POST /v1/chat/completions

Estado: Endpoint público estable.

Crea una respuesta de chat compatible con OpenAI.

Endpoint

POST https://api.nexorouter.com/v1/chat/completions
Authorization: Bearer YOUR_NEXOROUTER_API_KEY
Content-Type: application/json

Request body

Field	Type	Required	Notes
`model`	string	yes	Copia el ID exacto desde Models o `GET /v1/models`.
`messages`	array	yes	Lista de mensajes compatible con OpenAI, no vacía.
`temperature`	number	no	`0` a `2`.
`top_p`	number	no	`0` a `1`.
`max_tokens`	integer	no	Entero positivo.

Curl mínimo

curl https://api.nexorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $NEXOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      { "role": "user", "content": "Write one short launch checklist." }
    ],
    "max_tokens": 256
  }'

Forma de response

{
  "id": "chatcmpl_example",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Create an API key, choose a model, test in Playground, and monitor usage logs."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 18,
    "total_tokens": 38
  }
}

Verifica en Usage Logs

Después de que un request tenga éxito o falle, confirma que el log incluya API key, model ID, estado, tokens, costo, latencia y request ID.