Deploy model to Ray object store

curl --request POST \
  --url https://api.mixpeek.com/v1/namespaces/{namespace_id}/models/{model_id}/deploy \
  --header 'Authorization: Bearer <token>'

{
  "success": true,
  "model_id": "<string>",
  "namespace_id": "<string>",
  "deployment_status": "<string>",
  "message": "<string>",
  "cached": false
}

Models

Deploy model to Ray object store

Pre-load model weights into the Ray object store for fast access by plugins.

This operation:

Downloads the model archive from S3
Deserializes weights based on format (safetensors, pytorch, etc.)
Stores weights in Ray object store for zero-copy sharing

After deployment, plugins can load the model instantly using:

from engine.models.loader import load_namespace_model
weights = load_namespace_model("model_id")

Note: This is optional - models are also loaded on-demand when plugins first request them. Use this endpoint to pre-warm the cache.

POST

namespaces

{namespace_id}

models

{model_id}

deploy

Deploy model to Ray object store

curl --request POST \
  --url https://api.mixpeek.com/v1/namespaces/{namespace_id}/models/{model_id}/deploy \
  --header 'Authorization: Bearer <token>'

{
  "success": true,
  "model_id": "<string>",
  "namespace_id": "<string>",
  "deployment_status": "<string>",
  "message": "<string>",
  "cached": false
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

namespace_id

string

required

model_id

string

required

Response

Successful Response

Response model for model deployment.

Deploying a model pre-loads the weights into the Ray object store, making them available for zero-copy access by plugins.

success

boolean

required

Whether deployment succeeded

model_id

string

required

Model identifier

namespace_id

string

required

Namespace ID

deployment_status

string

required

Deployment status (deployed, failed)

message

string

required

Status message

cached

boolean

default:false

Whether model is cached in object store

Get model details Enable org model for namespace