cURL
curl --request POST \ --url https://906e-2001-5a8-6cc-e000-55c0-f0b-9da7-10b0.ngrok-free.app/chat/completions \ --header 'Content-Type: application/json' \ --data ' { "model": "<string>", "messages": [ { "role": "system", "content": "<string>" } ], "search": { "domain_filter": [ "<string>" ], "recency": "day" }, "stream": true, "user_context": {} } '
{ "data": { "choices": [ { "index": 123, "message": { "role": "system", "content": "<string>" } } ] }, "request_id": "<string>", "meta": { "api_version": "<string>", "processing_ms": 123, "tokens_used": 123, "cost": { "total": 1, "breakdown": {} } } }
curl -X POST https://api.agentserp.com/chat/completions \ -H "Authorization: Bearer <token>" \ -H "Content-Type: application/json" \ -d '{"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello, who are you?"}]}'
Input for POST /chat/completions
LLM engine to use
1
Show child attributes
OpenAI-style chat roles
system
user
assistant
tool
Optional search-control block for chat
Allowed hostnames while augmenting answer
Recency constraint for on-the-fly search
day
week
month
year
If true, SSE stream; else aggregate JSON
Opaque dict preserved across turns
Chat response
Universal response wrapper
Endpoint-specific payload
Single chat message
Echo of client-supplied ID or server-assigned UUID
Metadata block attached to every response
Semantic version string of the API that produced the response
Time taken on the server to satisfy the request, in ms
Total LLM tokens consumed (prompt+completion)
Per-request cost information
Total dollar cost for serving this request
x >= 0
Optional map of operation → incremental cost (e.g. neuralSearch: 0.004)
