Skip to main content
POST
Create dedicated endpoint

Authorizations

Authorization
string
header
required

Your workspace API key, e.g. sk_sovereign_..., sent as Authorization: Bearer <key>.

Body

application/json

This body is camelCase, unlike the snake_case loop endpoints. The service validates the model/flavor/GPU/region combo against the deploy templates, prices it, and requires prepaid balance for the first hour.

name
string
required
modelName
string
required

A template name from GET /v1/dedicated/templates.

flavorName
string
required

A flavor of that template.

gpuType
string
required
gpuCount
integer
required
region
string
required
minReplicas
integer
required

At least 1.

maxReplicas
integer
required

At least minReplicas.

description
string
customWeightsId
string

Serve a fine-tuned model's weights by artifact id (used when deploying a trained model).

fineTuningJobId
string

The source fine-tuning job id, when deploying a model trained on this platform.

Response

The created endpoint.

id
string
name
string
description
string | null
model_name
string
flavor_name
string
gpu_type
string
gpu_count
integer
region
string
min_replicas
integer
max_replicas
integer
status
enum<string>

Live-reconciled from the control plane on every list/get.

Available options:
STARTING,
UPDATING,
RUNNING,
STOPPING,
STOPPED,
DELETED,
WARNING
enabled
boolean

Whether the endpoint is started. Billing runs only while RUNNING and enabled.

hourly_rate_usd
number

Your price per GPU-hour for this configuration (rate frozen at deploy).

markup_bps
integer
pending_cost_usd
number

Cost accrued since the last metering sweep, at the frozen rate.

routing_key
string | null

Call the endpoint through the gateway as model "dedicated/<routing_key>".

base_url
string

The inference base URL to point your client at.

last_metered_at
string
created_at
string