Qwen3.8-Max - QwenCloud

Model Marketplace

Qwen3.8-Max<br>qwen3.8-max

Copied!

Try AIAPI RequestAdd to Compare<br>ReasoningVisual UnderstandingText Generation

Overview<br>ReasoningVisual UnderstandingText Generation

2.4-trillion-parameter MoE flagship delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized tasks across legal, financial, design, and other professional domains, producing production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. In long-horizon tasks, plans autonomously, iterates through closed feedback loops, and continuously evolves.<br>Input<br>ImageTextVideo

Output<br>Text

Features<br>Prefix Completion<br>Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling<br>Use function calling to connect large language models with external tools and systems.View docs

Cache<br>Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs<br>Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Web Search<br>Enable web search so the model can answer with real-time retrieved data.View docs

feature.funeTuning

Pricing<br>ModelsBuilt-in Tools<br>Input$2Per 1M tokens

Output$6Per 1M tokens

Input(Implicit Cache)$0.25Per 1M tokens

Explicit Cache Creation$2.5Per 1M tokens

Explicit Cache Read$0.17Per 1M tokens

Rate Limits & Context<br>Max Input991.80K

Max Output131.07K

RPMRequests Per Minute15K

TPMTokens Per Minute2M

Max Input (Thinking)983.61K

Max Output (Thinking)131.07K

Context1M

Built-in Tools<br>code_interpreterResponses API

web_extractorResponses API

web_searchResponses API

t2i_searchResponses API

i2i_searchResponses API

API Reference<br>Get API Key<br>DashScopeOpenAI<br>PythonJavacURL

Python

Copied!<br>123456789101112131415161718<br>import os<br>import dashscope<br>dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"

messages = [<br>"role": "user",<br>"content": [<br>{"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},<br>{"text": "What is depicted in the image?"}]<br>}]<br>response = dashscope.MultiModalConversation.call(<br>api_key=os.getenv('DASHSCOPE_API_KEY'),<br>model='qwen3.8-max',<br>messages=messages<br>print(response.output.choices[0].message.content[0]["text"])

Highlights