Skip to main content

qwen4-max (Latest Model)

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)
  • Singapore
  • Germany (Frankfurt)
  • US (Virginia)
  • Japan (Tokyo)
  • Hong Kong (China)
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

Supported

fine-tuning

Not supported

model deployment

Not supported

Model rate limits and context

Parameter

Token

Parameter

Token

Maximum input length

991,808

Maximum output length

131,072

Maximum input length (thinking mode)

983,616

Maximum output length (thinking mode)

262,144

Context length

1,000,000

Maximum chain-of-thought length

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

  • China (Beijing)
  • US (Virginia)
  • Singapore
  • Germany (Frankfurt)
  • Japan (Tokyo)
  • Hong Kong (China)
Model IDModeInput 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)
Non-Thinking and Thinking modes0<Token≤1MCNY 10CNY 301 million tokens
qwen4-max — Batch price (per million tokens)
APIInputOutput
Batch FileCNY 5CNY 15
Batch Chat (limited-time 50% off)Original price: CNY 10Original price: CNY 30
For prices and free quotas, see Model pricing.

Rate limits

  • China (Beijing)
  • Singapore
  • US (Virginia)
  • Germany (Frankfurt)
  • Japan (Tokyo)
  • Hong Kong (China)

Bailian platform monthly consumption:

Tier 1 (current) ≤¥100,000

Tier 2 ¥100,000~¥1,000,000

Tier 3 >¥1,000,000

Supported models

TPM rate limit tiers

qwen4-max

5,000,000

10,000,000

20,000,000

For rate limits and AutoTPM tiers, see Rate limits.

API access

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.