{"id":55491,"date":"2026-08-05T11:20:40","date_gmt":"2026-08-05T03:20:40","guid":{"rendered":"https:\/\/www.1ai.net\/?p=55491"},"modified":"2026-08-05T11:20:40","modified_gmt":"2026-08-05T03:20:40","slug":"deepseek-v4-flash-%e5%8d%95%e5%91%a8%e8%b0%83%e7%94%a8%e9%87%8f%e8%be%be-7-22-%e4%b8%87%e4%ba%bf-token%ef%bc%8c%e7%99%bb%e9%a1%b6-openrouter-%e6%a6%9c%e9%a6%96","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/55491.html","title":{"rendered":"DeepSeek V4 Flash calls 7.22 trillion token, top OpenRouter"},"content":{"rendered":"

AUGUST 5TH MESSAGE, THE LARGEST AI LARGE MODEL IN THE WORLD Aggregation Platform<\/a> OpenRouter<\/a> LAST WEEK, D@eepSeek<\/a> V4 Flash is at the top of the platform with a 7.22 trillion token weekly call, with a statistical cycle from 27 July to 2 August, an increase of 13% over the previous week\u3002<\/p>\n

\"1b3bbe41j00tja19800iwd000u00191m\"<\/p>\n

According to OpenRouter data, the two versions of DeepSeek V4 Flash processed a total of 67 billion tokens, with a total of 329 trillion tokens per week and a total of 61.3 trillion tokens per week\u3002<\/p>\n

Among the top 10, the Chinese models DeepSeek, MiMo-V2.5, Hy3 and GLM-5.2 occupied many seats and most of them were free or near free. OpenAI ranked 8th in GPT-5.6 Luna, the only OpenAI model in the top 10, with an increase of 465%, but still less than one third of DeepSeek V4 Flash\u3002<\/p>\n

OpenCode disclosed separately that DeepSeek V4 Flash's single-day processing capacity on its platform had reached 8 trillion token, of which 5 trillion came from free trial-level consumption and 3 trillion was used by developers on a fee basis\u3002<\/p>","protected":false},"excerpt":{"rendered":"

On August 5th, in the latest weekly newspaper published yesterday by OpenRouter, the largest AI large model API polymer platform in the world, DeepSeek V4 Flash ranked 7.22 trillion token in weekly calls at the top of the platform with a statistical cycle of 27 July to 2 August, an increase of 131 TP3T over the previous week. According to OpenRouter data, the two versions of DeepSeek V4 Flash processed a total of 67 billion tokens, with a total of 329 trillion tokens per week and a total of 61.3 trillion tokens per week. Top ten, DeepSeek, MiMo-<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[8743,8282,8511],"collection":[],"class_list":["post-55491","post","type-post","status-publish","format-standard","hentry","category-news","tag-eepseek","tag-openrouter","tag-8511"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/55491","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=55491"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/55491\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=55491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=55491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=55491"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=55491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}