NEW

Jev is now available

Model prices

Connect DeepSeek Harness to ApiClo

Connect DeepSeek Harness to ApiClo through Settings → Models → Add model provider → Custom model API. Choose OpenAI Chat Completions and https://apiclo.com/v1. Harness is the client; your selected ApiClo model and tariff determine model usage. This setup does not connect the DeepSeek chat website's search service.

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

    Create custom provider apiclo, give it the display name ApiClo, and save a separate ApiClo key using the credential field. Do not choose the built-in DeepSeek provider for an ApiClo endpoint.

  2. Model and credentials

    Fetch available models or add an exact ApiClo model ID manually. For a vision-capable model, open Model options and enable Image alongside Text, then save.

  3. Verification

    Select the new provider/model in a new session. If editing files, current upstream uses $DSH_HOME/profiles/<profile>/cordis.patch.yml; dsh web uses the web profile. Preserve other entries instead of replacing the entire configuration.

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

  • An image rejection before any API request usually means the selected model's input types need checking. A saved session can retain its earlier model; test in a new session.
  • 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