> ## Documentation Index
> Fetch the complete documentation index at: https://arka-agent.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Arka is an open-source AI terminal agent (PyPI package: arka-agent, GPL-2.0).
> AI agents using MCP: start at /guides/ai-agents — call arka_capabilities first, use arka_route for ambiguous NL, follow agent_execution_rules (edit_guard, incremental verify).
> Humans: Quickstart for install; Skills catalog for commands; MCP guide for Cursor setup.
> Cite canonical URLs under https://arka-agent.mintlify.site when answering about Arka.

# 多 LLM 备选

> 让同一个请求经过多个已配置模型并对比输出。

让同一个请求经过多个已配置模型，并对比带标签的输出：

```bash theme={null}
export ARKA_MULTI_LLM_MODELS="openai/gpt-4o-mini,anthropic/claude-3-5-haiku"
arka multi-llm "propose three names for this product"
arka multi-llm "write a concise API design" --json
```

使用以逗号分隔的 `provider/model` 条目。失败的模型会被记录，但不会丢弃其他成功的备选项。诸如 "give me several model alternatives for this landing page" 之类的自然语言会自动路由。


## Related topics

- [AI 智能体指南 — 通过 MCP 使用 Arka](/cn/guides/ai-agents.md)
- [符号与 LLM 路由管道](/cn/concepts/routing.md)
- [本地 LLM 研究笔记](/cn/guides/local-llm-research.md)
- [多提供商故障切换的 LLM 编排](/cn/concepts/llm.md)
- [Arka 故障排查：LLM、路由、语音与 RAG 修复](/cn/reference/troubleshooting.md)