Qwen3.5-35B-A3B - Qwen Cloud

Qwen3.5-Open-Source

Copied!

Try AIAdd to Compare

ReasoningText GenerationVisual Understanding

Overview

ReasoningText GenerationVisual Understanding

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.

Input

TextImageVideo

Output

Text

Features

Prefix Completion

Function Calling

Cache

Structured Outputs

Batches

Web Search

Pricing

Input
$0.25Per 1M tokens
Output
$2Per 1M tokens

Context

Standard

Context

262.14K

Max Input

260.09K

Max Output

65.53K

Thinking

Context

262.14K

Max Input

258.04K

Max Output

65.53K

Max Reasoning

81.92K

Rate Limits

RPMRequests Per Minute
600
TPMTokens Per Minute
5M

Built-in Tools

web_searchResponses API

web_extractorResponses API

code_interpreterResponses API

t2i_searchResponses API

i2i_searchResponses API

API Reference

Get API Key

Copied!

123456789101112131415161718

import os
import dashscope
dashscope.base_http_api_url = "https://[workspace-id].ap-southeast-1.maas.aliyuncs.com/api/v1"

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"text": "What is depicted in the image?"}]
    }]
response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3.5-35b-a3b',
    messages=messages
)
print(response.output.choices[0].message.content[0]["text"])

import os
import dashscope
dashscope.base_http_api_url = "https://[workspace-id].ap-southeast-1.maas.aliyuncs.com/api/v1"

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"text": "What is depicted in the image?"}]
    }]
response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3.5-35b-a3b',
    messages=messages
)
print(response.output.choices[0].message.content[0]["text"])