Connect Kimi Code 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

   Open /provider in the Kimi Code terminal UI or edit its user config.toml. Add a provider named apiclo with type openai and base_url https://apiclo.com/v1.

2. Model and credentials

   Use api_key_env=APICLO_API_KEY and set that environment variable in the launching process. Do not set api_key and api_key_env together; they are alternative credential methods.

3. Verification

   Register a model alias pointing to an exact ApiClo ID, select it, and verify text, tools, reasoning and images independently. For custom model names, declare only capabilities actually supported by the endpoint.

Examples

export APICLO_API_KEY="YOUR_APICLO_KEY"

$env:APICLO_API_KEY="YOUR_APICLO_KEY"

[providers.apiclo]
type = "openai"
base_url = "https://apiclo.com/v1"
api_key_env = "APICLO_API_KEY"

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 successful provider save is not an integration test. If the key is absent, explicitly set api_key_env; do not assume automatic fallback to arbitrary shell variables.
• 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

• Kimi Code