Primary use stated or inferred cautiously from official documentation.
Qwen4-Max
Alibaba multimodal model introduced on November 16, with a MoE architecture of 2.4 trillion total parameters and 71 billion active per token. It understands text, images and video and generates text for coding, visual analysis and agent tasks.
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 |
|---|---|
| Model type | Text and reasoning · Code · Multimodal |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 16 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Video |
| Exit | Text |
| Context window | 1,000,000 tokens; maximum input of 991,808 without reasoning or 983,616 with it |
| maximum output | 131,072 tokens without reasoning; 262,144 for reasoning and answer combined |
| Reasoning | Optional; enabled by default at high effort. Supports low, high and xhigh. |
| Published tools | Function calling · Web search · Parallel tools |
| Structured Outings | JSON Object and JSON Schema |
| Batch processing | Unavailable |
| Prompt cache | Implicit and explicit caching; TTL of 5 minutes or 1 hour |
| Fine-tuning | Unavailable |
| Verified platforms | Alibaba Cloud Model Studio |
Work with long documents, develop interfaces and coordinate tools in multistep tasks. The API supports streaming, parallel calls and JSON formats through Chat Completions, Responses, Anthropic Messages and DashScope.
One million tokens is the context window, not the output limit. Reasoning uses part of the 262,144 generation tokens. Batch inference, fine-tuning and self-hosting are unavailable. Access, quotas and regional data handling depend on the account and contracted scope. Future smaller Qwen4 models are not part of this release.
What it can do
Orientation
Work with long documents, develop interfaces and coordinate tools in multistep tasks. The API supports streaming, parallel calls and JSON formats through Chat Completions, Responses, Anthropic Messages and DashScope.
Context
1,000,000 tokens; maximum input of 991,808 without reasoning or 983,616 with it · 131,072 tokens without reasoning; 262,144 for reasoning and answer combined
Tools and integration
Function calling · Web search · Parallel tools
Access
Alibaba Cloud Model Studio · API and Token Plan
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | USD 1.50 / 1M tokens · Singapore | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | USD 4.50 / 1M tokens · Singapore | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Singapore international pricing: USD 1.50 input and USD 4.50 output per million tokens, including reasoning tokens. Cache reads cost USD 0.075; creation costs USD 1.875 with a 5-minute TTL or USD 3 with a 1-hour TTL. Global scope lists USD 1.413 input and USD 4.24 output. Do not mix regions or apply batch discounts to this model.
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 release publication shows 1,750 points and sixth place on Code Arena WebDev at xHigh effort, and 52.69 on Work360, a proprietary professional-task evaluation. These are published results, not tests reproduced by Inferama. The Arena ranking is a snapshot; Work360 and other tool-based tests depend on the environment and do not guarantee overall quality.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Code Arena WebDev | 1,750 | Arena score · xHigh | View source ↗ |
| Work360 | 52.69 | Overall score · proprietary evaluation | View source ↗ |
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
Stable pay-as-you-go version; distinct from qwen4-max-preview, released on November 11.