菜单
Image generation via flow_router OpenAI-shape /v1/images endpoint. Routes to active media providers (OpenAI, Stability, BFL, Gemini, etc.).
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
Chat / code generation via flow_router using OpenAI /v1/chat/completions or Anthropic /v1/messages or Gemini /v1beta/models/...:generateContent with streaming + auto-fallback combos.
Embeddings via flow_router /v1/embeddings. OpenAI-compat shape, routes to active embedding providers (OpenAI, Gemini, Cohere, etc.).
Entry point for flow_router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions flow_router, FLOW_ROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills.
Speech-to-text (audio transcription) via flow_router /v1/audio/transcriptions. OpenAI-compat shape (multipart form), routes to active STT providers.
Text-to-speech via flow_router. OpenAI /v1/audio/speech shape, routes to active TTS providers (OpenAI, ElevenLabs, Gemini TTS, Edge TTS, etc.).
Web fetch (URL → markdown) via flow_router /v1/web/fetch. Pulls a page and returns cleaned markdown text.
| name | flow-router-image |
| description | Image generation via flow_router OpenAI-shape /v1/images endpoint. Routes to active media providers (OpenAI, Stability, BFL, Gemini, etc.). |
curl -X POST $FLOW_ROUTER_URL/v1/images \
-H "Authorization: Bearer $FLOW_ROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-3",
"prompt": "A serene mountain lake at dawn",
"size": "1024x1024",
"n": 1
}'
Response: { "data": [{ "url": "..." }] } or { "data": [{ "b64_json": "..." }] } depending on provider.
curl $FLOW_ROUTER_URL/v1/models/image | jq '.data[].id'
Backed by media-providers configured in Dashboard → Media Providers.