---
title: "Live pod GPU capacity and per-class rates"
method: GET
path: "/v1/pods/capacity"
tags: ["Pods"]
---

# Live pod GPU capacity and per-class rates

`GET /v1/pods/capacity`

What a pod create can actually claim right now, per GPU model: free native (device-request) GPU units on online, non-delisted nodes (the exact filter admission uses), plus the SERVER-computed hourly rate per compute class (interruptible is discounted below the on-demand/reserved rate). Only models with pod units and a price are returned; a create flow should offer exactly these and render these rates verbatim rather than re-deriving prices from the catalog.

## Response `200`

Capacity per GPU model, cheapest first

- object
  - `items` PodCapacityItem[], required
    - `freeUnits` integer, required — GPU units claimable right now (each pod takes one whole GPU)
    - `gpuModelId` string, required
    - `name` string, required
    - `rateInterruptibleCentsPerHour` integer, required — discounted interruptible rate, cents per GPU-hour
    - `rateReservedCentsPerHour` integer, required — on-demand (reserved) rate, cents per GPU-hour
    - `totalUnits` integer, required — all pod units on online nodes, including ones currently claimed
    - `vramGb` integer, required

## Other responses

- `401` — Missing or invalid API key
- `403` — API key lacks the required scope

---

[API](https://skmtc.net/openrelay/apis/openrelay-api.md) · [All operations](https://skmtc.net/openrelay/apis/openrelay-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/openrelay/openrelay-api/versions/32905b8f44f8/schema)