Sign in

v1

latestSwagger 2.02026-08-04232286653.5 KB
Foundry

Returns a single self-serve deployment in the project.

get/projects/{project_id}/foundry/selfserve/deployments/{id}

Path parameters

project_idstring required

ID of the project.

idstring required

ID of the deployment.

Response

available_replicasinteger

Currently available replicas.

context_lengthinteger

Context length of the model.

created_atstring

RFC 3339 creation timestamp.

created_bystring

Identity that created the deployment.

deployment_namestring

User-chosen deployment name.

fine_tuned_modelstring

The fine-tuned model being served.

flavor_typestring

Flavor type in use.

gpu_typestring

GPU type in use.

gpus_per_replicainteger

GPUs per replica.

hourly_coststring

Hourly cost, as a decimal string.

idstring

Deployment ID.

modelstring

The underlying model.

providerstring

Serving provider.

quantizationstring

Quantization applied, if any.

statusstring

Deployment status.

target_replicasinteger

Target replica count.