段思维链内容,以提升最终答案的准确性。",displayName:"DeepSeek R1",id:"DeepSeek-R1",maxOutput:64e3,pricing:{currency:"CNY",input:4,output:16},type:"chat"}]}}]);

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.