Connect OpenCode to ApiClo

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.

Steps

1. Connection

   Export APICLO_API_KEY in the environment of the OpenCode server. For v2, add providers.apiclo with package @opencode/ai/providers/openai-compatible, env [APICLO_API_KEY] and settings.baseURL https://apiclo.com/v1.

2. Model and credentials

   Add a models entry whose modelID is the exact ApiClo model ID, and select apiclo/<alias>. The provider prefix belongs to the OpenCode selector; the upstream model ID remains the ApiClo ID.

3. Verification

   If you use v1, follow its provider/npm/options schema instead of mixing it with v2 providers/package/settings. Run text, tool and image checks separately; configure vision only for a model that actually supports it.

Examples

export APICLO_API_KEY="YOUR_APICLO_KEY"

$env:APICLO_API_KEY="YOUR_APICLO_KEY"

{
  "$schema": "https://opencode.ai/config.json",
  "model": "apiclo/sonnet",
  "providers": {
    "apiclo": {
      "env": ["APICLO_API_KEY"],
      "package": "@opencode/ai/providers/openai-compatible",
      "settings": {"baseURL": "https://apiclo.com/v1"},
      "models": {"sonnet": {"modelID": "claude-sonnet-5"}}
    }
  }
}

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

• A provider-schema error can indicate a v1/v2 mismatch. If the provider is unavailable, verify the key reaches the server process, not only a separate terminal.
• 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.

Sources

• OpenCode
• OpenCode v1