{"id":26899,"date":"2025-01-15T21:02:07","date_gmt":"2025-01-15T13:02:07","guid":{"rendered":"https:\/\/www.1ai.net\/?p=26899"},"modified":"2025-01-15T21:02:07","modified_gmt":"2025-01-15T13:02:07","slug":"kimi-%e5%a4%9a%e6%a8%a1%e6%80%81%e5%9b%be%e7%89%87%e7%90%86%e8%a7%a3%e6%a8%a1%e5%9e%8b-api-%e5%8f%91%e5%b8%83%ef%bc%8c1m-tokens-%e5%ae%9a%e4%bb%b7-12-%e5%85%83%e8%b5%b7","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/26899.html","title":{"rendered":"Kimi Multimodal Image Understanding Model API Released, 1M tokens priced from $12"},"content":{"rendered":"

January 15, 2011 - Dark Side of the Moon today released the\u00a0Kimi<\/a> Multimodality<\/a>Image Understanding Model API<\/a>The new multimodal picture comprehension model\u00a0moonshot-v1-vision-preview<\/strong>(hereinafter referred to as \"Vision model\") completes the multimodal capabilities of the moonshot-v1 model family.<\/p>\n

Description of model capabilities<\/strong><\/p>\n

Image Recognition<\/p>\n

\"cb180bdcj00sq4s2m008id000u000nhp\"<\/p>\n

Vision models are equipped with image recognition capabilities, recognizing complex details and nuances in images, be it food or animals, and being able to distinguish between similar but not identical objects.<\/p>\n

In the example below, 16 similar images of blueberry muffins and chihuahuas that are harder for the human eye to distinguish have been officially pieced together, with the Vision model recognizing and labeling the image types in order.Whether it's a blueberry muffin or a Chihuahua, the model can accurately differentiate and identify the<\/strong>.<\/p>\n

Text recognition and comprehension<\/p>\n

Vision models have advanced image recognition capabilities that are more accurate than ordinary document scanning and OCR recognition software in OCR text recognition and image understanding scenarios.Handwritten scribbles such as receipts \/ courier bills can be accurately recognized.<\/strong>.<\/p>\n

\"022554a2j00sq4s3v005jd000u000iop\"<\/p>\n

Taking this bar chart of \"A student's final exam results\" as an example, the official asked the model to extract and analyze the exam results and analyze the bar chart from the perspective of aesthetic style. The Vision model is also able to accurately identify the score values corresponding to each subject name in the bar chart and do a comparison of the scores, and at the same time, it can identify the style formatting and color of the bar chart.<\/p>\n

\"abca3503j00sq4s420061d000u000l4p\"<\/p>\n

model billing<\/p>\n

Vision models are billed on a per-volume basis<\/strong>The price of the model call varies according to the model selected, with the following distinctions:<\/p>\n\n\n\n\n\n\n
Model<\/td>\nBilling Unit<\/td>\nprice<\/td>\n<\/tr>\n
moonshot-v1-8k-vision-preview<\/span><\/td>\n1M tokens<\/td>\n\u00a512.00<\/td>\n<\/tr>\n
moonshot-v1-32k-vision-preview<\/span><\/td>\n1M tokens<\/td>\n\u00a524.00<\/td>\n<\/tr>\n
moonshot-v1-128k-vision-preview<\/span><\/td>\n1M tokens<\/td>\n\u00a560.00<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n
<\/div>\n
Description of model constraints<\/strong><\/div>\n
<\/div>\n
Features supported by the Vision visual model include:<\/div>\n<\/div>\n
    \n
  • \n
    many rounds of dialogue<\/span><\/div>\n<\/li>\n
  • \n
    streaming output<\/span><\/div>\n<\/li>\n
  • \n
    Tool Call<\/span><\/div>\n<\/li>\n
  • \n
    JSON Mode<\/span><\/div>\n<\/li>\n
  • \n
    Partial Mode<\/span><\/div>\n<\/li>\n<\/ul>\n
    \n
    The following features are not supported or partially supported at this time:<\/span><\/div>\n<\/div>\n
      \n
    • \n
      Internet search: not supported<\/span><\/div>\n<\/li>\n
    • \n
      Context Caching:<\/span>Creating a Context Cache with image content is not supported.<\/span>The Vision model can be called with a Cache that has already been created.<\/span><\/div>\n<\/li>\n
    • \n
      URL-formatted images: not supported, currently only base64-encoded image content is supported<\/span><\/div>\n<\/li>\n<\/ul>\n
      \n
      Other Platform Updates<\/span><\/div>\n<\/div>\n
        \n
      • \n
        Support for organizational project management functions<\/span><\/div>\n<\/li>\n
      • \n
        Support for one business entity to authenticate multiple accounts<\/span><\/div>\n<\/li>\n
      • \n
        Add File file resource management function: intuitively manage and view file resources.<\/span><\/div>\n<\/li>\n
      • \n
        Optimize mouse hover copy for resource management list<\/span><\/div>\n<\/li>\n
      • \n
        Context Caching has been released to full users.<\/span><\/div>\n<\/li>\n
      • \n
        Cache renewals are no longer charged for creation<\/span><\/div>\n<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"

        January 15, 2011 - The Dark Side of the Moon today released the Kimi Multimodal Image Understanding Model API, a new multimodal image understanding model, moonshot-v1-vision-preview (hereinafter referred to as the \"Vision model\"), which completes the moonshot-v1 model series' multimodal capabilities. model series. Model Capability Description Image Recognition The Vision model has the ability to recognize complex details and nuances in an image, whether it is a food or an animal, and to distinguish between objects that are similar but not identical. In the example below, 16 similar images of a blueberry muffin and a Chihuahua, which are difficult for the human eye to distinguish, have been assembled and recognized by the Vision model and labeled with the image classes in order.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1033,1814,592],"collection":[],"class_list":["post-26899","post","type-post","status-publish","format-standard","hentry","category-news","tag-api","tag-kimi","tag-592"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/26899","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=26899"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/26899\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=26899"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=26899"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=26899"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=26899"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}