List models

GET https://api.entrim.ai/v1/models

Returns a list of models with their input and output limits, pricing, and whether they're scheduled for retirement.

An API key is optional.

• Without an API key, returns all public models at their public list prices.
• With an API key, returns the models available to that key and the prices you'll pay when using it.

Example request

curl https://api.entrim.ai/v1/models \
  -H "Authorization: Bearer $ENTRIM_API_KEY"

With the OpenAI SDK for Python, client.models.list() makes the same call.

Example response

{
  "object": "list",
  "data": [
    {
      "id": "zai-org/GLM-5.3-Flash",
      "object": "model",
      "created": 1677610602,
      "owned_by": "openai",
      "datacenters": [{ "country_code": "SI" }],
      "beta": false,
      "max_input_tokens": 1048576,
      "max_output_tokens": 131072,
      "status": "stable",
      "pricing": {
        "prompt": "0.0000001",
        "completion": "0.00000035",
        "input_cache_read": "0.0000000175",
        "discount": 0.0
      }
    }
  ]
}

The response above is shortened to one model. The live response lists every model available to your key.

Model object

Field	Type	Description
id	string	The model ID to pass as model in requests
object	string	Always model
max_input_tokens	integer	The largest input the model accepts, in tokens
max_output_tokens	integer	The most tokens the model can generate in one response
datacenters	array	The countries the model is served from, as ISO 3166-1 alpha-2 codes in country_code
pricing	object	The price per token in USD, as decimal strings: prompt for input, completion for output, input_cache_read for cached input. With a key, discount is also present and is always 0
beta	boolean	true while the model is in beta
status	string	stable, beta, deprecated (still works, will be retired) or retired (stops working)
retires_at	string, optional	The UTC date (YYYY-MM-DD) from which the model may stop answering. Present once a retirement date is announced

After a model retires, requests using its model ID are either routed to a successor model or rejected with a model-not-found error. If the request is rejected and a replacement is available, the error identifies the replacement model.

Check status and retires_at in the /v1/models response so you can update your integration before the model retires.

created and owned_by are included for compatibility with OpenAI clients and don't describe the model.