Skip to content

Alibaba · Chat

Qwen4 Max

Alibaba 🇨🇳ChatQwen familyOne of its sources says the weights aren't publicly available.
From Empiriolabs's listing:
Next-generation Qwen flagship for coding, frontend design, office work, and complex agents, with image and video understanding across a 1M-token context.
llminfo IQ
144.9
Maker's price
$2.25 blended / 1M
Max context
1M
Listings
45

Evidence and sources

International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).

Model architecture, as its sources state it llminfo IQ 144.9, ranked among chat models. From 40 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 124.3, 95% interval 112–137. From 3 benchmark families across 2 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (61.7). Cheaper per task than its benchmark results predict. From 10 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 11 Nov 2026Maker HQ: CN (source)
All rankings: #3 in Lemmy discussions this week #6 in Wikipedia pageviews this week #8 in YouTube mentions this week #23 on OpenRouter today #26 on OpenRouter this week #36 in Bluesky discussions this week #60 on OpenRouter this month #110 on NanoGPT recentlyAll rankings: #3 in Lemmy discussions this week #6 in Wikipedia pageviews this week #8 in YouTube mentions this week #23 on OpenRouter today #26 on OpenRouter this week #36 in Bluesky discussions this week #60 on OpenRouter this month #110 on NanoGPT recentlySources: LMArena data, DeepInfra data, EmpirioLabs data, Models.dev data, Morpheus Inference Marketplace data, llminfo researchPrimary data from LMArena from DeepInfra: name from EmpirioLabs: primary mode, description from Models.dev: weights availability from Morpheus Inference Marketplace: architecture from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Video
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Alibaba CloudRegions: 🇯🇵🇸🇬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1qwen4-maxSources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen, LiteLLM data992K$1.50cache read $0.075$4.50cache write 5m $1.875cache write 1h $3.00——
 Nous Portalqwen/qwen4-max:free · freeSource: Nous Portal Inference Gateway data1M$0.00$0.00——
 Kenariqwen4-max:free · freeSource: Models.dev data1M$0.00$0.00——
 Together AIQwen/Qwen4-MaxSources: LiteLLM data, Together AI data1M$1.05cache read $0.0525$3.15——
 FlowdotQwen/Qwen4-MaxSource: FlowDot data1M$1.413$4.24——
 NanoGPTqwen/qwen4-maxSources: Models.dev data, NanoGPT1M$1.413cache read $0.071$4.24cache write $1.767——
 DeepInfraQwen/Qwen4-MaxSources: DeepInfra data, Models.dev data1M$1.413cache read $0.071$4.24——
 Novita AIqwen/qwen4-maxSources: Models.dev data, Novita AI data1M$1.413cache read $0.071$4.24cache write $1.767——
 OpenRouterInference by Alibaba Cloudqwen/qwen4-maxSource: OpenRouter data docs1M$1.425cache read $0.0713$4.275cache write $1.7813451,968.5ms
 Llmgatewayqwen4-maxSource: LLMGateway data1M$1.45cache read $0.072$4.25——
Show all 40 listings

Showing 10 of 40: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aihubmix, Chutes, Crossmodel, Eden AI, Empiriolabs, Hyper, Kilo, Llmgateway Providers, Meganova, Netmind, Ofox, Opencode Go, Ppio, Qiniu, Venice, Vercel, Wavespeed, Zenmux.

5 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Arena AgentSource: LMArena data · Nov 2026
ValsSource: Vals AI

Coding

Arena ELO WebdevSource: LMArena data · Nov 2026

Reasoning

Human preference

Other

SuperCLUESource: SuperCLUE data
ValsSource: Vals AI

Data credits: LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence)

Also known as: alibaba/qwen4-max, dashscope/qwen4-max, qwen 4 max, qwen-4-max, qwen/qwen4-max, qwen/qwen4-max:free, qwen/qwen4-max:thinking, qwen4-max-xhigh, qwen4-max:free, scx-ai-gp/qwen4-max, together_ai/qwen/qwen4-max

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works