Skip to main content

Scaleway Inference

@sntxrr/scaleway-inferencev2026.07.19.1· 6d agoMODELS
01README

Manage a Scaleway Managed Inference deployment — sync state, create, update, and delete dedicated model serving deployments, and discover deployments in a region, via the Managed Inference API with X-Auth-Token auth.

02Models1
@sntxrr/scaleway-inferencev2026.07.19.1scaleway_inference.ts

Global Arguments

ArgumentTypeDescription
secretKeystringScaleway API secret key. Wire with ${{ vault.get(scaleway, SCW_SECRET_KEY) }}.
projectIdstringScaleway Project ID that owns the inference deployment.
regionstringRegion, e.g. fr-par, nl-ams, pl-waw.
deploymentId?stringID of the Managed Inference deployment this model manages. Optional —
endpoint?stringOverride the API host. Defaults to https://api.scaleway.com.
fn sync()
Fetch the deployment's current state (GetDeployment).
fn create(name: string, modelId: string, nodeType: string, acceptEula: boolean, minSize?: number, maxSize?: number, tags?: array, publicEndpoint: boolean, privateNetworkId?: string, disableAuth: boolean, quantizationBits?: number)
Provision a new inference deployment (CreateDeployment) and snapshot it.
ArgumentTypeDescription
namestringName of the new inference deployment.
modelIdstringUUID of the model to deploy (see the Managed Inference model catalog).
nodeTypestringName of the node type to use, e.g. L4, H100, H100-2 (sent as node_type_name).
acceptEulabooleanAccept the model's End User License Agreement (EULA) if it requires one.
minSize?numberMinimum size of the serving pool. Optional; API default applies.
maxSize?numberMaximum size of the serving pool. Currently must equal minSize (no autoscaling).
tags?arrayTags to attach to the new deployment.
publicEndpointbooleanCreate a public endpoint for the deployment.
privateNetworkId?stringIf set, also create a private endpoint attached to this Private Network ID.
disableAuthbooleanDisable IAM authentication on the created endpoint(s). Defaults to protected.
quantizationBits?numberIf set, quantize each model parameter to this many bits.
fn update(name?: string, tags?: array, minSize?: number, maxSize?: number, modelId?: string, quantizationBits?: number)
Mutate an inference deployment's mutable fields (UpdateDeployment).
ArgumentTypeDescription
name?stringNew name for the deployment.
tags?arrayReplacement set of tags for the deployment.
minSize?numberNew minimum size of the serving pool.
maxSize?numberNew maximum size of the serving pool. Currently must equal minSize.
modelId?stringUUID of a new model to set on the deployment.
quantizationBits?numberNew quantization: number of bits per model parameter.
fn delete()
Deprovision the inference deployment (DeleteDeployment).
fn list()
Discover all inference deployments in the region (factory).

Resources

deployment(infinite)— Snapshot of the Managed Inference deployment's state
03Previous Versions1
2026.07.18.1
04Stats
A
100 / 100
Downloads
0
Archive size
12.4 KB
  • Has README or module doc2/2earned
  • README has a code example1/1earned
  • README is substantive1/1earned
  • Most symbols documented1/1earned
  • No slow types (deprecated)1/1earned
  • Dependencies pass trust audit2/2earned
  • Has description1/1earned
  • Platform support declared (or universal)2/2earned
  • License declared1/1earned
  • Verified public repository2/2earned
05Platforms
06Labels