Qwen4 Max is a large language model made by Qwen, added to the catalog on 16 Nov 2026. It has a context window of 1,000,000 tokens and costs $1.425 per 1M input tokens and $4.275 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: reviewing long documents, summarising extended text and answering questions about supplied images or video.
Price checked ยท source: OpenRouter
What Qwen4 Max is
Qwen4 Max is a multimodal model in Alibaba's Qwen4 series. It accepts text, image, and video input and produces text. Reasoning is enabled by default. Its context window holds up to 1,000,000 tokens, and its maximum output is 131,072 tokens. This gives it room to process extensive supplied context and return long text responses when a task calls for them. Its listed input and output modalities describe what it accepts and produces: text, images, and video as input, and text as output.
The model supports tools, structured outputs, and response_format. These capabilities are relevant to tasks that involve tool use or require responses in a specified format. The available facts do not identify particular tools, supported schemas, or video constraints, so those details depend on the use environment. Reasoning is enabled by default, and the model can be prompted with text alone or with text and visual material.
With its large context window, Qwen4 Max suits work involving long documents or several pieces of supplied text in a single prompt. Its image and video inputs suit questions or requests based on visual material, while its text output supports drafting, summarisation, and question answering. Structured output support also fits tasks that call for formatted text. These are possible applications of the stated capabilities, not guarantees of a particular result.
Key features
- Accepts text, image, and video input and produces text
- Has a context window of 1,000,000 tokens
- Supports a maximum output of 131,072 tokens
- Supports reasoning, tools, structured outputs, and response_format
Typical uses
- Reviewing long documents
- Summarising extended text
- Answering questions about supplied images or video
- Generating structured text responses
Qwen4 Max pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.425 |
| Output, per 1M tokens | $4.275 |
| Cached input read, per 1M tokens | $0.0713 |
| Cache write, per 1M tokens | $1.781 |
No price change since it was added on 16 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0020 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.039 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.051 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.220 |
Qwen4 Max specifications
| Model id | qwen/qwen4-max |
|---|---|
| Version | qwen4-max-20261115 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 16 Nov 2026 |
| Input types | text, image, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Qwen4 Max yet.
Compare Qwen4 Max
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.