import { Callout, Tabs } from "@/docs/components";

Models

<div className="status-badge status-stable">Stable</div>

Discover and list available AI models.

List Models

<div className="api-endpoint"> <span className="method-badge method-badge-get">GET</span> <span className="path">/api/v1/models</span> </div>

Returns a list of available models for the current deployment.

Request

bash

curl -X GET "https://elizacloud.ai/api/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

json

{
  "object": "list",
  "data": [
    {
      "id": "provider/model-id",
      "object": "model",
      "created": 1705312800,
      "owned_by": "provider",
      "capabilities": ["chat"]
    }
  ]
}

Chat Models

The /api/v1/models response is the source of truth for the full live catalog. Provider availability, context windows, and capabilities can change with provider catalogs and deployment configuration.

Embedding Models

Embedding model availability and dimensions are returned by the model catalog or the embeddings API response for the current deployment.

Image Models

Image model availability is also catalog-driven. Use /api/v1/models and the Image Generation API reference for current defaults.

Model Selection Tips

<Callout type="info"> Start with the dashboard or API Explorer defaults, then switch models based on observed quality, latency, and cost for your workload. </Callout>