# Klio Compute vs Google Cloud Run

> Klio Compute and Google Cloud Run side by side: where each is the better choice, features, and GPU prices per hour from Google Cloud Run's own pricing page.

Canonical page: https://klio.tech/compare/klio-vs-google-cloud-run

## In short

Google Cloud Run: Google Cloud's managed platform for running containers, with on-demand NVIDIA GPUs attached to services.

Klio Compute: serverless GPUs for Python. Run a function on a GPU with one decorator, deploy endpoints, task queues, schedules and sandboxes, or put an open model behind an OpenAI-compatible API, and pay per second from prepaid credit.

## Where Google Cloud Run is the better choice

- Any container, inside Google Cloud alongside the rest of your infrastructure.
- Billing rounded up to the nearest 100 milliseconds, and a monthly free tier for CPU and memory.
- On-demand GPUs with no reservation, and zonal redundancy as an option.

## Where Klio Compute differs

- A container can have 1, 2, 4 or 8 GPUs; Cloud Run attaches one per instance.
- More GPU types: H100, A100, L40S, A10 and others as well as L4.
- Python functions with a decorator, without building or deploying a container yourself.
- Prepaid credit: work stops at zero instead of running up an invoice, and a monthly purchase limit caps what can be spent.

## Features

Table: Features: Klio Compute and Google Cloud Run

| Feature | Klio Compute | Google Cloud Run |
| --- | --- | --- |
| Serverless GPU functions or containers | Yes. Functions, endpoints, task queues and schedules on a GPU from one decorator. ([docs](https://klio.tech/docs/gpus.md)) | Yes. Fully managed, on-demand GPUs. ([source](https://docs.cloud.google.com/run/docs/configuring/services/gpu)) |
| Scale to zero | Yes. Endpoints and models stop when idle and start on the next request. ([docs](https://klio.tech/docs/endpoints.md)) | Yes. ([source](https://docs.cloud.google.com/run/docs/configuring/services/gpu)) |
| Billing per second or finer | Yes. Metered per second. ([docs](https://klio.tech/docs/pricing.md)) | Yes. Rounded up to the nearest 100 ms. ([source](https://cloud.google.com/run/pricing)) |
| Several GPUs in one container | Yes. 1, 2, 4 or 8 GPUs of one type; more than one needs a paid workspace. ([docs](https://klio.tech/docs/gpus.md)) | No. One GPU per instance. ([source](https://docs.cloud.google.com/run/docs/configuring/services/gpu)) |
| Sandboxes | Yes. Create, run commands and code, read and write files. ([docs](https://klio.tech/docs/sandboxes.md)) | Not verified. |
| Volumes | Yes. Named volumes mounted into any container. ([docs](https://klio.tech/docs/volumes.md)) | Not verified. |
| OpenAI-compatible model serving | Yes. `klio model deploy`, for the models `klio model list` shows. ([docs](https://klio.tech/docs/models.md)) | Not verified. |
| Runs Modal code with an import change | Yes. `import klio_compute.compat as modal`; a few features are refused with a clear message. ([docs](https://klio.tech/docs/migrate-from-modal.md)) | No. Runs your container image. ([source](https://docs.cloud.google.com/run/docs/configuring/services/gpu)) |
| Prepaid credit | Yes. Top up, set a monthly purchase limit; work stops at zero. ([docs](https://klio.tech/docs/pricing.md)) | Not verified. |

## GPU prices per hour

Public list prices verified 8 November 2026 from [Google Cloud Run's pricing page](https://cloud.google.com/run/pricing). Klio Compute's prices are live, checked Nov 8, 09:00 UTC. GPU prices follow the market and are checked every few minutes. A running container keeps the price it started at.

Table: GPU price per hour: Klio Compute and Google Cloud Run

| GPU | Klio Compute | Google Cloud Run |
| --- | --- | --- |
| H100 80 GB | Not available right now | — — Cloud Run's price list has L4 and RTX PRO 6000 GPUs only. ([source](https://cloud.google.com/run/pricing)) |
| A100 80 GB | $2.49/h | — — Cloud Run's price list has L4 and RTX PRO 6000 GPUs only. ([source](https://cloud.google.com/run/pricing)) |
| L40S 48 GB | Not available right now | — — Cloud Run's price list has L4 and RTX PRO 6000 GPUs only. ([source](https://cloud.google.com/run/pricing)) |
| A10 24 GB | $1.95/h | — — Cloud Run's price list has L4 and RTX PRO 6000 GPUs only. ([source](https://cloud.google.com/run/pricing)) |
| L4 24 GB | $1.45/h | $0.67/h — Listed as NVIDIA L4, non-zonal redundancy, $0.0001867/s. ([source](https://cloud.google.com/run/pricing)) |

Cloud Run lists GPUs per second (L4 without zonal redundancy here); CPU and memory are billed on top.

Prices change; check Google Cloud Run's page before deciding. GPU price only, per GPU-hour; CPU, memory, storage and network may be billed separately, and discounts and committed-use prices aren't shown.

## Sources

Google Cloud Run's pages read on 8 November 2026:

- [https://cloud.google.com/run/pricing](https://cloud.google.com/run/pricing)
- [https://docs.cloud.google.com/run/docs/configuring/services/gpu](https://docs.cloud.google.com/run/docs/configuring/services/gpu)

## About this comparison

Google Cloud Run is a trademark of its owner. Klio Compute is not affiliated with it; names are used only to identify the products compared. "Not verified" means the vendor's pages we read didn't settle it either way. Corrections are welcome at support@klio.tech.