---
title: "Get model details"
method: GET
path: "/models/{model_id}"
tags: ["models"]
---

# Get model details

`GET /models/{model_id}`

Get detailed information about a specific custom model. The user must either own the model or the model must be shared with the user's organization via the model registry. Returns 404 if the model is not found or not accessible.

## Path parameters

- `model_id` string, required

## Response `200`

Model retrieved successfully

- GetModelResponse
  - `model` CustomModel, required — A custom model.
    - `model_id` string, required — Unique identifier for the model (base64 URL-safe encoded UUID).
    - `custom_model_uri` string, nullable — A custom model URI in the format model/<model_name>/version/<version_name>. Use this URI when generating images with this model. Only present for models that have been registered in the model registry.
    - `name` string, required — Display name of the model.
    - `status` 'CREATING' | 'DRAFT' | 'TRAINING' | 'COMPLETED' | 'ERRORED' | 'ARCHIVED', required — The status of a custom model.
    - `dataset_id` string, nullable — ID of the dataset (collection) the model was trained from.
    - `creation_time` string, date-time, required — When the model was created.
    - `last_update_time` string, date-time, nullable — When the model was last updated.
    - `is_available_for_generation` boolean, required — Whether the model is available for image generation.
    - `is_owned` boolean, required — Whether the authenticated user owns this model.
    - `training_runs` TrainingRun[] — Training run history. Only populated on the get-by-ID endpoint and only for owned models.
      - `training_run_id` string, required — Unique identifier for the training run.
      - `status` 'PREPARING_DATA' | 'QUEUED' | 'TRAINING' | 'FINALIZING' | 'COMPLETED' | 'FAILED', required — The status of a training run.
      - `training_steps` integer, nullable — Number of training steps configured.
      - `lora_rank` integer, nullable — LoRA rank used for training.
      - `num_chips` integer, nullable — Number of TPU chips used.
      - `ema` number, nullable — Exponential moving average decay rate.
      - `learning_rate` number, nullable — Learning rate for the optimizer.
      - `creation_time` string, date-time, required — When the training run was created.
      - `last_update_time` string, date-time, nullable — When the training run was last updated.

## Other responses

- `401` — Unauthorized
- `404` — Model not found

---

[API](https://skmtc.net/ideogram/apis/ideogram-openapi-3-0.md) · [All operations](https://skmtc.net/ideogram/apis/ideogram-openapi-3-0/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/ideogram/ideogram-openapi-3-0/revisions/bd40f367a834/schema)