菜单
Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through KeiRouter.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions KeiRouter, KEIROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.
Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
Generate images via KeiRouter /v1/images/generations using OpenAI DALL-E / Gemini Imagen / FLUX / MiniMax / Stability AI / Fal.ai models. Use when the user wants to create, generate, draw, or render an image, picture, or text-to-image (txt2img).
Speech-to-text via KeiRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
Text-to-speech via KeiRouter /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Inworld voices. Use when the user wants to convert text to speech, generate audio, voiceover, narrate, or read text aloud.
Fetch URL → markdown / text / HTML via KeiRouter /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
| name | keirouter-chat |
| description | Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through KeiRouter. |
Requires KEIROUTER_URL (and KEIROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/mydisha/keirouter/main/skills/keirouter/SKILL.md for setup.
POST $KEIROUTER_URL/v1/chat/completions — OpenAI formatPOST $KEIROUTER_URL/v1/messages — Anthropic formatPOST $KEIROUTER_URL/v1/responses — OpenAI Responses formatcurl $KEIROUTER_URL/v1/models | jq '.data[].id'
# Per-model metadata (contextWindow, params)
curl "$KEIROUTER_URL/v1/models/info?id=openai/gpt-4o"
Combos (e.g. vip, mycodex) auto-fallback through multiple providers.
curl -X POST $KEIROUTER_URL/v1/chat/completions \
-H "Authorization: Bearer $KEIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-5","messages":[{"role":"user","content":"Hi"}],"stream":false}'
JS (OpenAI SDK):
import OpenAI from "openai";
const client = new OpenAI({ baseURL: `${process.env.KEIROUTER_URL}/v1`, apiKey: process.env.KEIROUTER_KEY });
const res = await client.chat.completions.create({
model: "openai/gpt-5",
messages: [{ role: "user", content: "Hi" }],
stream: true,
});
for await (const chunk of res) process.stdout.write(chunk.choices[0]?.delta?.content || "");
curl -X POST $KEIROUTER_URL/v1/messages \
-H "Authorization: Bearer $KEIROUTER_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{"model":"anthropic/claude-opus-4-7","max_tokens":1024,"messages":[{"role":"user","content":"Hi"}]}'
OpenAI (/v1/chat/completions):
{ "id": "chatcmpl-...", "object": "chat.completion", "model": "openai/gpt-5",
"choices": [{ "index": 0, "message": { "role": "assistant", "content": "Hello!" }, "finish_reason": "stop" }],
"usage": { "prompt_tokens": 8, "completion_tokens": 2, "total_tokens": 10 } }
Streaming (stream:true) emits SSE: data: {choices:[{delta:{content:"..."}}]}\n\n ... data: [DONE]\n\n.
Anthropic (/v1/messages):
{ "id": "msg_...", "type": "message", "role": "assistant", "model": "anthropic/claude-opus-4-7",
"content": [{ "type": "text", "text": "Hello!" }],
"stop_reason": "end_turn", "usage": { "input_tokens": 8, "output_tokens": 2 } }
| Provider | model format | Examples |
|---|---|---|
| OpenAI | openai/<model> | openai/gpt-5, openai/gpt-4o |
| Anthropic | anthropic/<model> | anthropic/claude-opus-4-7, anthropic/claude-sonnet-4-6 |
| Claude Code | cc/<model> | cc/claude-opus-4-7 |
| Gemini | gemini/<model> | gemini/gemini-2.5-pro, gemini/gemini-2.5-flash |
| Groq | groq/<model> | groq/llama-3.3-70b |
| DeepSeek | ds/<model> | ds/deepseek-chat, ds/deepseek-coder |
| OpenRouter | openrouter/<model> | openrouter/anthropic/claude-opus-4-7 |
| Mistral | mistral/<model> | mistral/mistral-large-latest |
| xAI | xai/<model> | xai/grok-3 |
| Ollama Local | ollama-local/<model> | ollama-local/llama3.2 |
| Custom OpenAI | custom-openai/<model> | Any model on your custom endpoint |