Alibaba Cloud

Qwen3.5-Plus

Qwen3.5 native vision-language Plus model with a hybrid linear-attention + sparse MoE architecture for strong reasoning and multimodal efficiency

Category Text Model ID qwen3.5-plus

Context Length128K tokens

Model TypeNative vision-language Plus (linear attention + sparse MoE)

Core CapabilitiesText generation, deep reasoning, visual understanding

Pricing & Specs

💰 Pricing

Input¥0.8 / M tokens

Output¥4.8 / M tokens

Cache Write¥1 / M tokens

Cache Hit¥0.8 / M tokens

⚙️ Specs

Context Length128K tokens

Model TypeNative vision-language Plus (linear attention + sparse MoE)

Core CapabilitiesText generation, deep reasoning, visual understanding

Input ModalitiesText, image

Output ModalitiesText

Model VersionFunctionally equivalent to snapshot qwen3.5-plus-2026-02-15

Model ExperienceFunction calling, structured output, web search, prefix continuation, cache, batch inference, model tuning

I/O Pricing (<=128K)Input ¥0.0008 / 1K tokens; Output ¥0.0048 / 1K tokens

Explicit Cache PricingCreate ¥0.001 / 1K tokens; Hit ¥0.00008 / 1K tokens

Tool Call Pricingweb_search ¥4 / 1K calls; t2i_search ¥24 / 1K calls

API Examples

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": "You are a multimodal assistant."},
        {"role": "user", "content": "Summarize this requirement and provide an implementation plan."}
    ],
    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": "You are a multimodal assistant."},
      {"role": "user", "content": "Summarize this requirement and provide an implementation plan."}
    ],
    "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": "Summarize this requirement and provide an implementation plan.",
    "temperature": 0.6
  }'

Developer Assist

# Configure ~/.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

← Back to Models