{"rewrite":{"id":"r_25e1851d12b0db5532c8a6c8","clusterId":"c_b472f9b08afd42b38160c06f","slug":"orcarouter-adds-qwen4-max-to-its-api-catalog-for-japanese-users","model":"deepseek-v4-1-flash","headline":"OrcaRouter Adds Qwen4 Max to Its API Catalog for Japanese Users","summary":"FlashLabs said OrcaRouter has begun API provision of Qwen4 Max, Alibaba Cloud's latest flagship model from the Qwen team. The model takes text, image, and video input and returns text, with a 1,000,000-token context and up to 65,536 output tokens. Pricing is $1.50 per million input tokens and $4.50 per million output tokens. Artificial Analysis scores it 43 on its Intelligence Index, up from 34 for Qwen3.8 Max.","whyItMatters":"OrcaRouter's pitch is speed of access, and Qwen4 Max reaching Japanese developers through a single OpenAI-compatible gateway days after release is the clearest test of that model so far.","webCardHtml":"\u003cp\u003eThe model is callable as \u0026#34;qwen/qwen4-max\u0026#34; through the OpenAI Chat Completions API, the OpenAI Responses API, and the Anthropic Messages API. FlashLabs describes OrcaRouter as an AI inference gateway developed by the U.S. research organization Continuum AI, which the company provides for the Japanese market.\u003c/p\u003e\u003cp\u003eQwen4 Max is a large Mixture of Experts model with adjustable thinking budget, built-in web search, function calling, and structured JSON output. Prompt caching is supported at $0.075 per million tokens for cache reads and $1.875 for writes. Zero Data Retention is also offered, which routes requests only to providers with no-retention agreements.\u003c/p\u003e","blueskyPost":"Qwen4 Max's 1,000,000-token context and video input are the draw for OrcaRouter, but $4.50 per million output tokens sets the real cost ceiling for Japanese developers building on it.","twitterPost":"OrcaRouter's Qwen4 Max listing prices output at $4.50 per million tokens, a rate that shapes what Japanese developers can afford to build at scale.","threadsPost":"OrcaRouter's Qwen4 Max listing carries a 1,000,000-token context and video input, which reads as capacity. The pricing is what constrains it: $1.50 per million input tokens against $4.50 per million output tokens sets the cost of long, generative workloads.","newsletterBlurb":"FlashLabs has begun API provision of Qwen4 Max through OrcaRouter, the inference gateway it provides for the Japanese market. The Alibaba Cloud model handles text, image, and video input with a 1,000,000-token context and up to 65,536 output tokens. Artificial Analysis puts it at 43 on its Intelligence Index, nine points above Qwen3.8 Max.","attributionJson":"[{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/453/4453881/?rss\",\"title\":\"OrcaRouter Begins API Provision of Alibaba's Latest Flagship Model \\\"Qwen4 Max\\\"\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":5571,"outputTokens":877,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1795332315,"createdAt":"2026-11-22T07:21:05.000Z","publishedAt":"2026-11-22T07:24:12.000Z","updatedAt":"2026-11-22T07:24:12.000Z"},"cluster":{"id":"c_b472f9b08afd42b38160c06f","canonicalTitle":"OrcaRouter、Alibabaの最新フラッグシップモデル「Qwen4 Max」のAPI提供を開始","representativeArticleId":"a_5f29878ef9940e97fb30f1cd","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"Qwen4 Max\"],\"studios\":[\"Alibaba\",\"OrcaRouter\"],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-11-22T06:10:00.000Z","lastSeenAt":"2026-11-22T06:10:00.000Z","updatedAt":"2026-11-22T07:24:13.000Z"},"attribution":[{"source":"ASCII.jp","url":"https://ascii.jp/elem/000/004/453/4453881/?rss","title":"OrcaRouter、Alibabaの最新フラッグシップモデル「Qwen4 Max」のAPI提供を開始"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["Qwen4 Max"],"studios":["Alibaba","OrcaRouter"],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":["OrcaRouter has begun API provision of Qwen4 Max, Alibaba Cloud's latest flagship model from the Qwen team.","Qwen4 Max supports a 1,000,000-token context and up to 65,536 output tokens, with text, image, and video input.","Pricing is $1.50 per million input tokens and $4.50 per million output tokens at provider list price.","Artificial Analysis scores Qwen4 Max at 43 on its Intelligence Index, up from 34 for Qwen3.8 Max.","The model is callable as qwen/qwen4-max through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs."],"pageLinks":{"healthSlugs":["qwen4-max","alibaba","orcarouter"],"storySlugs":[],"entities":[{"slug":"qwen4-max","supported":1,"disputed":0,"contradicted":0,"unverified":2,"overall":"green","story_count":2,"has_dossier":false},{"slug":"alibaba","supported":0,"disputed":0,"contradicted":0,"unverified":5,"overall":"unverified","story_count":12,"has_dossier":true},{"slug":"orcarouter","supported":0,"disputed":0,"contradicted":0,"unverified":3,"overall":"unverified","story_count":7,"has_dossier":true}],"stories":[],"entitiesOk":true,"storiesOk":true}}
