# Chatbox Mobile

> Connect Chatbox mobile (iOS / Android) to LMU AI: open Model Provider from ☰ and set the API Host for both protocols — direct connection in China, no proxy.

URL: https://docs.lmuai.com/en/docs/tools/chatbox-mobile





Chatbox mobile (iOS / Android) shares the same configuration logic as the desktop version — only the entry point and field names differ slightly. This guide walks through it screen by screen for mobile; for desktop, see [Chatbox — all platforms](./chatbox).

<Callout type="info" title="Almost the same as desktop">
  * **Different entry point*&#x2A;: on mobile you open Settings from the **☰ menu in the top-left**; on desktop it's Settings in the bottom-left.
  * **Same fields**: on mobile they're labeled **API Host** and **API Path**, matching the desktop version exactly — just follow the steps below.
</Callout>

***

## Download and install [#download-and-install]

* **Official site**: [https://chatboxai.app](https://chatboxai.app)
* Install from the App Store (iOS) or the app store / official APK (Android) — no account needed to use bring-your-own-key (BYOK) mode.

***

## Opening the configuration entry point [#opening-the-configuration-entry-point]

Open Chatbox → tap the **menu icon ☰ in the top-left** to open the sidebar → tap **Settings** → go to **Model Provider** → tap **Add** at the bottom.

Once you're on the configuration screen, fill it in following Method 1 / Method 2 below.

***

## The two protocols [#the-two-protocols]

LMU AI supports two connection protocols; choose one based on the model type:

| Protocol                              | Models                                                          | API Host                | API Path        |
| ------------------------------------- | --------------------------------------------------------------- | ----------------------- | --------------- |
| **Claude API (Anthropic Compatible)** | Claude models, Chinese models (DeepSeek, Qwen, GLM, Kimi, etc.) | `https://api.lmuai.com` | Default is fine |
| **OpenAI Responses API Compatible**   | OpenAI models (GPT-5.6 / GPT-5.5, etc.)                         | `https://api.lmuai.com` | `/responses`    |

<Callout type="info" title="The API Host never includes /v1">
  Chatbox appends the path automatically, so &#x2A;*always enter the API Host up to the domain only — do not include `/v1`**. After you fill it in, the full assembled address is shown live below the fields — for example, the OpenAI Responses protocol becomes `https://api.lmuai.com/v1/responses`. &#x2A;*If the domain isn't `api.lmuai.com`, the API Host is wrong.**
</Callout>

***

## Method 1: Anthropic protocol (Claude and Chinese models) [#method-1-anthropic-protocol-claude-and-chinese-models]

1. **API Mode*&#x2A;: select &#x2A;*`Claude API (Anthropic Compatible)`**
2. **Name**: anything you like (e.g. `LMU AI`)
3. **API Host**: enter `https://api.lmuai.com` (**without** `/v1`)
4. **API Key**: enter the `sk-` key generated in the console
5. **Add models**: the mobile preset list may not include the latest models, so in the Model section tap New / Add Model and enter the model ID, for example:

   * `claude-opus-5`
   * `claude-sonnet-5`
   * `claude-haiku-4-5`
   * `deepseek-v4-pro`
   * `qwen3.8-max-preview`
   * `glm-5.2`
   * `kimi-k3`

   For the full list of available models, see the [Model Gallery](/en/docs/guide/models).

***

## Method 2: OpenAI protocol (GPT models) [#method-2-openai-protocol-gpt-models]

<Callout type="warn" title="Requirements">
  You need to meet one of these conditions:

  * You have subscribed to a **GPT plan**
  * You use pay-as-you-go billing and have selected the **GPT group** in the LMU AI console
</Callout>

1. **API Mode*&#x2A;: select &#x2A;*`OpenAI Responses API Compatible`** (not `OpenAI API Compatible`)
2. **Name**: anything you like (e.g. `LMUAI-GPT`)
3. **API Host**: enter `https://api.lmuai.com`
4. **API Path**: enter `/responses`
5. **API Key**: enter the `sk-` key generated in the console
6. **Add models**: in the Model section tap New and enter the model ID, e.g. `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.5`, `gpt-5.4`.

Chatbox joins the API Host, `/v1`, and API Path into the full address `https://api.lmuai.com/v1/responses`, shown live below the fields.

***

## A worked example and mobile-specific details [#a-worked-example-and-mobile-specific-details]

Below is a completed mobile configuration screen (OpenAI Responses protocol; the full address `https://api.lmuai.com/v1/responses` is already assembled below the fields):

<img alt="A completed Chatbox mobile configuration" src="__img0" />

<Callout type="info" title="Two details for mobile">
  * **"Improve Network Compatibility"**: turn **on** this switch near the bottom of the screen; it reduces connection problems on mobile networks.
  * **Check the full address assembled below the fields**: once filled in, Chatbox shows the final request URL live (in the screenshot above it yields `https://api.lmuai.com/v1/responses`). If the domain isn't `api.lmuai.com`, the **API Host** is wrong.
</Callout>

***

## Troubleshooting [#troubleshooting]

* **Changes don't take effect**: after saving, restart Chatbox once or reselect the model in the chat screen; on mobile you sometimes also need to restart after switching between Wi-Fi and cellular.
* **401 / 403 errors**: check in order whether the API Key is the `sk-` key from the LMU AI console, whether the API Host is correct (without `/v1`), whether the OpenAI protocol's API Mode and API Path are right, and whether your current plan / billing group includes the model you're calling.
* For more on the protocols, model IDs, and common issues, see the shared desktop-and-mobile [Chatbox — all platforms](./chatbox) page.