Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
curl -X POST "https://router.example.com/v1/router/chat" \
-H "Authorization: Bearer <api-key>" \
-H "Content-Type: application/json" \
-d '{
"model": "default",
"messages": [{"role": "user", "content": "Hello router"}],
"dry_run": true
}'
{
"decision": {
"provider": "openai",
"model": "gpt-4o",
"recipe": "semantic-router"
},
"response": {
"id": "chatcmpl-example",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello! How can I help?"},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 8,
"total_tokens": 18
}
}
}
通过咏唱引擎 ROUTER 发送一次测试聊天补全并预览路由决策。支持 dry-run 模式。
curl -X POST "https://router.example.com/v1/router/chat" \
-H "Authorization: Bearer <api-key>" \
-H "Content-Type: application/json" \
-d '{
"model": "default",
"messages": [{"role": "user", "content": "Hello router"}],
"dry_run": true
}'
{
"decision": {
"provider": "openai",
"model": "gpt-4o",
"recipe": "semantic-router"
},
"response": {
"id": "chatcmpl-example",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello! How can I help?"},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 8,
"total_tokens": 18
}
}
}
/v1/chat/completions 相同的请求体，并新增一个可选的 dry_run 标志。可用它在不向下游发出请求的情况下校验路由规则、检查 provider 选择并调试配方。
此接口会返回路由决策；在非 dry-run 模式下，还会返回下游 provider 的响应。
POST /v1/router/chat
Authorization: Bearer <api-key>。
true 时，router 计算路由决策但不向 provider 发送请求。curl -X POST "https://router.example.com/v1/router/chat" \
-H "Authorization: Bearer <api-key>" \
-H "Content-Type: application/json" \
-d '{
"model": "default",
"messages": [{"role": "user", "content": "Hello router"}],
"dry_run": true
}'
{
"decision": {
"provider": "openai",
"model": "gpt-4o",
"recipe": "semantic-router"
},
"response": {
"id": "chatcmpl-example",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello! How can I help?"},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 8,
"total_tokens": 18
}
}
}
Was this page helpful?