Qwen4-Max API — status, pricing & access
Qwen4-Max (also written “Qwen 4 Max”) is Alibaba’s flagship model, released on November 16, 2026: a 2.4T-parameter Mixture-of-Experts with text, image and video input and a 1M-token context, scoring 43 on the Artificial Analysis Intelligence Index (v5.0.1).
Quick facts
Section titled “Quick facts”| Model | Qwen4-Max |
| Status here | Under review — waiting on license. Not in any pool |
| Released | November 16, 2026 (hosted API only) |
| Open weights | Not published. No date or license announced |
| AA Intelligence Index | 43 (v5.0.1) — Qwen3.8 Max scores 34 on the same version |
| Architecture | 2.4T-parameter MoE, 71B active (Alibaba’s figures) |
| Context window | 1M tokens |
| Input | Text, image and video |
| Per-token price elsewhere | $1.50 in / $4.50 out per 1M — reference only |
What you can use today
Section titled “What you can use today”The predecessor is live. Qwen3.8 Max is served in the Flagship Pool next to Kimi K3.1 Pro on unlimited, flat-rate time-block subscriptions from $199/mo — no per-token billing, no token caps during your reserved hours. Live availability is on /pools.
curl https://api.cheapestinference.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "qwen3.8-max", "messages": [{"role": "user", "content": "Hello"}]}'The model id qwen4-max is not available on this API. If it joins a pool it will be announced in the changelog the day it goes live.
Why it is waiting
Section titled “Why it is waiting”Every model in our pools belongs to a generation whose weights are published under a license that permits commercial serving. Qwen3.8 Max joined the Flagship Pool on August 14, 2026, the day after its open-weight release. For Qwen4 there are no weights and no license to read yet, so there is no date from us either.
Common questions
Section titled “Common questions”Is there an unlimited Qwen4-Max API? Not yet. Qwen4-Max is under review at CheapestInference and waiting on its open-weights license. The Flagship Pool serves Qwen3.8 Max and Kimi K3.1 Pro with uncapped usage from $199/month for a daily 8-hour block.
Is Qwen4-Max open source? No. It is a closed, hosted model. As of November 17, 2026 no Qwen4 weights or license are published; Alibaba has said smaller Qwen4 models will be open-sourced later, without a date.
When will Qwen4 open weights be released? Alibaba has not given a date, sizes or a license.
How much does Qwen4-Max cost per token? Alibaba lists $1.50 per 1M input tokens and $4.50 per 1M output tokens, 25% below Qwen3.8 Max ($2 / $6).
Where can I read the full analysis? Qwen4-Max: specs, benchmarks, pricing, open-weights status & API options — index position, vendor benchmarks and the open-weights timeline.