List Models

List models exposed by the hosted service. Use a returned id as the model field in inference requests.

Text

GET /v1/models

Base URLs and authentication. The free API requires no key; add Authorization: Bearer $VALEN_API_KEY when using the keyed endpoint.

Quick request

No request body is needed. Install requests in the client environment to run the Python example.

Python

Python

import requests

response = requests.get(
    "https://api.valen-team.workers.dev/v1/models",
    timeout=30,
)
response.raise_for_status()
models = response.json()["data"]
print([model["id"] for model in models if model["id"].startswith("valen-")])

cURL

Bash

curl --fail-with-body https://api.valen-team.workers.dev/v1/models

Response

Successful requests return HTTP 200. This example shows one model from the list:

JSON

{
  "object": "list",
  "data": [
    {
      "id": "valen-2b",
      "object": "model",
      "created": 1792745074
    }
  ]
}

Field	Type	Description
object	string	List type: list.
data	object[]	Model list.
data[].id	string	Model identifier to use in the request's model field.
data[].object	string	Entry type: model.
data[].created	integer	Upstream creation time as a Unix timestamp in seconds.

Read model names from data[].id, such as valen-0.8b, valen-2b, and valen-4b.

Use a model

Set the model field in a System One or Decisions request to your chosen Valen model ID, such as "model": "valen-2b".