Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
通过 OpenAI 兼容的自定义 provider，把 Kilo Code 直接接入 LithosAI。
配置 LithosAI
| 设置项 | 值 |
|---|---|
| Provider ID | lithosai |
| Display name | LithosAI |
| Provider API | OpenAI Compatible |
| Base URL | https://api.lithosai.cloud/v1 |
| API key | 你的 LithosAI API key |
| Models | 从 LithosAI 模型列表中添加或选择 ID，例如 moonshotai/Kimi-K3-fast |
保存 provider
limit.context 和 limit.output。VS Code 推理强度配置
provider.lithosai.models 下你的模型条目里，即可启用 low、high 和 max，默认为 high：{
"reasoning": true,
"options": { "reasoningEffort": "high" },
"variants": {
"low": { "reasoningEffort": "low" },
"high": { "reasoningEffort": "high" },
"max": { "reasoningEffort": "max" },
"medium": { "disabled": true },
"minimal": { "disabled": true },
"xhigh": { "disabled": true }
}
}
设置 API key
export LITHOSAI_API_KEY="your-key"
配置 LithosAI
moonshotai/Kimi-K3-fast 为例。把它合并到 ~/.config/kilo/kilo.jsonc，并按你的模型设置 token 上限。一定要写在这个全局配置文件里：在不受信任的项目文件中，{env:...} 形式的凭据不会被解析。Kilo CLI 配置
{
"$schema": "https://app.kilo.ai/config.json",
"model": "lithosai/moonshotai/Kimi-K3-fast",
"provider": {
"lithosai": {
"npm": "@ai-sdk/openai-compatible",
"name": "LithosAI",
"options": {
"baseURL": "https://api.lithosai.cloud/v1",
"apiKey": "{env:LITHOSAI_API_KEY}"
},
"models": {
"moonshotai/Kimi-K3-fast": {
"name": "moonshotai/Kimi-K3-fast",
"reasoning": true,
"limit": {
"context": 32768,
"output": 4096
},
"options": { "reasoningEffort": "high" },
"variants": {
"low": { "reasoningEffort": "low" },
"high": { "reasoningEffort": "high" },
"max": { "reasoningEffort": "max" },
"medium": { "disabled": true },
"minimal": { "disabled": true },
"xhigh": { "disabled": true }
}
}
}
}
}
}
provider.lithosai.models 下的条目，再对照模型列表修改它的 key 和 name。调整 token 上限和支持的推理强度，然后重新打开 Kilo。开始对话
kilo。在当前对话里，用 /models 在已配置的模型之间切换。/variants 选择 low、high 或 max，默认为 high。