Get a model
Retrieve full detail for one of your organization’s models.
user_instruction. That user_instruction is the model’s always-applied
guidance: it is injected as mandatory (“MUST FOLLOW”) direction into every image
and video generation that composes the model — not passive metadata. It contrasts
with default_prompt, an AI-generated capability description that is also appended
at generation. Set or change it via
PATCH /models/{model_id}. Unknown,
other-organization, or deleted ids return
404 not_found. Requires the models.read scope.Authorizations
Organization API key as a bearer token: Authorization: Bearer samsa_sk_....
Path Parameters
Response
Successful Response
A single model with full detail — the GET /models/{id} body (ADR §10).
"Acme Brand Style"
Creation status: pending, processing, completed, or failed.
pending, processing, completed, failed "completed"
True when the model is completed AND active — usable for generation.
true
Model category — one of style, object, person, setting.
style, object, person, setting "style"
Presigned, time-limited HTTPS thumbnail URL (null when the model has none).
"https://cdn.samsa.ai/models/…/thumbnail.webp?X-Amz-Signature=…"
Presigned, time-limited HTTPS URLs of the reference images used to create the model.
Free-text guidance for how to use the model.
"Use for hero banners and social posts."
The model's default prompt / capability description.
"A bold flat-design illustration in the Acme brand palette."
Trigger words associated with the model.

