Add an uncensored OpenAI-compatible provider to Chatbox

Chatbox is a chat client for Windows, macOS, Linux, mobile and the web. On desktop it reaches any API directly; on the web version you turn on one switch so requests go through Chatbox's proxy.

Set it up

1. Sign in at wildwestapi.com/signup/ with the six-digit code sent to your email, open the dashboard and create an API key. It starts with sk-ww- and is shown in full once, so copy it somewhere safe.
2. Open Settings from the sidebar and go to Model Provider.
3. Click Add at the bottom, enter a name such as Wild West, and choose OpenAI API Compatible as the API mode.
4. Set API Host to https://wildwestapi.com/v1 and leave API Path on its default /chat/completions. The Preview line should read https://wildwestapi.com/v1/chat/completions.
5. Paste your sk-ww- key into API Key.
6. Add a model with the id outlaw-1. At least one model is required.
7. Save, then press Check to test the connection.
8. On the web version only: turn on Improve Network Compatibility for this provider.

Does it work with the Wild West API?

On the desktop app, yes, with no extra steps. The desktop build disables the browser's cross-site checks for its own window, so requests go straight to the API.

On the web version, the page itself makes the request, and the API does not answer CORS preflight today, so a plain connection fails. Chatbox's custom providers have an Improve Network Compatibility switch that sends the request through Chatbox's own proxy instead. Turn it on and the web version works too. Chatbox notes it can make connections slower, and it means your traffic passes through their proxy.

The settings that matter for long roleplay

• Max Message Count in Context decides how many earlier messages are sent. A low number is the usual reason a character forgets the plot. The models here have 512K to 1M tokens of context window, so you can raise it a lot, at the cost of more input tokens per turn.
• Max Output Tokens caps reply length; see max tokens.
• Stream output shows text as it is generated; see streaming.
• Put your character or narrator instructions in the conversation's system prompt.

Troubleshooting Chatbox

• 401: the key is missing, mistyped or disabled. Paste it again with no trailing space and check it starts with sk-ww-. A key from another provider will never work here.
• 402: your balance is too low for the request. Top up in the dashboard; see pricing. A huge context on every turn burns credit faster than you might expect.
• 404 or 400 with an unknown model: the model id is wrong. Use an exact id from the model list, such as outlaw-1, with no provider prefix and no spaces.
• 429: you are rate limited. Wait a few seconds and send again, and turn off any auto-retry loop that fires instantly.
• 5xx: trouble upstream. Retry; if it keeps happening, switch to another model id for a while.
• Network error, "Failed to fetch" or a CORS message: you are on the web version without Improve Network Compatibility. Switch it on for the provider, or use the desktop app.
• 404 on every request: check the Preview line. If it shows /v1 twice or no /chat/completions, fix API Host and API Path so the preview reads https://wildwestapi.com/v1/chat/completions.

FAQ

Related