Qwen3 Max

by Alibaba

Qwen3 Max is Alibaba's flagship proprietary large language model, built with a mixture-of-experts architecture and optimized for reasoning, instruction following, and long-context processing. It delivers strong performance across math, coding, logic, and science tasks while maintaining accuracy on complex instructions in both Chinese and English. The model supports over 100 languages, performs well on retrieval-augmented generation, and provides tool-calling capabilities for agentic systems. It is built for developers working on demanding reasoning problems that also need reliable instruction following and multilingual coverage. With a 262K context window and a non-reasoning design that favors direct answers, Qwen3 Max is well suited to applications that process long documents, orchestrate agents, and run production RAG where visible reasoning steps are not required.

Key info

Input
Output
Features
Context window
256K
Max output
256K
Input price
$1.20 /1M
Output price
$6.00 /1M
  • US residency available
  • Zero data retention via Enterprise
  • No training by default
  • GDPR DPA available

Available routes

Qwen3 Max runs on 2 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
USEnterpriseNo$1.20$6.00
USEnterpriseNo$2.11$8.45

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Qwen3 Max has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Limited debug logs
Third-party access
None disclosed
GDPR DPA
No DPA
Transfer mechanism
unknown

Novita β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
SCCs

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#155 of 534 LLMs
TierEfficient
Output speed60 tok/s
First token1.85s
Intelligence Index24.0
Math Index80.7
Reasoning & knowledge
MMLU-Pro
84%
GPQA Diamond
76%
Humanity's Last Exam
11%
Long-context reasoning
47%
Coding
LiveCodeBench
77%
SciCode
38%
Agentic & tool use
Terminal-Bench Hard
20%
τ²-Bench Telecom
74%
Math & instruction following
AIME 2025
81%
IFBench
44%

Get started

Call Qwen3 Max through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β€” Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent β€” Claude Code, Cursor, Codex, and more β€” 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.click/v3/compat",
});
const completion = await client.chat.completions.create({
model: "deepinfra/Qwen/Qwen3-Max",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Qwen3 Max with…

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

Other models from Alibaba

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Qwen3 Max by Alibaba β€” pricing, benchmarks | Opper AI