Primary use stated or inferred cautiously from official documentation.
Qwen4-Max-Preview
Preview of Qwen4-Max, available since November 11 through Token Plan. It combines text, image and video understanding with reasoning and text generation.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | qwen4-max-preview |
|---|---|
| Model type | Text and reasoning · Code · Multimodal |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 11 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Video |
| Exit | Text |
| Context window | 1M tokens |
| maximum output | 393,216 tokens for reasoning and answer |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Alibaba Cloud Token Plan |
Explore coding, interface design and visual document analysis. Tools and JSON formats are supported. Compatible interfaces include Chat Completions, Responses and Messages.
The preview ends on November 25, 2026 at 24:00 UTC+8 and the model will then be retired. The output limit is shared by reasoning and the final answer. The default effort is xhigh.
What it can do
Orientation
Explore coding, interface design and visual document analysis. Tools and JSON formats are supported. Compatible interfaces include Chat Completions, Responses and Messages.
Context
1M tokens · 393,216 tokens for reasoning and answer
Tools and integration
Not published
Access
Alibaba Cloud Token Plan
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Access is offered exclusively through Token Plan. The documentation publishes no pay-as-you-go rate for this model. Check the credits and terms of the relevant subscription.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
The launch documentation describes preview features and limits. A public results table specific to this identifier has not been verified.
i We have not found published benchmarks for this model.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
qwen4-max-preview
Preview through November 25 via Token Plan.