Scaledown 推出约束解码模型家族上线 OpenRouter
A family of constrained-decoding models from @scaledown_team is live on OpenRout…
A family of constrained-decoding models from @scaledown_team is live on OpenRouter, each one purpose-built for a single task:
@scaledown_team 的受限解码模型系列已上线 OpenRouter，每个模型专为单一任务而设计：
• Summarize: turns long text, images, and PDFs into short, consistent summaries for context compaction and transcript digests • Extract: describe the fields you want in plain English and get clean JSON back, with confidence scores and source spans • Classify-1: set your own labels and get a calibrated probability for each, via our Decisions API
• 摘要：将长文本、图像和 PDF 转换为简短一致的摘要，用于上下文压缩和转录稿精简 • 提取：用自然英语描述所需字段，返回干净的 JSON，附带置信度分数和来源跨度 • 分类-1：自定义标签，通过我们的 Decisions API 获取每个标签的校准概率
20% off for launch: $0.04/M input tokens, output free.
首发优惠 8 折：输入 token 价格为 $0.04/M，输出免费。
http://openrouter.ai/provider/scaledown
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力