Get a model
Returns one model. Public models are readable by any authenticated caller. A private model
is readable by members of the owning account and by accounts the owner granted access.
Any other caller gets 403, whether or not the model exists.
The full view goes to an account_admin or developer of the owning account. Every other
reader gets the public view: id, name, account, description, status,
is_public, created_at, and updated_at.
Authorizations
A Reactor API key (rk_...), sent as Authorization: Bearer rk_.... Keep it on a server.
Path Parameters
The model's ID (not its project ID). Find it with GET /models?name=your-org/your-model.
Response
The model.
- Option 1
- Option 2
The full view of a model, for its owner.
"your-org/your-model"
The model's status, always lowercase in responses.
active, deprecated, disabled When it was created, as an RFC 3339 timestamp.
"2026-01-15T10:30:00Z"
When it was last updated, as an RFC 3339 timestamp.
"2026-01-15T10:30:00Z"
The owning account.
The owning account's name.
"NVIDIA_H100"
"4"
"32Gi"
Makes the model multi-session: each instance runs one model server, which holds the model
and the GPUs, plus count workers, each serving one session. The model's own gpu_*,
cpu_*, and memory_* fields apply to the model server. Omit workers for one session
per instance. The CLI sends this from model.resources.workers in reactor.yaml.
For a model with workers: the CPU and memory of one whole instance, with defaults
filled in. This is what your account's per-model quotas are checked against.
The model's project. Only on GET /models/{id}.