Qwen4-Max

Model release Qwen 官方模型 Source language: Chinese

Alibaba Cloud Model Studio's official changelog shows that Qwen4-Max launched on 2026-11-16. For specifications and regional availability, refer to the official documentation.

Full text

Qwen4-Max is the next-generation flagship multimodal model in the Qwen family, combining text generation, image and video understanding, and deep reasoning. It is designed for coding, office productivity, frontend design, and complex agentic tasks. With support for web search, tool calling, and structured outputs, along with compatibility with the OpenAI and Anthropic APIs, it enables developers to build intelligent applications capable of multimodal understanding and task execution.

Qwen4-Max is the next-generation flagship multimodal model in the Qwen family, combining text generation, image and video understanding, and deep reasoning. It is designed for coding, office productivity, frontend design, and complex agentic tasks. With support for web search, tool calling, and structured outputs, along with compatibility with the OpenAI and Anthropic APIs, it enables developers to build intelligent applications capable of multimodal understanding and task execution.

Model invocation ID (model parameter): qwen4-max

Inference provider

Alibaba Cloud Model Studio

Model capabilities

China (Beijing)

Deployment scope: Chinese mainland

Capability

Support

Capability

Support

Input modalities

Text, image, video

Output modality

Text

Streaming

Supported

deep thinking

Supported

parallel tool calling

Supported

web search

Supported

prefix completion

Supported

Function Calling

Supported

Thinking summary and encryption

Supported

OpenAI Chat Completions, Responses, Anthropic Messages, DashScope

Supported

Structured output (JSON Object, JSON Schema)

Supported

Explicit cache, implicit cache

Supported

Batch inference

Not supported

fine-tuning

Not supported

model deployment

Not supported

Singapore

Scope: International

Capability

Support

Capability

Support

Input modalities

Text, image, video

Output modality

Text

Streaming

Supported

deep thinking

Supported

parallel tool calling

Supported

web search

Supported

prefix completion

Supported

Function Calling

Supported

Thinking summary and encryption

Supported

OpenAI Chat Completions, Responses, Anthropic Messages, DashScope

Supported

Structured output (JSON Object, JSON Schema)

Supported

Explicit cache, implicit cache

Supported

Batch inference

Not supported

fine-tuning

Not supported

model deployment

Not supported

Germany (Frankfurt)

Scope: Global

Capability

Support

Capability

Support

Input modalities

Text, image, video

Output modality

Text

Streaming

Supported

deep thinking

Supported

parallel tool calling

Supported

web search

Supported

prefix completion

Supported

Function Calling

Supported

Thinking summary and encryption

Supported

OpenAI Chat Completions, Responses, Anthropic Messages, DashScope

Supported

Structured output (JSON Object, JSON Schema)

Supported

Explicit cache, implicit cache

Supported

Batch inference

Not supported

fine-tuning

Not supported

model deployment

Not supported

US (Virginia)

Scope: Global

Capability

Support

Capability

Support

Input modalities

Text, image, video

Output modality

Text

Streaming

Supported

deep thinking

Supported

parallel tool calling

Supported

web search

Supported

prefix completion

Supported

Function Calling

Supported

Thinking summary and encryption

Supported

OpenAI Chat Completions, Responses, Anthropic Messages, DashScope

Supported

Structured output (JSON Object, JSON Schema)

Supported

Explicit cache, implicit cache

Supported

Batch inference

Not supported

fine-tuning

Not supported

model deployment

Not supported

Japan (Tokyo)

Scope: Global

Capability

Support

Capability

Support

Input modalities

Text, image, video

Output modality

Text

Streaming

Supported

deep thinking

Supported

parallel tool calling

Supported

web search

Supported

prefix completion

Supported

Function Calling

Supported

Thinking summary and encryption

Supported

OpenAI Chat Completions, Responses, Anthropic Messages, DashScope

Supported

Structured output (JSON Object, JSON Schema)

Supported

Explicit cache, implicit cache

Supported

Batch inference

Not supported

fine-tuning

Not supported

model deployment

Not supported

Hong Kong (China)

Scope: Global

Capability

Support

Capability

Support

Input modalities

Text, image, video

Output modality

Text

Streaming

Supported

deep thinking

Supported

parallel tool calling

Supported

web search

Supported

prefix completion

Supported

Function Calling

Supported

Thinking summary and encryption

Supported

OpenAI Chat Completions, Responses, Anthropic Messages, DashScope

Supported

Structured output (JSON Object, JSON Schema)

Supported

Explicit cache, implicit cache

Supported

Batch inference

Not supported

fine-tuning

Not supported

model deployment

Not supported

Context limits

Parameter

Token

Parameter

Token

Context length

1,000,000

Maximum output length (non-thinking)

131,072

Maximum input length (non-thinking)

991,808

Maximum input length (thinking)

983,616

Maximum combined tokens for thinking and the final answer

262,144

Default parameters

Parameter

Default

temperature

1.0 in thinking mode; 0.7 in non-thinking mode.

top_p

0.95 in thinking mode; 0.8 in non-thinking mode.

top_k

20

repetition_penalty

1.0

presence_penalty

0.0 (Thinking); 1.5 (Non-thinking)

logprobs

false

enable_thinking

true

preserve_thinking

true

reasoning_effort

high

thinking_budget

131072

max_completion_tokens

262144 (Thinking); 131072 (Non-thinking)

When reasoning_effort and thinking_budget are omitted, the defaults are reasoning_effort=high and thinking_budget=131072.

Thinking effort

ProtocolParameterSupported valuesDefaultMapping

OpenAI Chat Completions / DashScopereasoning_effortlow, high, xhighhighminimal → low; medium → high; max → xhigh

OpenAI Responsesreasoning.effortlow, high, xhighhighminimal → low; medium → high; max → xhigh

Anthropic Messagesoutput_config.effortlow, high, xhighhighmedium → high; max → xhigh

Model pricing

Singapore

Model IDDeployment scopeModeInput tokens per requestInput price (per 1 million tokens)Output price (per 1 million tokens)

Chain of thought + answer

Free quota(Note)

Valid for 90 days from the date of Model Studio activation, model release, or application approval, whichever is later

qwen4-max

Cache price (per million tokens)

International

Non-Thinking and Thinking modes

0<Token≤1M

$1.5

$4.5

1 million tokens

China (Beijing)

Model IDModeInput tokens per requestInput price (per 1 million tokens)Output price (per 1 million tokens)

Chain of thought + answer

qwen4-max

Cache price (per million tokens)

Non-Thinking and Thinking modes

0<Token≤1M

$1.413

$4.24

Hong Kong (China)

Model IDDeployment scopeModeInput tokens per requestInput price (per 1 million tokens)Output price (per 1 million tokens)

Chain of thought + answer

qwen4-max

Cache price (per million tokens)

Global

Non-Thinking and Thinking modes

0<Token≤1M

$1.413

$4.24

Germany (Frankfurt)

Model IDDeployment scopeModeInput tokens per requestInput price (per 1 million tokens)Output price (per 1 million tokens)

Chain of thought + answer

qwen4-max

Cache price (per million tokens)

Global

Non-Thinking and Thinking modes

0<Token≤1M

$1.413

$4.24

US (Virginia)

Model IDDeployment scopeModeInput tokens per requestInput price (per 1 million tokens)Output price (per 1 million tokens)

Chain of thought + answer

qwen4-max

Cache price (per million tokens)

Global

Non-Thinking and Thinking modes

0<Token≤1M

$1.413

$4.24

Japan (Tokyo)

Model IDDeployment scopeModeInput tokens per requestInput price (per 1 million tokens)Output price (per 1 million tokens)

Chain of thought + answer

qwen4-max

Cache price (per million tokens)

Global

Non-Thinking and Thinking modes

0<Token≤1M

$1.413

$4.24

For prices and free quotas, see Model pricing.

Rate limits

Singapore

Bailian platform monthly consumption:

Tier 1 (current) ≤$8,000

Tier 2 $8,000~$140,000

Tier 3 >$140,000

Supported models

TPM rate limit tiers

qwen4-max

5,000,000

10,000,000

20,000,000

China (Beijing)

Bailian platform monthly consumption:

Tier 1 (current) ≤$8,000

Tier 2 $8,000~$140,000

Tier 3 >$140,000

Supported models

TPM rate limit tiers

qwen4-max

5,000,000

10,000,000

20,000,000

US (Virginia)

ModelService Deployment ScopeRate limit conditions (triggered when any value is exceeded)

The following are per-minute rate limit conditions. The service may impose limits based on RPS (RPM/60) and TPS (TPM/60).

Calls per minute (RPM)Tokens consumed per minute (TPM)

Includes input and output tokens

qwen4-max

Global

30,000

5,000,000

Germany (Frankfurt)

ModelService Deployment ScopeRate limiting conditions (triggered when any value is exceeded)

The following are per-minute rate limiting conditions. The service may also limit by RPS (RPM/60) and TPS (TPM/60)

Calls per minute (RPM)Tokens consumed per minute (TPM)

Includes input and Output tokens

qwen4-max

Global

30,000

5,000,000

Hong Kong (China)

ModelService Deployment ScopeRate limiting conditions (triggered when any value is exceeded)

The following are per-minute rate limiting conditions. The service may limit by RPS (RPM/60) and TPS (TPM/60).

Calls per minute (RPM)Tokens consumed per minute (TPM)

Includes input and output Tokens

qwen4-max

Global

30,000

5,000,000

Japan (Tokyo)

ModelService Deployment ScopeRate limit conditions (triggered when any value is exceeded)

The following are per-minute rate limit conditions. The service may limit by RPS (RPM/60) and TPS (TPM/60).

Calls per minute (RPM)Tokens consumed per minute (TPM)

Includes input and output Tokens

qwen4-max

Global

30,000

5,000,000

For rate limits and AutoTPM tiers, see Rate limits.

API access

OpenAI Chat Completions

OpenAI Responses

Anthropic Messages

DashScope

Model capabilities

CoT Summary

Prompt Cache

Usage

Explicit caching

Reuse common input prefixes such as system prompts, tool descriptions, and reference documents to reduce repeated input costs. Supported by OpenAI Chat Completions, Responses, and Anthropic Messages, with TTLs of 5m and 1h. See Explicit caching.

Chain-of-thought summary and encryption

Returns a reasoning summary for display and encrypted reasoning for use in subsequent turns. Pass historical encrypted content back unchanged in multi-turn conversations. For configuration, streaming responses, and complete examples, see Chain-of-thought summary and encryption.

Sources

← Back to the daily brief