Connect Orca to ApiClo
Use ApiClo with Orca by configuring the coding agent that Orca launches: Codex CLI, Claude Code, Pi. Orca orchestrates agent sessions and worktrees; the child agent owns its API endpoint, credentials and model configuration.
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
Connection
Choose one child agent and complete its ApiClo setup guide first. Verify one short response outside Orca before adding orchestration.
Model and credentials
Open the repository in Orca and launch that configured agent. Make sure the actual local or remote runner has access to the agent's configuration and credential environment.
Verification
Run a small task in an isolated worktree. Increase concurrency only after checking combined token usage; each worker's model requests can add to the bill. Send images through the child agent's supported attachment flow.
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 the same agent works in a terminal but fails in Orca, compare the runner environment and config location. An ApiClo key on your laptop is not automatically available to a remote runner.
- 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