Skip to content
StatusStart free

Chatbox

Chatbox is a cross-platform desktop and mobile chat client. Add MirAPI as a custom OpenAI-compatible provider to reach the whole catalog (chat, vision, and reasoning models) with one base URL and one key.

What you need

Section titled “What you need”
Element Value
Base URL https://api.mirapi.ai/v1
API key Your MirAPI key (sk-...)
Model deepseek-chat

Chatbox speaks the OpenAI-compatible protocol, so the base URL is the only address you configure. Because Chatbox appends /chat/completions itself, the base URL must end in /v1.

Configure

Section titled “Configure”
  1. Open Settings → Add custom provider (or Add Provider).
  2. Choose OpenAI API compatible.
  3. Fill in:
API domain / Base URL: https://api.mirapi.ai/v1
API key: sk-...
Default model: deepseek-chat
  1. Save the provider.
  2. If the provider’s model list is empty, add deepseek-chat (or any other model ID from GET /v1/models) to it. Then start a new chat with the MirAPI provider.

Verify with a message

Section titled “Verify with a message”

Send:

Reply with exactly: connected to MirAPI

The reply should contain the exact phrase. If you get an error instead, the cause is almost always the base URL or the key, so check both against the table above.

Tool-specific pitfalls

Section titled “Tool-specific pitfalls”
  • Keep /v1 in the base URL. https://api.mirapi.ai/v1 is correct; https://api.mirapi.ai alone breaks the chat path.
  • Pick models your key can call. A model outside your whitelist returns 403 even with a valid key.
  • 403 can also mean an empty balance. Top up and retry; the same key works again immediately.
  • 429 means rate limited. Retry with jittered exponential backoff; MirAPI sends no Retry-After header and does not retry for you.
  • Errors carry a request ID. Chatbox shows the raw HTTP error text, including MirAPI’s request ID suffix. Keep it for support tickets.
Section titled “Related links”