Models endpoint

Returns a flat JSON array of every model id currently registered in the Meridian routing table — 227 entries as of this writing. No pagination, no authentication required. Use this endpoint to populate dropdowns, validate user-supplied model names, or audit which providers are live.

Response shape

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1715367049,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-5-sonnet-20241022",
      "object": "model",
      "created": 1729536000,
      "owned_by": "anthropic"
    }
    // ... 225 more entries
  ]
}

Every entry carries id, object (always "model"), a Unix-epoch created timestamp, and an owned_by provider slug.

Filtering client-side

The array is unsorted. Filter by provider or substring match before rendering:

const res = await fetch("https://api.getnimbus.net/v1/models");
const { data } = await res.json();

const openaiModels = data.filter(m => m.owned_by === "openai");
const search = data.filter(m => m.id.includes("claude"));

Rate limits

This endpoint shares the global rate-limit bucket — 60 requests per minute per IP. Responses are CDN-cached for 120 seconds, so repeated calls within that window hit the edge and incur zero origin cost.