Qwen4-Max

by Alibaba

Released 82 days after Qwen3.8 Flash · Announcement · All Alibaba releases

Qwen4-Max is the first model in Alibaba's Qwen4 family and the new top of the Qwen line, following Qwen3.8-Max. It combines step-by-step reasoning with native image and video understanding, and is built for coding, professional work, design and scientific exploration, using tools and feedback to turn a complex goal into a deliverable that can be reviewed. The model reads up to one million tokens of context and can write up to 262,144 tokens of thinking and answer together, or 131,072 with thinking switched off. Reasoning effort can be set per request or turned off entirely, and the model supports function calling, parallel tool calls and strict JSON schema output. Alibaba's launch material shows it building a game in Unreal Engine, turning production-line layouts into 3D models, producing financial research with linked spreadsheets and editable presentations, and running legal due diligence with cross-checked, traceable citations. It suits long-running agent tasks where a single session has to plan, iterate and keep a large body of material in view. Alibaba offers it as a hosted model and has not published its weights.

Call Qwen4-Max on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Key info

Input
Output
Features
Context window
1M
Max output
262K
Input price
$1.50 /1M$0.07 cache read
Output price
$4.50 /1M
Released
Web search
  • Zero data retention with abuse monitoring
  • No training by default

Available routes

Qwen4-Max runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutputCache read
MultiNo$1.50$4.50$0.07

Live routes and prices as JSON: api.opper.ai/v3/models?q=alibaba%3Aglobal%2Fqwen4-max

Uptime and availability

Qwen4-Max runs on a single route through the Opper gateway today, so its availability is that provider's availability.

100%route uptime, last 30 days
Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Qwen4-Max has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Alibaba Cloud — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs.

Zero data retention
With abuse monitoring, window not stated.
Training
No training on customer data.
Logging
Abuse monitoring
Abuse monitoring
On by default, holds flagged content
Caching
Content cached for replay
Transfer mechanism
SCCs

Best for

Where Qwen4-Max ranks among the models on Opper with a score for each use case.

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Intelligence Index42.9
Coding
FrontierCode 2.0
27%
Terminal-Bench 4.0
49%
Agentic & knowledge work
AutomationBench
73%
GDPval
65%
GDP.pdf
26%
Briefcase (Elo)1686
Science & reasoning
Terminal-Bench Science
23%
CritPt (hard)
43%
HLE Diamond
45%
Knowledge
Omniscience27.7
By domain
Finance & accounting
54.1
Legal
49.6
Engineering
50.1
Economics
51.3
Strategy & operations
56.9

Get started

Call Qwen4-Max through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen4-Max is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "alibaba:global/qwen4-max",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Use Qwen4-Max in your apps

Pick your tool, then choose Qwen4-Max to see how to run it through Opper.

Use Qwen4-Max with tools

The tools Qwen4-Max can use through Opper. Pick one to see how to set it up.

Compare Qwen4-Max with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Alibaba

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation