Skip to content
ACS Infra
Models

Retrieve Model

GET
/v1/models/{model_id}

Return one model of GET /v1/models, as OpenAI's retrieve does. It asks no Inference.

Authorization

bearer
headerAuthorizationBearer <token>

An API key: Authorization: Bearer sk-acs-..., or a key of the old platform, acs-bm-.... A User makes and revokes keys in the App.

Path Parameters

model_id*string

The Model id from GET /v1/models, such as llama-8b, or its served_model_name, with its slash as it is or as %2F.

Response Body

Model

application/json
  1. response
id*string

The Model id to send as model, such as llama-8b.

object*"model"
Value in"model"
owned_by*"acs"
Value in"acs"
served_model_name*string

The Checkpoint that Inference serves, which each answer's model names.

gpu_shape*string

GPUs and their type, such as 1xL40S or 8xH200.

status*"live"
Value in"live"
default*boolean

A request without model runs on this model.

capabilities*
Example Request
curl -X GET 'https://api.v2.infra.acsresearch.org/v1/models/string' \  -H 'Authorization: Bearer <API_KEY>'
Example Response
{  "id": "string",  "object": "model",  "owned_by": "acs",  "served_model_name": "string",  "gpu_shape": "string",  "status": "live",  "default": true,  "capabilities": {    "max_model_len": 0,    "max_logprobs": 0,    "max_output_work_tokens": 0,    "max_inflight_per_key": 0,    "max_queued_per_key": 0,    "rate_limit_per_minute": 0,    "logprobs": true,    "prompt_logprobs": true,    "prompt_logprobs_full_vocab": true,    "full_vocab_max_prompt_tokens": 0,    "activations": true,    "max_steering_vectors": 0,    "max_activation_prompt_tokens": 0,    "n_layers": 0,    "hidden_size": 0,    "chat_template": null  }}

List Models GET

List the Base models that the API serves, each with its Model id, the Checkpoint it serves, its GPUs, and its capabilities: its context length, Layers, hidden size, and the limits of a request to it. `default` marks the model of a request without `model`. The API lists them from its settings and asks no Inference, so a list never starts a GPU.

Get Model Status GET

Say whether the model's next request most likely starts at once (`warm`), or which stage its start has reached (`boot`). The API answers from what it saw and asks no Inference, so the route never starts a GPU.