阿里云
Qwen3.5-Plus
Qwen3.5 原生视觉语言 Plus 模型，融合线性注意力与稀疏 MoE 架构，兼顾深度推理、多模态理解与推理效率
上下文长度128K tokens
模型类型原生视觉语言 Plus（线性注意力 + 稀疏 MoE）
核心能力文本生成、深度思考、视觉理解
定价与规格
💰 定价
输入¥0.8 / M tokens
输出¥4.8 / M tokens
缓存创建¥1 / M tokens
缓存命中¥0.8 / M tokens
⚙️ 规格
上下文长度128K tokens
模型类型原生视觉语言 Plus（线性注意力 + 稀疏 MoE）
核心能力文本生成、深度思考、视觉理解
输入模态文本、图像
输出模态文本
模型版本功能等同快照 qwen3.5-plus-2026-02-15
模型体验Function Calling、结构化输出、联网搜索、前缀续写、Cache 缓存、批量推理、模型调优
输入/输出计费（<=128K）输入 ¥0.0008/千 tokens；输出 ¥0.0048/千 tokens
显式缓存计费创建 ¥0.001/千 tokens；命中 ¥0.00008/千 tokens
工具调用价格web_search ¥4/千次；t2i_search ¥24/千次
API 调用示例
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
api_key="your-api-key",
base_url="https://api.xairouter.com/v1"
)
response = client.chat.completions.create(
model="qwen3.5-plus",
messages=[
{"role": "system", "content": "你是一个多模态助手。"},
{"role": "user", "content": "总结一下这份需求，并给出实现步骤。"}
],
temperature=0.6
)
print(response.choices[0].message.content)cURL (OpenAI API)
# OpenAI Chat Completions API
curl https://api.xairouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "qwen3.5-plus",
"messages": [
{"role": "system", "content": "你是一个多模态助手。"},
{"role": "user", "content": "总结一下这份需求，并给出实现步骤。"}
],
"temperature": 0.6
}'
# OpenAI Responses API
curl https://api.xairouter.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "qwen3.5-plus",
"input": "总结一下这份需求，并给出实现步骤。",
"temperature": 0.6
}'开发者辅助
# 配置 ~/.codex/config.toml
cat > ~/.codex/config.toml << 'EOF'
model_provider = "xai"
model = "qwen3.5-plus"
approval_policy = "never"
sandbox_mode = "danger-full-access"
network_access = true
preferred_auth_method = "apikey"
[shell_environment_policy]
inherit = "all"
ignore_default_excludes = false
[model_providers.xai]
name = "xai"
base_url = "https://api.xairouter.com"
wire_api = "responses"
requires_openai_auth = false
env_key = "OPENAI_API_KEY"
web_search = true
EOF
export OPENAI_API_KEY="sk-Xvs..."
codex