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

Using it from a coding client

The 1M window lets a reasoning session hold a whole repository in Claude Code or Codex CLI without chunking. Keep an eye on the $5.10 output rate with agents that talk a lot.

• Run it in Claude Code
• Run it in Codex CLI

How it compares within its family

Qwen ships two reasoning-tagged models here, 3.7 MAX and 3.8 MAX, and both run the 1M window shared across the family. Qwen3.7 MAX lists at $1.70 per million input tokens and $5.10 output. Qwen3.8 MAX lists at $2.00 and $6.00, about eighteen percent more on each side. Nothing else in the catalogue separates them, so the choice is the newer release against the cheaper one. Everything else in the Qwen line is tagged for vision rather than reasoning: the Plus tier at $0.50 to $1.20 on input, the Flash tier at $0.15 to $0.20. If the task is long-chain reasoning rather than reading, the MAX pair is where to look, and 3.7 MAX is the cheaper way in.

Other models on this platform

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

Questions