Skip to content
OpenRelay is in early access, and the /v1 API is stable. New capabilities ship in the changelog.
Skip to Content
PricingDashboard
GuidesAPI ReferenceCLI
API ReferenceInferenceModel Imports

Import model weights

Copies a model's weights from Hugging Face, S3 or Google Cloud Storage into OpenRelay and checks them, to serve on a dedicated endpoint. Name a credential for a private source. attestRights must be true: you attest you have the rights to the weights, under the license you name. The import runs in the background; poll it until it succeeds or fails. Your organization runs a limited number of imports at once (409 IMPORT_LIMIT names it), and a create passes the same balance and account checks as a VM create.

Required permission

Requires the import.create permission. See Permissions for the roles and API key permissions that include it.

Command line

The orl CLI wraps this endpoint:

orl imports create --attest-rights --source <source>
POST
/v1/inference/imports

Authorization

apiKey
headerAuthorizationBearer <token>

OpenRelay API key. Send it as Authorization: Bearer or_… (legacy vl_… keys still work).

Request Body

application/json
  1. body

A customer's model import.

source*
license?string

The license the weights are under.

attestRights*boolean

Must be true: you attest you have the rights to import and serve the weights under that license.

Response Body

Started

application/json
  1. response
id*string
orgId*string
artifactId*string

The artifact the import produces, pending until it succeeds.

status*string
Value in"queued""copying""validating""succeeded""failed"
source*
attempt*integer

Importer tasks started for this import.

progress*
failure?
artifact?
createdAt*string
Formatdate-time
updatedAt*string
Formatdate-time
Example Request
curl -X POST 'https://api.openrelay.inc/v1/inference/imports' \  -H 'Content-Type: application/json' \  -d '{  "source": {    "uri": "string"  },  "attestRights": true}'
Example Response
{  "id": "string",  "orgId": "string",  "artifactId": "string",  "status": "queued",  "source": {    "uri": "string",    "revision": "string",    "pinnedRevision": "string",    "credentialId": "string"  },  "attempt": 0,  "progress": {    "filesDone": 0,    "filesTotal": 0,    "bytesDone": 0,    "bytesTotal": 0  },  "failure": {    "code": "string",    "message": "string"  },  "artifact": {    "id": "string",    "importId": "string",    "status": "pending",    "weightsRef": "string",    "digest": "string",    "format": "string",    "architecture": "string",    "dtype": "string",    "quantization": "string",    "paramCount": 0,    "bytes": 0,    "files": 0,    "compat": {      "evaluatedAt": "2019-08-24T14:15:22Z",      "policyId": "string",      "policyVersion": 0,      "fits": [        "string"      ],      "refusals": {        "property1": "string",        "property2": "string"      }    }  },  "createdAt": "2019-08-24T14:15:22Z",  "updatedAt": "2019-08-24T14:15:22Z"}

List your organization's model imports GET

Every model import of your organization, running or ended, each with its status, progress, source and the artifact it produces. Read the artifact for its facts and the hardware it fits. Imports are listed by id, not by when they started.

Get a model import GET

One of your organization's model imports: its status, progress, the revision it pinned, and why it failed, with the artifact it produces. Another organization's import reads as not found.