NEW

Jev is now available

Model prices

Connect Trae to ApiClo

Connect Trae to ApiClo through Settings → Models → Add Model → Custom Config when that option is available in your version and account. Choose the API format before entering the URL: OpenAI-compatible Chat Completions and Anthropic Messages use different request paths.

Before you start

  • Create a separate ApiClo API key and check balance and the selected model's current rates.
  • Use the client version matching the linked documentation. Keep credentials out of project files.
Create an API key

Steps

  1. Connection

    Sign in to Trae and open the custom model configuration. Name the connection ApiClo and enter a separate ApiClo key, not a Trae subscription credential.

  2. Model and credentials

    For OpenAI-compatible Base URL use https://apiclo.com/v1. For Anthropic, check the field description: use the root https://apiclo.com when the client adds /v1/messages, or the full https://apiclo.com/v1/messages only when it asks for a complete endpoint.

  3. Verification

    Enter an exact ApiClo model ID, save and select that model in the chat. Test a short answer, then tools or an image only if the chosen client mode and model support them.

Check the result

Send one small request and inspect ApiClo Logs for the exact model, outcome and charged usage. Test tool calls and images separately. Cache settings in the client do not prove a hit: check actual read/write token counts.

Troubleshooting

  • If custom models are unavailable, check the installed Trae version and account rather than changing the ApiClo key repeatedly. An empty response requires checking API format, model ID and output settings.
  • For 401, check the active key and credential source; for 404, check the request URL and model ID. Preserve the sanitized error body for support.

Compatibility and billing

ApiClo is an independent gateway. A client integration does not include that client's subscription or guarantee all its features. Compare ordinary input, cache reads, cache writes and output at current model rates; cache hits and savings are workload-dependent.

All documentation

Sources