大模型
x.com ·
@LlamaIndex 🦙 (@llama_index)
LlamaIndex 发布 OpenDocRouter：用统一 API 切换文档解析模型
LlamaIndex 宣布推出 OpenDocRouter，将文档解析模型统一到一个 API 下。官方称 Hugging Face 上约有 4000 个 OCR 模型且前沿实验室几乎每月更新，因此重点从“选哪个模型”转向“多快能切换”。功能包括：一行代码切换模型并保持相同 markdown 输出；首发接入 10 个前沿与开源模型（含 Claude Opus 5.5、Gemini 3.8 Flash、GPT-6 Luna、MinerU2.5-Pro、PaddleOCR-VL-1.6）；用 ParseBench 对质量与成本打分；layout:true 可为任意模型输出带定位的边界框与统一版面类别；按 token 计费、失败页面不计费，最低充值 25 美元。官方给出的成本区间为每 1000 页 0.86 至 48.82 美元。上述模型清单、评分与定价均为厂商自述，片段中未提供可独立验证的证据。
AI推荐理由 LlamaIndex 官方账号发布的 OpenDocRouter 产品公告，属于一手来源，信息密度较高：给出统一 API 切换文档解析模型、首发 10 个模型、ParseBench 评分、按 token 计费与失败页不收费等具体机制，并给出每千页 0.86 至 48.82 美元的成本区间。局限在于内容为厂商自述，ParseBench 评分标准、模型清单真实性（如 Claude Opus 5.5、GPT-6 Luna 等命名）与定价细节均未在片段中提供可独立验证的证据，也未说明实际部署效果，需保留其宣传性质。
72
浏览 38,081
点赞 206
评论 24
转发 29
正文
Today we're announcing OpenDocRouter: every model for document parsing under one API.
There are ~4,000 OCR models on Hugging Face, and the frontier labs ship a new one nearly every month. Whatever's best for your docs today won't be by Q1.
So stop asking which model to use for doc parsing. Ask how fast you can switch.
✅ Switch models in one line: same request, same markdown output, no new prompts or integrations
✅ Any model you want: 10 frontier and open-source models at launch, including Claude Opus 5.5, Gemini 3.8 Flash, GPT-6 Luna, MinerU2.5-Pro and PaddleOCR-VL-1.6
✅ Choose with receipts: every model scored on ParseBench for quality and cost
✅ Traceable output from any model: "layout: true" adds grounded bounding boxes and the same layout classes, even for models that don't support it natively
✅ Pay only for what works: per-token pricing, failed pages never charged, top up from $25
The spread is the point: $0.86 to $48.82 per 1,000 pages, depending on what your documents actually need.
Live now → https://t.co/sXXygu3fPL