在 OpenCode 中使用 LithosAI - LithosAI

开始之前

安装 OpenCode CLI，在 API Key 页面创建 key，并在模型页面选好模型。

1

设置 API key

把 key 设为环境变量：

export LITHOSAI_API_KEY="your-key"

2

配置 LithosAI

把以下配置合并到 ~/.config/opencode/opencode.json，保留已有的 provider。示例包含 Kimi K3 fast、Kimi K3 ultra 和 DeepSeek V4.1 Flash fast。按所用模型设置 token 上限。

OpenCode 配置

~/.config/opencode/opencode.json

{
  "$schema": "https://opencode.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" },
            "minimal": { "disabled": true },
            "medium": { "disabled": true },
            "xhigh": { "disabled": true }
          }
        },
        "moonshotai/Kimi-K3-ultra": {
          "name": "moonshotai/Kimi-K3-ultra",
          "reasoning": true,
          "limit": {
            "context": 32768,
            "output": 4096
          },
          "options": { "reasoningEffort": "high" },
          "variants": {
            "low": { "reasoningEffort": "low" },
            "high": { "reasoningEffort": "high" },
            "max": { "reasoningEffort": "max" },
            "minimal": { "disabled": true },
            "medium": { "disabled": true },
            "xhigh": { "disabled": true }
          }
        },
        "deepseek-ai/DeepSeek-V4.1-Flash-fast": {
          "name": "deepseek-ai/DeepSeek-V4.1-Flash-fast",
          "reasoning": true,
          "limit": {
            "context": 32768,
            "output": 4096
          },
          "options": { "reasoningEffort": "high" },
          "variants": {
            "low": { "reasoningEffort": "low" },
            "high": { "reasoningEffort": "high" },
            "max": { "reasoningEffort": "max" },
            "minimal": { "disabled": true },
            "medium": { "disabled": true },
            "xhigh": { "disabled": true }
          }
        }
      }
    }
  }
}

要使用其他模型或速度档位，复制 provider.lithosai.models 下的一个条目，按照模型目录修改它的键名和 name。再按该模型调整 token 上限和支持的推理强度，然后重新打开 OpenCode。

3

开始对话

运行 opencode 开始对话。

模型与推理强度

模型与速度档位：在当前对话中用 /models 切换。
推理强度：用 /variants 选择 low、high 或 max，默认为 high。

所有 Agent 通用的问题见常见问题。

参考资料