Models Endpoint

The gateway exposes an OpenAI-compatible GET /v1/models endpoint that returns the list of models available through your CoreValue account. This lets you use the standard OpenAI SDK's models.list() method to discover available models.

Authentication

The endpoint requires authentication. Provide your CoreValue API key as a Bearer token:

Authorization: Bearer $COVA_API_KEY

Requests are IP rate-limited before authentication and org rate-limited after authentication succeeds.

Behavior

Aspect	Detail
Format	OpenAI-compatible `{"object": "list", "data": [...]}`
Filtering	Server-side filter by `requireExplicitRouting` — models that require explicit routing are excluded. There is no client-side bypass.
Caching	In-memory cache for 60 seconds
Auth	Required (Bearer token or `api-key` header)

The model list is filtered server-side based on requireExplicitRouting. Models flagged as requiring explicit routing are omitted from the response. This filtering cannot be bypassed by the client.

Example

cURL

curl https://gateway.corevalue.dev/v1/models \
  -H "Authorization: Bearer $COVA_API_KEY"

SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.COVA_API_KEY,
  baseURL: "https://gateway.corevalue.dev/v1",
});

const models = await client.models.list();

for (const model of models.data) {
  console.log(model.id);
}

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["COVA_API_KEY"],
    base_url="https://gateway.corevalue.dev/v1",
)

models = client.models.list()

for model in models.data:
    print(model.id)

Sample Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1715367049,
      "owned_by": "openai"
    },
    {
      "id": "groq/llama-3.1-70b-versatile",
      "object": "model",
      "created": 1715367049,
      "owned_by": "groq"
    }
  ]
}

Provider Routing

The 18 model prefixes and routing behavior

Gateway Overview

All six gateway routes