Run OpenClaw with ShuttleAI

Now Available: Run OpenClaw with ShuttleAI

OpenClaw is a powerful open source AI agent. It can browse the web, manage files, run terminal commands, and connect to apps like Discord or WhatsApp.

But managing multiple model providers can get messy.

ShuttleAI solves that by giving you one API for Claude, GPT, and other top models. One subscription. One endpoint. Simple.

Why Use ShuttleAI with OpenClaw?

OpenClaw supports any LLM provider. ShuttleAI makes it easier by unifying everything under one API.

With ShuttleAI you get:

• ShuttleAI Auto (Smart request router that dynamically chooses the best model for coding, quick queries, or complex long-form tasks.)

• Claude Opus 4.6

• Claude Sonnet 4.6

• GPT-5.2

• GPT-OSS 120B

• And more

No switching dashboards. No juggling API keys from different companies.

Step 1 — Create a ShuttleAI Account

1. Go to https://shuttleai.com

2. Click Get API Key

3. Create your account

4. Choose a plan

Plan overview:

• Free → Testing with GPT-OSS

• Basic → Auto + GPT-5.2 + Claude Haiku

• Premium → Claude Opus 4.6 + Sonnet 4.6

• Scale → Production agents

If you want Claude Opus or Sonnet for serious agent workflows, choose Premium or Scale.

After subscribing:

• Go to Dashboard

• Copy your API key

Step 2 — Locate Your OpenClaw Config

OpenClaw stores configuration here:

~/.openclaw

Main config file:

~/.openclaw/openclaw.json

This file controls your providers and models.

You can override the default location using environment variables:

OPENCLAW_HOME
OPENCLAW_STATE_DIR
OPENCLAW_CONFIG_PATH

Workspace directory for the agent memory is usually:

~/openclaw/workspace

Step 3 — Edit openclaw.json

Open the file:

nano ~/.openclaw/openclaw.json

Add ShuttleAI as a provider.

Example configuration:

{
  "models": {
    "mode": "merge",
    "providers": {
      "shuttleai": {
        "baseUrl": "https://api.shuttleai.com/v1",
        "apiKey": "YOUR_API_KEY_HERE",
        "api": "openai-completions",
        "models": [
          {
            "id": "shuttleai/auto",
            "name": "ShuttleAI API",
            "reasoning": false,
            "input": ["text"]
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "shuttleai/auto"
      }
    }
  }
}

Replace:

YOUR_API_KEY_HERE

with your actual ShuttleAI key.

Save and exit.

Step 4 — Restart OpenClaw

Restart the agent:

openclaw restart

Or verify health:

openclaw gateway health

If it returns healthy, ShuttleAI is connected.

Optional — Add More Models

You can add additional models under ShuttleAI:

{
  "id": "openai/gpt-5.2",
  "name": "GPT-5.2"
}

Now your agent can:

• Use Opus for deep reasoning

• Use Sonnet for fast tasks

• Use GPT-OSS for lightweight work

All from one API.

Why Teams Choose ShuttleAI

Companies use ShuttleAI with OpenClaw because:

• No token math

• Simple monthly pricing

• Unified API

• Clean scaling

• Reliable infrastructure

It removes complexity and makes production setups easier.

Final Thoughts

OpenClaw is powerful. ShuttleAI makes it easier to run.

Create an account, choose a plan, edit your config, and you are live in minutes.