Estimate on-demand model resource cost

Estimates a model resource's on-demand hourly price without creating it.

Authorization

bearerAuth

AuthorizationBearer <token>

In: header

application/json

Request to provision a standalone model resource

base_model*string

Base model to provision the resource for, selected from /rl/supported-models

base_weights_ref?string

Model in this project's model registry whose weights the resource trains in place of the base model's own. It must be a full-weight model.

Match^together://ml_[A-Za-z0-9]+(@rv_[A-Za-z0-9]+)?$

Lengthlength <= 256

compute_config?

Compute layout to provision.

lora_enabled?boolean

Whether the resource hosts LoRA sessions or a single full-weight session

Defaulttrue

optimizer_config?

Optimizer configuration for this resource.

curl -X POST "https://example.com/rl/model-resources/estimate-cost" \  -H "Content-Type: application/json" \  -d '{    "base_model": "string"  }'

{  "price_per_hour": 0.1,  "currency": "string"}