跳转到主要内容

Qwen4 Max

AlibabaQwenProprietary

描述

Qwen4-Max is Alibaba's next-generation flagship multimodal model in the Qwen family, generally available on 2026-11-16 (model id qwen4-max). It is a sparse mixture-of-experts model with 2.4 trillion backbone parameters, 71 billion active parameters per token, and an additional 328 billion N-gram Embedding parameters, with native text, image, and video understanding, a 1,000,000-token context window, and thinking enabled by default (reasoning_effort levels low, high, and xhigh; default high; thinking_budget default 131,072; maximum thinking plus final answer 262,144 tokens; maximum input 983,616 tokens in thinking mode and 991,808 in non-thinking mode). It supports function calling, web search, structured outputs, explicit and implicit cache, and the OpenAI Chat Completions and Responses APIs and the Anthropic Messages API. QwenCloud Singapore list pricing is $1.50 per million input tokens and $4.50 per million output tokens, with cache write $1.875 (5-minute TTL) or $3 (1-hour TTL) and cache read $0.075 per million tokens. Beijing and Global regions list $1.413 input and $4.24 output, with cache write $1.767 (5-minute TTL) or $2.827 (1-hour TTL) and cache read $0.071 per million tokens. This card is the generally available model; the earlier Token Plan-only preview is cataloged separately as qwen4-max-preview. The official Qwen team launch post says smaller models in the Qwen4 family are coming to open source; no open weights for Qwen4-Max were published at catalog time.

发布日期
2026-11-16
参数规模
2.4T
上下文长度
1.0M
支持模态
image, text, video

能力雷达图

43
general
100
coding
50
reasoning
68
science估算
50
agents
50
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
智能体能力模型榜40
58.0
LS
通用能力榜18
65.0
AA
多模态榜121
35.0
LS
科学能力17
66.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Job Bench68.5%自报
Agents' Last Exam46.7%自报
Program Bench31.5%自报

Biology

BioMysteryBench85.0%自报

Code

WebDev Arena1750.00 / 2000自报
DeepSWE 1.175.7%自报

Healthcare

HealthBench Professional60.0%自报

Reasoning

APEX-Agents72.1%自报
Humanity's Last Exam51.7%自报
Terminal-Bench 4.048.5%自报

Vision

Chartography54.2%自报

AA 评测指数

(Artificial Analysis)
Strategy And Ops
56.9
Finance And Accounting
54.1
Economics
51.3
Engineering(Artificial Analysis)
50.1
Legal
49.6
Healthcare And Medical
48.2
Intelligence Index(Artificial Analysis)
42.9

LLM Stats 分类评分

(LLM Stats (zeroeval))
Frontend Development
100
Code
100
Reasoning
100
General
100
Science
80
Biology
80
Productivity
70
Healthcare
60
Agents
60
Math
50
Multimodal
50
Tool Calling
50
Vision
50

定价

输入价格$1.5 / 1M tokens
输出价格$4.5 / 1M tokens
混合价格(3:1)$2.25 / 1M tokens
缓存读取价格$0.07125 / 1M tokens
缓存写入价格$1.78125 / 1M tokens

速度

Tokens/秒51.9
首Token延迟3.33s
首回答延迟41.90s

供应商价格排行

供应商价格排行

13 个供应商

最便宜: NanoGPT最贵: CrossModel
供应商输入输出
1NanoGPT最便宜
$1.413
$4.24
2Novita AI
$1.413
$4.24
3OpenRouter
$1.425
$4.275
4Alibaba主要
$1.5
$4.5
5QwenCloud
$1.5
$4.5
6OpenCode Go
$1.5
$4.5
7Kilo Gateway
$1.5
$4.5
8DevPass (LLM Gateway)
$1.5
$4.5
9EmpirioLabs AI
$1.5
$4.5
10Ofox
$1.5
$4.5
11Charm Hyper
$1.5
$4.5
12Eden AI
$1.5
$4.5
13CrossModel
$1.6
$4.8

比较该模型在不同 API 供应商之间的定价。

外部链接