Overview
Acklix exposes a REST API for managing models, deployments, conversations, and running inference.
All execution requests are routed through deployments. Models cannot be used directly for inference.
This guide explains how to integrate external applications with Acklix using the REST API.
Acklix exposes a REST API for managing models, deployments, conversations, and running inference.
All execution requests are routed through deployments. Models cannot be used directly for inference.
All API requests require an API key. Access tokens and OAuth-based authentication are not supported.
API keys are scoped to a workspace and must be kept server-side.
To execute a model, send a request to the inference endpoint using a deployment ID.
curl -X POST "https://platform.acklix.com/api/v1/inference" \
-H "Authorization: Api-Key YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"deployment_id": "dep_12345",
"input": "How can I reset my password?"
}'Only deployment IDs are accepted by the inference API.
Errors are returned using standard HTTP status codes with a structured error payload.
{
"error": "deployment_not_found"
}401 — Invalid API key404 — Deployment not found409 — Deployment not active429 — Rate limit exceeded