Tools

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.

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.

Almost the same as desktop

  • Different entry point: 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.

Download and install

  • Official site: 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

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

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

ProtocolModelsAPI HostAPI Path
Claude API (Anthropic Compatible)Claude models, Chinese models (DeepSeek, Qwen, GLM, Kimi, etc.)https://api.lmuai.comDefault is fine
OpenAI Responses API CompatibleOpenAI models (GPT-5.6 / GPT-5.5, etc.)https://api.lmuai.com/responses

The API Host never includes /v1

Chatbox appends the path automatically, so 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. If the domain isn't api.lmuai.com, the API Host is wrong.

Method 1: Anthropic protocol (Claude and Chinese models)

  1. API Mode: select 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.

Method 2: OpenAI protocol (GPT models)

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
  1. API Mode: select 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

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):

A completed Chatbox mobile configuration

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.

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 page.

Last updated:

Chatbox

Connect Chatbox on every platform (Windows / macOS / Linux / iOS / Android / Web) to the LMU AI API — dual-protocol, no proxy needed in China.

Hermes Agent

Connect Hermes Agent to LMU AI — edit ~/.hermes/config.yaml with a base_url that includes /v1 and your sk- key to switch to any available model.

On this page

Download and installOpening the configuration entry pointThe two protocolsMethod 1: Anthropic protocol (Claude and Chinese models)Method 2: OpenAI protocol (GPT models)A worked example and mobile-specific detailsTroubleshooting