List available models. Runars serves a catalog of models—this endpoint returns the ones your organization can access. It also provides compatibility with OpenAI SDK's .models.list() method.

Endpoint

GET https://api.runars.ca/v1/models

Authentication

Include your API key as a Bearer token:

-H "Authorization: Bearer sk-runars-..."

Note: Unlike some OpenAI APIs, this endpoint requires authentication. Invalid or missing keys return 401 Unauthorized.

Response

{
  "object": "list",
  "data": [
    {
      "id": "glm-5.2",
      "object": "model",
      "owned_by": "runars",
      "permission": []
    }
  ]
}

The response includes one entry per enabled model in your catalog. Requesting a model id that isn't in this list returns 404 model_not_found—unknown ids are never silently substituted.

Examples

Using curl

curl https://api.runars.ca/v1/models \
  -H "Authorization: Bearer sk-runars-..."

Using the OpenAI SDK

import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://api.runars.ca/v1",
  apiKey: process.env.OPENAI_API_KEY,
})

const models = await openai.models.list()
console.log(models.data)

Output:

[
  {
    id: 'glm-5.2',
    object: 'model',
    owned_by: 'runars',
    permission: []
  }
]

Programmatically checking model availability

const models = await openai.models.list()
const runarsAvailable = models.data.some((m) => m.id === "glm-5.2")
console.log(`GLM-5.2 available: ${runarsAvailable}`)

Error responses

401 Unauthorized

Invalid or missing API key:

{
  "error": {
    "message": "Unauthorized",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Returned by /v1/messages, /v1/chat/completions, and /v1/responses when the requested model id isn't in the catalog. Requesting an unknown model never substitutes a default—the caller must send a valid id from GET /v1/models.

Model details

The glm-5.2 model is:

744B-parameter Mixture-of-Experts model
131,072-token context window
Served from our Canadian GPU Cloud in Montreal & Calgary (Canadian data residency)
Pricing: $1.00/1M input tokens, $4.00/1M output tokens (see Pricing or browse all Models)

Additional models may be added to your catalog over time—this endpoint always reflects the current set. For more information, see the Overview.

GET /v1/models