Skip to content

Qwen4-Max Becomes Available on Vercel AI Gateway

Qwen · XRelayed· @Alibaba_Qwen·· 7 hours ago

14.5K views · 181 likes · 5 reposts (at collection)

Original
Who
Vercel
What
made available Qwen4-Max on AI Gateway
Quote
Qwen4-Max from @Alibaba_Qwen is now available on AI Gateway.

What happened

Qwen says to build with Qwen4-Max on Vercel's AI Gateway, quoting Vercel's announcement that the model is now available there. Vercel describes it as built for 3D modeling and game development, with pricing 25% lower than Qwen3.8-Max and up to 384K output tokens.

Read next

See the full storyAlibaba Releases Qwen4-Max with Native Vision and Live API Access
Article

🙌 Build with Qwen4-Max on Vercel's AI Gateway! @vercel_dev

Quoted postVercel Developers@vercel_dev

Qwen4-Max from @Alibaba_Qwen is now available on AI Gateway.

  • Built for 3D modeling and game dev
  • 25% lower pricing than Qwen3.8-Max
  • Up to 384K output tokens

𝚊𝚕𝚒𝚋𝚊𝚋𝚊/𝚚𝚠𝚎𝚗𝟺-𝚖𝚊𝚡

vercel.com/changelog/qwen4-ma…

View the quoted post on X

The story so far

Alibaba released Qwen4-Max, a 2.4T-parameter MoE model with native vision and a 1M-token context window, with its API now live on QwenCloud and the Qianwen AI platform. The model is also available on Qwen Studio, QwenWork, Qoder, Qwen APP, Alibaba’s Token Plan, OpenRouter, OpenCode Go, Vercel AI Gateway, and Novita Labs. Vercel says its version supports up to 384K output tokens and is priced 25% below Qwen3.8-Max. Qwen lists QwenCloud API pricing at $1.5 per million input tokens, $4.5 per million output tokens, and $0.075 per million tokens for implicit caching, which it says is 70% lower than Qwen3.8-Max. QbitAI reports Qianwen AI platform cache-hit pricing as low as 0.5 yuan per million tokens. Alibaba says open weights for smaller Qwen4 models will be released over time. In Qwen’s evaluations, Qwen4-Max scored 52.69 on Work360, about 10% above Qwen3.8-Max, while cutting token use by about 24% at Xhigh and 35% at High and lowering average task cost from $4.43 to $1.67. On Terminal-Bench 4.0, Qwen says token use fell by about 48% and 49% at those settings, while QbitAI reports a score of 48.5 versus 38.9 for Qwen3.8-Max, with average task cost down 58%.

How the story developed · 3

View full event
  1. 11/16 22:39 (UTC+8)
    Alibaba Releases Qwen4-Max with 2.4T Parameters and 1M-Token ContextQbitAI
  2. 11/16 16:44 (UTC+8)

    Qwen4-Max Becomes Available on Vercel AI Gateway This report

  3. 11/16 10:38 (UTC+8)
    Qwen4-Max launches with native vision and a 1M-token context windowQwen · X