Qwen4 Max
qwen/qwen4-max
Back to model catalog

Qwen · Model guide

Qwen4 Max

Compare
qwen/qwen4-maxReleased Nov 16, 2026

The first model of the Qwen4 generation: a 2.4T-parameter mixture of experts activating 71B per token, plus a 328B n-gram embedding table, built on a hybrid Gated DeltaNet and Qwen Sparse Attention stack. It takes text, image and video in across a 1M-token context, with adjustable reasoning, function calling, structured output and context caching. Qwen aims it at professional work, coding and long-horizon agents that keep delivering results over many hours.

Modalities
TextImageVideoText
Context
1M
Max output
393K
Price / 1M tokens
$ 1.60in$ 4.80out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorQwen presents Qwen4-Max as an always-on AI teammate for work, creation and exploration, with stronger professional tool use, long-horizon task execution and delivery of finished results.source

Best for
  • Professional and industry work · Qwen reports its gains across finance research, legal due diligence, clinical records and engineering workflows, and a higher score than Qwen3.8-Max on its Work360 industry benchmark.(vendor claim)source

  • Long-horizon agents · Qwen positions the model for 24/7 agents that deliver a usable first version and keep shipping updates, and demonstrates game development in Unreal Engine, Unity and Godot.(vendor claim)source

  • Million-token context · Serves a 1M-token context with up to 991K input, 393K output and a 262K thinking budget.source

Neighbouring models
  • qwen/qwen3.8-maxpredecessor —Choose Qwen3.8 Max to keep an existing integration on the previous generation's behavior.source
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 1.60
Output$ 4.80
Cache read$ 0.080
Cache write$ 2.00
Estimate a request
$ 0.0256
Estimated cost per request
10.0K × $ 1.60
+ 2.0K × $ 4.80
≈ $ 25.60 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
393.2K tokens
Input / output modalities
Text + Image + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Reasoning effort
low · high · xhigh
Thinking budget
1 – 262.1K tokens
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 4.0
    pass_rate·Qwen Team · 2026-11-16setup not fully disclosed

    厂商自测;未披露推理档位与 harness。同图把 Claude Opus 5.5 记作 59.6、Kimi K3.1 Pro 记作 67.2,与各自厂商发布值(66.4 / 65.7)不同,说明是 Qwen 按自己的设置重跑,横向比较时留意。

    48.5%
Coding
  • DeepSWE 1.1
    resolved_rate·Qwen Team · 2026-11-16setup not fully disclosed

    厂商自测;发布页图表未披露推理档位、harness 与采样设置。同图 GPT-6.1 Sol(75.2)、GPT-6 Astra(74.1)、Kimi K3.1 Pro(75.5)与各自厂商发布值一致。

    75.7%
  • ProgramBench
    score·Qwen Team · 2026-11-16setup not fully disclosed

    厂商自测(黑盒软件复刻);来源图表只给出数值,未说明具体 metric,保守记为 score;未披露评测设置。

    31.5%
Knowledge work
  • HealthBench Professional
    score·Qwen Team · 2026-11-16setup not fully disclosed

    厂商自测(临床推理);未披露评测设置。同图把 GPT-6.1 Sol 记作 65.1,与 OpenAI system card 的 64.2(length-adjusted)/ 67.2(未调整)都不一致。

    60%
Multimodal reasoning
  • Chartography (no tools)
    score·Qwen Team · 2026-11-16setup not fully disclosed

    评测说明:Qwen4-Max 在 min_pixels = 4096×32×32 下测得。发布页未明说是否带工具;同图 Claude Opus 5.5 记作 66.3,与其带工具成绩 89.0 相差很大,故归入不带工具的身份。

    54.2%
Reasoning
  • Humanity's Last Exam
    accuracy·Qwen Team · 2026-11-16setup not fully disclosed

    官方未说明是否使用工具,故按目录内不带工具的默认身份记录(与 qwen/qwen3.8-flash 同口径)。

    51.7%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

See all integration guides →

Frequently asked questions

What is Qwen4 Max?
Qwen4 Max is available on CrossModel as qwen/qwen4-max. It has a 1M-token context window and can return up to 393K tokens per request.
How much does Qwen4 Max cost?
Currently $ 1.60 per 1M input tokens and $ 4.80 per 1M output tokens. Cached input is billed at $ 0.080 per 1M.
Does Qwen4 Max support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.