List the AI models an agent step can use

GET /automation/models

Requires `automation:create` or `automation:manage`. Every model the organization stored, on every provider, the same rows the AI models settings list: `ref` (`<provider>:<id>`) is what an agent step's `model` takes, and `can_run` with `blocked_reason` (`no_key`, `key_rejected`, `no_tools`) and `blocked_message` says whether it can run now. Leave `model` out of a step to follow the organization default (`default_model_ref`, a ref, or '' when there is none; `default_model` is its bare id). Filtered by `q` on the server. `can_manage` says whether the caller may change the models in settings.

Query Parameters

qstring

Matches the model label, id or provider. LIKE wildcards are matched literally. Max 200 characters.

Response Body

can_manageboolean

context_windowinteger

default_modelstring

The organization default's own model id, without its provider; '' when no model can run.

default_model_labelstring,null

default_model_refstring

The organization default as a ref (<provider>:<id>); '' when no model can run.

next_cursorstring,null

prev_cursorstring,null

resultobject[]

blocked_messagestring,null

blocked_reasonstring,null

Possible values:

no_keykey_rejectedno_toolsnull

can_runboolean

context_windowinteger

defaultboolean

idstring

labelstring

providerstring

provider_labelstring

refstring

sourcestring

Possible values:

enabledcustom

supports_toolsboolean

curl -X GET 'https://api.elaichi.ai/automation/models' \
  -H 'Authorization: Bearer $ELAICHI_API_TOKEN' \
  -H 'Content-Type: application/json'

const response = await fetch('https://api.elaichi.ai/automation/models', {
  method: 'GET',
  headers: {
    'Authorization': 'Bearer ' + process.env.ELAICHI_API_TOKEN,
    'Content-Type': 'application/json',
  },
});

const data = await response.json();
console.log(data);

import os
import requests

url = "https://api.elaichi.ai/automation/models"
headers = {
    "Authorization": f"Bearer {os.environ['ELAICHI_API_TOKEN']}",
    "Content-Type": "application/json",
}

response = requests.get(url, headers=headers)
print(response.json())