Procesar texto con un modelo LLM específico

🚀 Servidor de producción

https://api.hiveflow.ai/api

POST

/llm/process

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.hiveflow.ai/api/llm/process' \
--header 'Content-Type: application/json' \
--data-raw '{
    "llm": "openai",
    "model": "gpt-3.5-turbo",
    "prompt": "Analiza el sentimiento del siguiente texto...",
    "agentObjective": "Eres un experto en análisis de sentimientos",
    "url": "string",
    "temperature": 0.7,
    "maxTokens": 1000
}'

Response Example

{
    "success": true,
    "result": "string",
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "total_tokens": 0
    },
    "model": "string",
    "provider": "string"
}

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/json

Examples

Responses

🟢200OK

application/json

Procesamiento exitoso

Body

🟠400Bad Request

🟠401Unauthorized

🟠429429

🔴500Server Error

Modified at 2025-06-19 15:26:15

Obtener modelos disponibles por proveedor

Obtener lista de proveedores disponibles