Qwen4-Max
Alibaba’s Qwen 4 flagship (Nov 16, 2026). OpenAI-compatible API on QwenCloud; also on OpenRouter as qwen/qwen4-max.
Model idqwen4-max
Price$1.50 in, $4.50 out per 1M tokens
Checked16 November 2026
No published training cutoff
At least43events since its release on 16 November 2026
1 historic, 15 major. 3 days of news.
Alibaba (Qwen) doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.
How to call it
4 ways to use Qwen4-Max, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| QwenCloud (Alibaba Cloud Model Studio) | qwen4-max |
qwencloud.com | |
| OpenRouter | qwen/qwen4-max |
openrouter.ai | |
| Vercel AI Gateway | qwen4-max |
||
| Web app | chat.qwen.ai |
Pricing
| Input | $1.50 per 1M tokens |
|---|---|
| Output | $4.50 per 1M tokens |
| Cache read | $0.075 per 1M tokens |
As published: “per 1M tokens (USD), QwenCloud / Alibaba Cloud International; implicit-cache input 0.075; regional prices differ”.
Source: qwencloud.com, checked 16 November 2026.
Specs
- Input
- Text, images, video and PDF
- Output
- Text
- Context window
- 991,808 tokens
- Max output
- 131,072 tokens
- Open weights
- No
- Licence
- Proprietary
- Training cutoff
- Not published
- Released
- 16 November 2026
- Status
- Current
- Type
- Reasoning model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Native vision in a new MoE flagship
Built on a new mixture-of-experts architecture with native vision (image, video, PDF input) and a ~1M-token context; reported 2.4T total / 71B active parameters (not in Alibaba’s X post).
Lower cost per task than Qwen3.8-Max
Alibaba: up to ~50% fewer tokens and over 60% lower average cost per task than Qwen3.8-Max in internal evaluations; Artificial Analysis measured $3.27 per Intelligence Index task.
Notes
Hosted only: no open weights for the flagship (smaller Qwen4 models promised as open). Artificial Analysis Intelligence Index 43 (Nov 16), below Kimi K3.1 Pro; verbose (127M output tokens on the index). Thinking input limit 983,616 tokens; thinking + answer up to 262,144. No batch or fine-tuning. Preview id qwen4-max-preview (Token Plan, from Nov 11). Knowledge cutoff not published.