{"id":12986,"date":"2024-06-13T09:18:11","date_gmt":"2024-06-13T01:18:11","guid":{"rendered":"https:\/\/www.1ai.net\/?p=12986"},"modified":"2024-06-13T09:18:11","modified_gmt":"2024-06-13T01:18:11","slug":"%e5%ad%97%e8%8a%82%e8%b7%b3%e5%8a%a8%e7%81%ab%e5%b1%b1%e6%96%b9%e8%88%9f%e5%a4%a7%e6%a8%a1%e5%9e%8b%e5%b9%b3%e5%8f%b0%e5%90%91%e4%b8%aa%e4%ba%ba%e5%bc%80%e5%8f%91%e8%80%85%e5%bc%80%e6%94%be%ef%bc%8c","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/12986.html","title":{"rendered":"ByteDance's Volcano Ark large model platform is open to individual developers, providing 500,000 tokens of free inference quota"},"content":{"rendered":"

ByteDance<\/a>Volcano Engine officially announced that its one-stopLarge Model<\/a>Service PlatformVolcano Ark<\/a>Will officially provide services to individual developers<\/span>Individual developers can experience and apply dozens of large models including the Doubao large model family and other platform functions.<\/p>\n

All models of Doubao on Volcano Ark will be available to individual users\u00a0500,000 tokens of free inference quota<\/span>In addition, the 4K and 32K versions of Doubao Universal Model Pro and Doubao Universal Model Lite also provide users with a traffic quota of 10,000 RPM (requests per minute) and 800,000 TPM (tokens per minute).<\/p>\n

After the free quota is used up, taking the Doubao Universal Model Pro-32k version as an example, the model inference input price is\u00a00.0008 yuan\/1,000 tokens<\/span>. IT Home attached pricing table is as follows:<\/p>\n

\"2abd90a7-c485-4d79-97d8-04a01b7ce640\"<\/p>\n

Individual developers need to complete the Volcano Engine official websitePersonal real-name authentication<\/span>. After completing the real-name authentication, you can enter the Volcano Ark console from the Volcano Ark\/Doubao Large Model official website.<\/p>\n

\"e6dffa4f-9aa1-442e-a92c-96ef0d382cde\"<\/p>\n

Next, you can view the various large models currently provided by Volcano Ark in the Model Square. Individual developers can view the model name, introduction, provider, whether it can be experienced, and application scenarios through the model card.<\/p>\n

\"2c0ebf9e-209a-4157-b528-639cd0b2690f\"<\/p>\n

After selecting a model, developers can also use the console page operation provided by Volcano Ark or call the API to experience and compare models. The specific methods are as follows:<\/p>\n

\"aab60b0a-6b75-45df-8dbc-34b824b4ad80\"<\/p>\n

\"aa88ffe1-dd3c-462a-98be-4a32744a50ec\"<\/p>\n

\"61bc5c96-fe7c-424d-81af-6588a9c96ad0\"<\/p>\n

After completing the experience, individual developers can call the corresponding model according to their actual needs and complete tasks such as reasoning:<\/p>\n

\"ee0806fb-3a49-4b73-96a2-a9f3295e5d88\"<\/p>\n

In addition, individual developers can also upload data sets and fine-tune the model through SFT (Supervised FineTuning) and Continue Pretraining.<\/p>\n

\"8cdb8d27-70fd-45df-9b0c-d591d66327b6\"<\/p>","protected":false},"excerpt":{"rendered":"

Byte jumping volcano engine official announcement, its one-stop big model service platform volcano ark will be formally for individual developers to provide services, individual developers can experience, application, including beanbag big model family, including dozens of big models and other platform features. Volcano Ark on the beanbag whole series of models will provide individual users with 500,000 tokens of free reasoning quota, in addition to the beanbag general model pro and beanbag general model lite 4K and 32K version, also provides users with 10,000 RPM (number of requests per minute) and 800,000 TPM (number of tokens per minute) of the flow of the quota. After the free quota is used up, the model inference input price is 0.0008 for the beanbag generic model pro-32k version, for example.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[216,548,3043],"collection":[],"class_list":["post-12986","post","type-post","status-publish","format-standard","hentry","category-news","tag-216","tag-548","tag-3043"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/12986","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=12986"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/12986\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=12986"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=12986"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=12986"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=12986"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}