Deploy model to Ray object store

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

This operation:

1. Downloads the model archive from S3
2. Deserializes weights based on format (safetensors, pytorch, etc.)
3. 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 /v1/namespaces/{namespace_id}/models/{model_id}/deploy

Deploy model to Ray object store

cURL

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

200

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

Authorizations

Authorization · string · header · required

Mixpeek API key, sent as Authorization: Bearer mxp_sk_.... Create one in Studio under Settings → API Keys, or with an admin key via POST /v1/organizations/users/{user_email}/api-keys. A missing header returns 403; an invalid or revoked key returns 401.

Path Parameters

namespace_id · string · required

model_id · string · required

Response

200

application/json

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