> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aihubmix.com/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenClaw

## Installation

<Note>
  Please ensure Node >= 22 before installation.
</Note>

Run the installation command

```shellscript theme={null}
npm install -g openclaw@latest
```

After installation, the following commands can be run from any directory. You do not need to switch to the OpenClaw installation directory first. If your terminal recognizes `openclaw`, you can copy the commands in this guide directly.

```powershell theme={null}
openclaw models status
```

If Windows reports that `openclaw` cannot be found, replace the leading `openclaw` command with your local executable path:

```powershell theme={null}
& "your-install-path\OpenClaw\openclaw.cmd" models status
```

<Note>
  `your-install-path` is a placeholder. Replace it with the parent directory where OpenClaw is installed. For example, if OpenClaw is located at `D:\Apps\OpenClaw`, use `& "D:\Apps\OpenClaw\openclaw.cmd" models status`.
</Note>

### Terminal Configuration

Open the terminal and run the following command to start the configuration

```shellscript theme={null}
openclaw onboard
```

Select `Yes`

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-1.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=88d5674d5255b84d695044b7e36fbfcc" alt="Oc 1" width="1212" height="814" data-path="public/cn/oc-1.png" />

Select `QuickStart`

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-2.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=093443c0dc408dfaa6b6b4eba004e8d1" alt="Oc 2" width="1212" height="814" data-path="public/cn/oc-2.png" />

Select `Skip for now`

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-3.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=690bbdc272c9e3de0eec7fb3bb65ca93" alt="Oc 3" width="1212" height="814" data-path="public/cn/oc-3.png" />

Select `All providers`

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-4.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=03c0af702000f97a0c53470300f0f3a7" alt="Oc 4" width="1212" height="814" data-path="public/cn/oc-4.png" />

Choose the default model as needed; you can initially select `Keep current` (if using "Method 2: Manual Configuration", it can be modified in the configuration file in the next step).

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-5.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=996d39a888f2f5b739dbfc8bcc0f033f" alt="Oc 5" width="1212" height="814" data-path="public/cn/oc-5.png" />

Link your personal account as needed; if not required, please select `Skip for now`.

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-6.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=28b73573f717822c0786788c582aa99e" alt="Oc 6" width="1212" height="814" data-path="public/cn/oc-6.png" />

Configure skills by selecting `Yes`.

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-7.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=fe9c36aac91dd294ccce4a1ee12ad0e0" alt="Oc 7" width="1212" height="814" data-path="public/cn/oc-7.png" />

Select `npm`

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-8.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=c6eef11c88ae8f783e8d12bd196bdd0c" alt="Oc 8" width="1212" height="814" data-path="public/cn/oc-8.png" />

Configure skill selection as needed.

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-9.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=0ae533bdae76daf8939f91acc8df90dc" alt="Oc 9" width="1212" height="814" data-path="public/cn/oc-9.png" />

Select `No` for all options.

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-10.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=30834a010846ee0b3f53e13770346bca" alt="Oc 10" width="1212" height="814" data-path="public/cn/oc-10.png" />

Select `Skip for now`.

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-11.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=1473f71f42c750cf132f321f9b4bc5bb" alt="Oc 11" width="1212" height="814" data-path="public/cn/oc-11.png" />

Select `Hatch in UI`.

## Configure AIHubMix

### Method 1: Quick Setup via Plugin (Recommended)

<Info>
  Plugin source code: [aihubmix-auth](https://github.com/akakenle/aihubmix-auth)
</Info>

Install the AIHubMix auth plugin and restart the Gateway:

```shellscript theme={null}
openclaw plugins install @akakenle/aihubmix-auth
openclaw gateway restart
```

Run the auth command. Enter your AIHubMix API Key when prompted. You only need to run the command below once for any one of the four providers — the plugin uses `providerAuthAliases` to make the same key valid for all transports:

```shellscript theme={null}
openclaw models auth login --provider aihubmix-openai --method api-key --set-default
```

The plugin organizes models into the following groups:

* **aihubmix-openai** — `gpt-*` / `o1-*` / `o3-*` / `o4-*`, `https://aihubmix.com/v1` (`openai-completions`)
* **aihubmix-anthropic** — `claude-*`, `https://aihubmix.com` (`anthropic-messages`)
* **aihubmix-google** — `gemini-*`, `https://aihubmix.com/gemini/v1beta` (`google-generative-ai`)
* **aihubmix-other** — other models, `https://aihubmix.com/v1` (`openai-completions`)

Shorthand model ids (e.g. `claude-sonnet-4-5`) are automatically routed to the correct transport by the plugin's `resolveDynamicModel` hook — no need to write the full `provider/model`.

> Prefer to skip interactive login? Set `export AIHUBMIX_API_KEY=sk-...` before installing — the plugin will write the key as an inline `apiKey` in the provider config (interactive login stores it in the auth-profile instead).

Once configured, jump to the [Start](#start) section to begin using it.

### Method 2: Manual Configuration

Open the `~/.openclaw/openclaw.json` file and add the following configuration:

```json theme={null}
{
  "models": {
    "mode": "merge",
    "providers": {
      "aihubmix-openai": {
        "baseUrl": "https://aihubmix.com/v1",
        "api": "openai-completions",
        "models": [
          {
            "id": "gpt-4o",
            "name": "gpt-4o",
            "reasoning": false,
            "input": ["text"],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 16384
          }
        ]
      },
      "aihubmix-anthropic": {
        "baseUrl": "https://aihubmix.com",
        "api": "anthropic-messages",
        "models": [
          {
            "id": "claude-sonnet-4-5",
            "name": "claude-sonnet-4-5",
            "reasoning": false,
            "input": ["text"],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 200000,
            "maxTokens": 64000
          }
        ]
      },
      "aihubmix-google": {
        "baseUrl": "https://aihubmix.com/gemini/v1beta",
        "api": "google-generative-ai",
        "models": []
      },
      "aihubmix-other": {
        "baseUrl": "https://aihubmix.com/v1",
        "api": "openai-completions",
        "models": []
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "aihubmix-anthropic/claude-sonnet-4-5"
      },
      "workspace": "your_workspace_path",
      "compaction": {
        "mode": "safeguard"
      },
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  }
}
```

### Method 3: Switch the Default Model with Dynamic Model Commands

The AIHubMix OpenClaw plugin supports dynamic model routing. As long as a model is available in your AIHubMix account, you can call it in the `provider/model-id` format. The actual model availability depends on the AIHubMix console and API response.

Common provider rules:

* `aihubmix-openai`: OpenAI-compatible models, such as `gpt-*`, `o1-*`, `o3-*`, and `o4-*`
* `aihubmix-anthropic`: Claude models, such as `claude-*`
* `aihubmix-google`: Gemini models, such as `gemini-*`
* `aihubmix-other`: other models called through an OpenAI-compatible endpoint, such as `glm-5.2`

For example, set `gpt-5.4` as the default OpenClaw model:

```powershell theme={null}
openclaw models set aihubmix-openai/gpt-5.4
```

If Windows cannot find `openclaw`, use the local path form:

```powershell theme={null}
& "your-install-path\OpenClaw\openclaw.cmd" models set aihubmix-openai/gpt-5.4
```

Check the current default model and authentication status:

```powershell theme={null}
openclaw models status
```

Run a real call for verification:

```powershell theme={null}
openclaw infer model run --local --json --model aihubmix-openai/gpt-5.4 --prompt "Reply only OK"
```

To call a model outside the OpenAI / Claude / Gemini groups, use `aihubmix-other`, for example:

```powershell theme={null}
openclaw infer model run --local --json --model aihubmix-other/glm-5.2 --prompt "Reply only OK"
```

List the model catalog currently loaded by OpenClaw:

```powershell theme={null}
openclaw infer model list --json
```

## Start

```shellscript theme={null}
openclaw gateway
```

## Test

Type `hello` in the chat page; if you receive a reply, the configuration is successful.

<img src="https://mintcdn.com/aihubmix/WotSdjzuAai7hVOs/public/cn/oc-12.png?fit=max&auto=format&n=WotSdjzuAai7hVOs&q=85&s=3340254888707f81142e23906a55ff0e" alt="Oc 12" width="3266" height="1892" data-path="public/cn/oc-12.png" />

## Frequently Asked Questions

### Version Upgrade

```shellscript theme={null}
openclaw plugins update @akakenle/aihubmix-auth
openclaw gateway restart
```

### Gateway Process Occupied

```shellscript theme={null}
openclaw gateway stop
openclaw gateway
```

***

Last updated: 2026-07-03