Getting Started

Build with Qwen Cloud

AI models for text, vision, speech, and image & video generation.

Developer quickstart

Make your first API request in minutes. Seamlessly integrate with any OpenAI SDK or client.

Get started →

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
)
completion = client.chat.completions.create(
  model="qwen3.6-plus",
  messages=[{"role": "user", "content": "Summarize the benefits of solar energy in three bullet points."}]
)
print(completion.choices[0].message.content)

Models

Start with qwen3.6-plus for complex reasoning and coding. Choose qwen3.5-flash for speed and cost efficiency. All models share the same API — just change the model parameter. Browse all models →

qwen3.6-plus

Complex reasoning, coding, agents — 1M context

qwen3.5-flash

Fast and cost-effective — 1M context

qwen3-max

Complex reasoning and coding

Start building

Read and generate text

Prompt models to generate text, summarize, translate, or write code

Understand images and video

Analyze images, extract text from screenshots, or reproduce designs from mockups

Generate images

Create and edit images from text prompts with Wan and Flux models

Generate videos

Animate images into video clips or generate videos from text descriptions

Synthesize speech

Convert text to natural speech with built-in voices, voice cloning, or voice design

Build agentic applications

Connect models to external tools and APIs with function calling

Tackle complex tasks with thinking

Use reasoning models to solve multi-step math, logic, and coding problems

Get structured data from models

Extract JSON that conforms to a schema from any model response

Pricing | API Reference | Free Quota