Qwen Max API

Try this model

Qwen Max: powerful AI, excels in stability, competes globally.

Modalities: Text, ImageText
In / Out price: $1.6/$6.4per 1M
Context window: 32K tokens
Released: Sep 9, 2025

Qwen Max overview

Qwen Max by Alibaba Cloud

Alibaba's Qwen Max is a powerful multimodal AI with OpenAI-compatible API, notable for instruction-following stability.

Qwen Max specs

Model ID: alibaba/qwen-max
Developer: Alibaba Cloud
Context window: 32,000 tokens
Max output: 8,192 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Basic Information

Developer/Creator: Alibaba Cloud
Release Date: January 25, 2025
Model Type: Multimodal Large Language Model (LLM)

Overview:

Qwen Max is a large-scale Mixture-of-Experts (MoE) language model developed by Alibaba Cloud. It excels in language understanding, generation, and task performance across a variety of modalities.

Key Features:

Mixture-of-Experts (MoE) Architecture: Uses 64 specialized "expert" networks, activating only relevant ones per task for efficient processing.
Extensive Multilingual Support: Supports 29 languages, including Chinese, English, and Arabic.
Long-Context Optimization: Supports 262K context windows with 8K generation.
High Stability: Demonstrates high stability in maintaining prompt instructions, with no erroneous replies during extensive testing.

Intended Use:

Qwen Max is designed for a broad range of applications, including:

AI agents and workflows requiring stable instruction following.

Language Support:

Supports 29 languages, including Chinese, English, and Arabic.

Architecture:

64 specialized "expert" networks
Transformer-based architecture.

Use cases

enterprise virtual assistants and customer service automation across multiple languages
multilingual content creation and translation for global audiences
code generation, debugging, and software development assistance
educational content creation, tutoring, and accessibility tools
data analytics and research automation in finance, healthcare, and marketing
creative content generation including video, audio scripting, and multimedia storytelling
business intelligence and knowledge management with advanced NLP

Capabilities

Function calling
Streaming
Structured outputs
Web search

Qwen Max API pricing

Qwen Max pricing in US dollars
Usage	Price	Unit
Input	$1.6	1M tokens
Output	$6.4	1M tokens
Cached input	$0.32	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Qwen Max vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Qwen Max	$1.6	$6.4
Qwen3.8 Omni Flash	$0.15	$0.47
Qwen3.8-Flash	$0.16	$0.47
Qwen 3.8 27B	$0.4761	$3.39
Qwen3.8 Max Prime	$4.23	$12.7

How to use the Qwen Max API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "alibaba/qwen-max",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "alibaba/qwen-max",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "alibaba/qwen-max",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Qwen Max FAQ

What is the context window of Qwen Max?

Qwen Max has a 32,000 tokens context window and can return up to 8,192 tokens.

What inputs and outputs does Qwen Max support?

Qwen Max takes text as input and returns text.

What is the model ID for Qwen Max?

Use alibaba/qwen-max as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Qwen Max released?

Qwen Max became available on September 9, 2025.

How much does Qwen Max cost?

Qwen Max costs $1.6 input and $6.4 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Qwen Max support streaming?

Yes, Qwen Max can stream responses as they are generated.

Who created Qwen Max?

Qwen Max was built by Alibaba Cloud.

Start building with Qwen Max

Get API key

Qwen Max API

alibaba/qwen-max

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "alibaba/qwen-max",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "alibaba/qwen-max",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "alibaba/qwen-max",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Qwen Max API

Qwen Max overview

Qwen Max by Alibaba Cloud

Qwen Max specs

Basic Information

Overview:

Key Features:

Intended Use:

Language Support:

Architecture:

Use cases

Capabilities

Qwen Max API pricing

Qwen Max vs other models: token prices

How to use the Qwen Max API

Build with your agent

1Get your API key

2Make your first request

Related articles

Qwen Max FAQ

Start building with Qwen Max

Qwen Max API

Build with your agent

1Get your API key

2Make your first request

Qwen Max API

Qwen Max overview

Qwen Max by Alibaba Cloud

Qwen Max specs

Basic Information

Overview:

Key Features:

Intended Use:

Language Support:

Architecture:

Use cases

Capabilities

Qwen Max API pricing

Qwen Max vs other models: token prices

How to use the Qwen Max API

Build with your agent

1Get your API key

2Make your first request

Models similar to Qwen Max

Qwen3.8 Max Prime

Qwen3.8 Omni Flash

Qwen3.8-Flash

Gemini Flash Latest

Medium 3.5

GPT-5.4 Mini

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Qwen Max FAQ

Start building with Qwen Max