Using Infux with OpenClaw

What is OpenClaw?

OpenClaw is an open-source personal AI assistant that runs locally on your machine. It connects through popular chat apps like WhatsApp, Telegram, Discord, and more. Because OpenClaw supports OpenAI-compatible APIs, you can point it at Infux to get access to 18 open-weight models with flat-rate pricing and automatic failover.

Prerequisites

• OpenClaw installed (see below)
• An Infux API key (get one at dashboard)

Step 1: Install OpenClaw

Install OpenClaw with the official install script:

curl -fsSL https://openclaw.ai/install.sh | bash

Step 2: Configure Environment Variables

Set these environment variables to point OpenClaw at the Infux gateway. Add them to your shell profile (~/.zshrc or ~/.bashrc):

export OPENAI_API_KEY="sk-infux-your_key_here"
export OPENAI_BASE_URL="https://api.infux.dev/v1"

Then reload: source ~/.zshrc

Recommended Models

Set the model via the OPENAI_MODEL environment variable:

export OPENAI_MODEL="minimax-m2.5"  # highest SWE-bench score

Why Infux + OpenClaw?

• Flat-rate pricing — no per-token billing, starting at $15/mo
• 18 open-weight models — switch models without changing providers
• Auto-failover — every model has 1-3 provider backends, failover in <500ms
• Works everywhere — use the same API key across WhatsApp, Telegram, Discord, and more

Verify It Works

Start OpenClaw and send a test message through your preferred chat app. You should see responses powered by the Infux gateway.

openclaw start

Check the Infux dashboard to confirm requests are flowing through.

Troubleshooting