Kimi Code
Kimi models on a Kimi Code subscription. Bring your own key; nothing is billed by us.
What the harness already knows
| Provider id | kimi-coding |
| Base URL | https://api.kimi.ai/coding/v1 |
| Protocol | OpenAI-compatible chat completions |
| API key | KIMI_CODING_API_KEY |
| Model discovery | No — models come from the catalogue and from what you configure. |
Connecting it
The endpoint above is built in, so there is nothing to configure. Put the key in the environment and the provider appears in the model picker:
export KIMI_CODING_API_KEY="..."Keys are issued by Kimi Code — where to get one.
Worth knowing
The international Kimi Code endpoint (kimi.ai), over the OpenAI-compatible form models.dev records. A plan endpoint: its own env var, because a plan key sent to the pay-as-you-go host (or the reverse) is refused or billed per token.
Pointing it somewhere else
A regional host, a gateway, or a server of your own. Overrides in ~/.oharness/config.json are field level, so changing the endpoint does not mean restating the rest of the provider — this is the whole block, shown holding the default so the shape is clear:
{
"providers": {
"kimi-coding": {
"baseUrl": "https://api.kimi.ai/coding/v1"
}
}
}What you get either way
The same agent loop, the same tools, the same MCP servers and the same permission rules, whichever provider is underneath — and switching between them mid-session converts nothing, because history is never stored in a vendor’s shape. What an agent harness is covers why that is the hard part, and the providers reference covers the catalogue itself.