托管的 PaddleOCR-VL-1.6 API

5 分•作者: TimurKramar•2 个月前
我们处理大量文档,而 PaddleOCR-VL-1.6 是我们使用过的最好的开源模型之一。 我们想将其作为 API 使用,但找不到任何托管服务。因此,我们开始自己托管,但为了充分利用 GPU 资源,我们决定也让其他人使用。 如果我们定价得当(我希望如此),它应该是最便宜的 OCR 服务,每页仅需 0.001 美元。如果您觉得它有用,请告诉我们:https://openparser.dev
查看原文
We do a lot of document processing, and PaddleOCR-VL-1.6 is one of the best open models we&#x27;ve used.<p>We wanted to use it as an api, but couldn&#x27;t find anyone hosting it. so we started hosting it ourselves, but to get full utilization on the GPUs, we decided to let others use it as well.<p>If we did the pricing math right (which I hope we did), it should be the cheapest OCR there is, at just $0.001&#x2F;page. Let us know if you find it useful https:&#x2F;&#x2F;openparser.dev