Qwen3.5 Plus API: pricing, base URL and quick setup

Specifications and pricing

Prices synced with platform billing (USD per 1M tokens).

Quick setup

curl https://a2agent.me/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer sk-your-a2agent-key" \
  -d '{
    "model": "qwen3.5-plus",
    "messages": [{"role": "user", "content": "Reply with OK"}]
  }'

Using it from a coding client

Workable in a client that sends images alongside code, but check the Flash tier first. Qwen3.8 Flash reads images too, on the same 1M window, at under a third of this input rate.

• Run it in Cline
• Run it in Roo Code

How it compares within its family

Every Qwen model in this catalogue runs a 1M window, so context never decides between them. Price and tag do. Qwen3.5 Plus lists at $0.50 per million input tokens and $3.00 output, and carries the vision tag. The Flash tier undercuts it across the board: Qwen3.6 Flash at $0.20 and $1.20, Qwen3.7 Flash at $0.20 and $0.80, Qwen3.8 Flash at $0.15 and $0.47. Notice the shape of that. Qwen3.5 Plus is older than all three Flash releases and costs more than every one of them, and the $3.00 output rate is the number that bites on long answers. Pick it when you have already validated a prompt suite against it, not because Plus sounds stronger than Flash.

Other models on this platform

• Qwen3.6 Flash1M
• Qwen3.7 Flash1M
• Qwen3.7 Plus1M
• Qwen3.7 MAX1M
• Qwen3.8 Flash1M

Questions