Qwen3.5-Plus
qwen/qwen3.5-plus
The Qwen3.5 native vision-language series Plus models are based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across various task evaluations, the 3.5 series demonstrates exceptional performance comparable to current top-tier frontier models, marking a leap forward in both plain text and multimodal capabilities compared to the 3 series.
价格
| 输入 | $0/百万 tokens |
| 输出 | $0/百万 tokens |
阶梯计费
| 每次请求输入长度 | 输入 | 输出价格 |
|---|---|---|
| 0 < tokens <= 256,000 | $0.4 | $2.4 |
| 256,000 < tokens <= 1,000,000 | $1.2 | $7.2 |
使用以下代码示例来集成我们的API：
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.highwayapi.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="qwen/qwen3.5-plus",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=64000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)信息
提供商
量化
-
支持的功能
上下文长度
1000000
最大输出
64000
serverless
支持
函数调用
支持
结构化输出
支持
推理
支持
Input Capabilities
text, image, video
Output Capabilities
text