Skip to content

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).

ModelQwen4-Max
Status hereUnder review — waiting on license. Not in any pool
ReleasedNovember 16, 2026 (hosted API only)
Open weightsNot published. No date or license announced
AA Intelligence Index43 (v5.0.1) — Qwen3.8 Max scores 34 on the same version
Architecture2.4T-parameter MoE, 71B active (Alibaba’s figures)
Context window1M tokens
InputText, image and video
Per-token price elsewhere$1.50 in / $4.50 out per 1M — reference only

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.

Terminal window
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.

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.

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.