Qwen: Qwen4 Max Preview

alibaba/qwen4-max-preview

Qwen4 Max Preview is the first model of Alibaba's Qwen 4 generation, released on November 11, 2026 as the next-generation flagship multimodal model in the Qwen family. It combines text generation, image and video understanding and deep reasoning (thinking on by default), with tool calling, web search and structured outputs, a 1M-token context and up to 393K output tokens. Alibaba positions it for coding, office work, frontend design and complex agent tasks. It is a time-limited preview that Alibaba plans to retire after November 25, 2026.

Input price
$2.00USD / 1M tokens
Output price
$6.00USD / 1M tokens
Cache read
$0.25USD / 1M tokens
Cache write
$2.50USD / 1M tokens
Context window
N/A
Max output
131.1K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction calling
Input
Text, image
Output
Text

Questions

FAQ

How do I call Alibaba Qwen4 Max Preview through SandBase?

Create a SandBase API key, then send requests with the model ID "alibaba/qwen4-max-preview" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does Alibaba Qwen4 Max Preview cost?

$2 per 1M input tokens and $6 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

Which features does Alibaba Qwen4 Max Preview support?

Alibaba Qwen4 Max Preview supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate Alibaba account?

No. One SandBase API key and balance gives you access to Alibaba Qwen4 Max Preview and the other models in the catalog; you do not need to sign up with Alibaba separately.