Qwen3.7 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": "qwen3.7-plus",
    "messages": [{"role": "user", "content": "Reply with OK"}]
  }'

Using it from a coding client

Use it when image input matters and a Flash release has already fallen short on the task. Otherwise the money is better spent on MAX for reasoning, or saved on Flash.

• Run it in Cline
• Run it in Cursor

How it compares within its family

Qwen3.7 Plus lists at $1.20 per million input tokens and $4.80 output, with the vision tag and the 1M window every Qwen model here carries. It sits between the Flash releases, which run $0.15 to $0.20 on input, and the MAX tier at $1.70 to $2.00. Set against Qwen3.7 MAX from the same generation, the input is roughly thirty percent cheaper and the output slightly lower, and the tag differs: Plus is vision, MAX is reasoning. Set against Qwen3.5 Plus, the older release in the same tier, it costs more than twice as much on both sides. So Plus is not the value tier inside Qwen. It is the multimodal option one step below MAX.

Other models on this platform

• Qwen3.5 Plus1M
• Qwen3.6 Flash1M
• Qwen3.7 Flash1M
• Qwen3.7 MAX1M
• Qwen3.8 Flash1M

Questions