Connect Chatbox to CaMeL Hub: One Key for GPT, Claude, Gemini & DeepSeek

Chatbox is a free, open-source AI chat client for Windows, macOS, Linux, iOS, Android, and the web — clean UI, conversations saved locally, and support for any OpenAI-compatible API endpoint instead of a single hardcoded provider. Point it at CaMeL Hub instead of one vendor's API and the same app can drive GPT-5.5, Claude Sonnet 5, Gemini 3.1 Pro, DeepSeek V4 Flash, and dozens of other models — one API key, one bill, no separate account per provider.

Chatbox ↗

1. Get your CaMeL Hub API key

   Sign in to the CaMeL Hub console and open the Token page. Create a new token and copy the key — you'll paste it into Chatbox in a later step. Treat it like a password: anyone who has it can spend your quota.

2. Add a custom model provider in Chatbox

   Open Chatbox, go to Settings, then the model provider screen (labeled Model Provider or AI Provider depending on version). Add a new custom provider and give it a name you'll recognize, e.g. "CaMeL Hub".

3. Switch the API mode to OpenAI-compatible

   In the provider's settings, find the field named API Mode / Provider Type and set it to OpenAI API Compatible (some versions just show OpenAI). This tells Chatbox to speak the standard /v1/chat/completions protocol that CaMeL Hub implements.

4. Point the host and path at CaMeL Hub

   Chatbox splits the endpoint into two fields — one usually named API Host / API Domain, the other API Path. Put the bare host in the first field; do not append /v1 there, since the path field supplies it separately:

   API Host:  https://api.camel-hub.com
   API Path:  /v1/chat/completions

5. Paste your API key

   Paste the key from step 1 into the field named API Key / Secret Key, then save the provider.

6. Add the model IDs you want to use

   Custom providers in Chatbox don't auto-discover a model list, so add each model ID by hand exactly as it appears on the CaMeL Hub console's Models page — for example:

   gpt-5.5
   claude-sonnet-5
   gemini-3.1-pro
   deepseek-v4-flash

7. (Optional) Import the whole provider as JSON

   Chatbox 1.15.1 and later can import a provider from a single JSON blob (Settings → Model Provider → Import). Paste the snippet below, then trim or extend the model list to match what you'll actually use — check current context-window and max-output limits on the CaMeL Hub Models page before relying on them, since provider specs change over time:

   {
     "id": "camelhub",
     "name": "CaMeL Hub",
     "type": "openai",
     "urls": {
       "website": "https://api.camel-hub.com/console/",
       "getApiKey": "https://api.camel-hub.com/console/token",
       "docs": "https://api.camel-hub.com/docs",
       "models": "https://api.camel-hub.com/console/models"
     },
     "settings": {
       "apiHost": "https://api.camel-hub.com",
       "apiPath": "/v1/chat/completions",
       "models": [
         { "modelId": "gpt-5.5", "nickname": "GPT-5.5", "type": "chat", "capabilities": ["vision", "tool_use"] },
         { "modelId": "claude-sonnet-5", "nickname": "Claude Sonnet 5", "type": "chat", "capabilities": ["vision", "tool_use"] },
         { "modelId": "gemini-3.1-pro", "nickname": "Gemini 3.1 Pro", "type": "chat", "capabilities": ["vision", "reasoning", "tool_use"] },
         { "modelId": "deepseek-v4-flash", "nickname": "DeepSeek V4 Flash", "type": "chat", "capabilities": ["tool_use"] }
       ]
     }
   }

8. Send a test message

   Start a new chat, pick one of the models you added, and send a short message. A reply confirms the connection works; check the usage/log page in the CaMeL Hub console to confirm the request billed to your account.

Frequently asked questions