OpenClaw LaunchOpenClaw Launch
← Home

Guide

OpenClaw + Qwen 3.7: Use Qwen 3.7 and Qwen 3.7 Max with OpenClaw

Alibaba's Qwen 3.7 generation is live on OpenClaw. Pick Qwen 3.7 for the best cost-to-quality balance, or Qwen 3.7 Max for frontier reasoning and long-context agentic work — both route through OpenRouter with your own key (BYOK).

What Is Qwen 3.7?

Qwen is Alibaba's open model family, and Qwen 3.7 is the newest generation — a step up from Qwen 3.5 and 3.6 on reasoning, coding, and tool use. It ships in two tiers: Qwen 3.7 for fast, low-cost everyday work and Qwen 3.7 Max, the flagship tuned for complex reasoning and long-context agentic tasks.

Versus the 3.5/3.6 line, Qwen 3.7 brings better instruction-following, sharper coding, more reliable tool-calling for agent loops, and a longer usable context window. For an OpenClaw bot that searches, codes, and chains tools, that translates to fewer dropped steps and cleaner multi-turn behavior.

Qwen 3.7 vs Qwen 3.7 Max

ModelBest forStrengths
Qwen 3.7High-volume chat, agent tool loops, day-to-day codingFast, cheapest in the lineup, strong general quality
Qwen 3.7 MaxHard reasoning, multi-file refactors, long-document analysisFrontier reasoning, best instruction-following, long context

A simple rule: run Qwen 3.7 as the default for Telegram and Discord bots where speed and cost matter, and reach for Qwen 3.7 Max when a task needs deeper reasoning. You can switch between them at runtime — no redeploy.

How to Deploy Qwen 3.7 with OpenClaw Launch

Qwen 3.7 is brand new, so you run it through OpenRouter with your own key (BYOK) rather than the curated one-click models. It still deploys in about 30 seconds:

  1. Go to openclawlaunch.com and open the configurator.
  2. Add your OpenRouter key in the BYOK settings.
  3. In the model dropdown, choose Custom model and enter qwen/qwen3.7-plus for the cheaper tier or qwen/qwen3.7-max for frontier quality.
  4. Pick your chat platform (Telegram, Discord, WhatsApp, WeChat, or browser gateway) and click Deploy. Your Qwen 3.7 agent is live in about 30 seconds.
Tip: Switch between Qwen 3.7 and Qwen 3.7 Max any time from the dashboard or with the /model chat command — no redeploy needed. A common pattern is the cheaper tier for everyday chat and Max for hard coding sessions.

Self-Hosted Configuration

If you run OpenClaw on your own server, configure OpenRouter as a provider in your openclaw.json and point the default agent at Qwen 3.7 or Qwen 3.7 Max:

{
  "models": {
    "providers": {
      "openrouter": {
        "apiKey": "sk-or-..."
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "openrouter/qwen/qwen3.7-plus"
      }
    }
  }
}

Swap qwen3.7-plus for qwen3.7-max to route to the Max variant instead. Grab an OpenRouter key at openrouter.ai/keys.

Which Qwen 3.7 Model Should You Pick?

  • Pick Qwen 3.7 for high-volume chat, agent tool loops, and general coding. It's the best cost-per-quality option in the Qwen lineup and a great default for messaging bots.
  • Pick Qwen 3.7 Max for frontier-class reasoning — complex refactors, architecture discussions, and long-document analysis where 3.7 occasionally slips on nuance.
  • Run both — one instance per role, or swap at runtime with /model.

BYOK with Qwen 3.7

If you already have an OpenRouter account or a direct Alibaba/DashScope key, bring it to OpenClaw Launch via BYOK. In the configurator, select BYOK and paste your OpenRouter key — all requests route through your key and your own billing.

What's Next?

Deploy with Qwen 3.7

Get an AI agent powered by Qwen 3.7 or Qwen 3.7 Max running in 30 seconds.

Deploy Now