Skip to main content
Text Generation

qwen3.6-max-preview

The Max model, the largest and most capable variant in the Qwen3.6 series, is now available in a preview version. At present, only its plain-text capabilities are open for experimentation. Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.

Inference Service Provider

The inference service provider for qwen3.6-max-preview is Alibaba Cloud Model Studio.

Model Capabilities

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

245760

Max Output Length

65536

Context Window

262144

Max Input Length (Thinking Mode)

229376

Max Output Length (Thinking Mode)

65536

Max Chain-of-Thought Length

131072

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
  • China (Beijing)
  • Singapore

Input<=128k

Billing ItemPrice (USD)Unit

Input

1.238

Per 1M tokens

Output

7.426

Per 1M tokens

Explicit Cache Creation

1.547

Per 1M tokens

Explicit Cache Read

0.1238

Per 1M tokens

Billing ItemPrice (USD)Unit

Input

2.063

Per 1M tokens

Output

12.377

Per 1M tokens

Explicit Cache Creation

2.579

Per 1M tokens

Explicit Cache Read

0.206

Per 1M tokens

Rate Limits

  • China (Beijing)
  • Singapore
ParameterValue

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000

Snapshot Versions

qwen3.6-max-preview

The Max model, the largest and most capable variant in the Qwen3.6 series, is now available in a preview version. At present, only its plain-text capabilities are open for experimentation. Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.

Inference Service Provider

The inference service provider for qwen3.6-max-preview is Alibaba Cloud Model Studio.

Model Capabilities

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

245760

Max Output Length

65536

Context Window

262144

Max Input Length (Thinking Mode)

229376

Max Output Length (Thinking Mode)

65536

Max Chain-of-Thought Length

131072

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
  • China (Beijing)
  • Singapore

Input<=128k

Billing ItemPrice (USD)Unit

Input

1.238

Per 1M tokens

Output

7.426

Per 1M tokens

Explicit Cache Creation

1.547

Per 1M tokens

Explicit Cache Read

0.1238

Per 1M tokens

Billing ItemPrice (USD)Unit

Input

2.063

Per 1M tokens

Output

12.377

Per 1M tokens

Explicit Cache Creation

2.579

Per 1M tokens

Explicit Cache Read

0.206

Per 1M tokens

Rate Limits

  • China (Beijing)
  • Singapore
ParameterValue

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000

Token Plan
Model Playground
  • Music generation
Statistics and Monitoring