---
title: "Run a GPU job and keep the result"
description: "Declare a pinned target with a price and timeout, start a job, watch its progress, cancel it, and read the result from files."
section: "guides"
status: "Building for 0.6"
spec: "compute"
canonical: "https://mainsdk.dev/docs/guides/run-gpu-jobs"
updated: "2026-10-28"
---

# Run a GPU job and keep the result

> Declare a pinned target with a price and timeout, start a job, watch its progress, cancel it, and read the result from files.

Status: Building for 0.6 · Canonical: https://mainsdk.dev/docs/guides/run-gpu-jobs · Updated: 2026-10-28

You will upscale an image on your own Replicate account without holding a request open, with a cost limit, and store the result in files. It takes about 20 minutes.

## You need

- A MainSDK app with `files` set up (see [file uploads](https://mainsdk.dev/docs/guides/file-uploads)).
- A Replicate API token in `secret:REPLICATE_API_TOKEN`, and a webhook secret in `secret:REPLICATE_WEBHOOK_SECRET`.

## 1. Declare the target

```yaml title="main.yaml"
compute:
  poll: 15s
  limits: { per-tenant: $50/month }
  targets:
    upscale:
      driver: replicate
      model: nightmareai/real-esrgan:f121d640bd286e1fdc67f9799164c1d5be36ff74576ee11c803ae5b665dd46aa
      region: us
      timeout: 30m
      price: $0.0014/s
      max-cost: $2
```

A target with no price or timeout, a timeout over 24 hours, or no version hash stops `mainsdk check`. Use the `local` driver with a `program` in tests; it runs through `system.run`.

## 2. Start a job

```ts title="app/photos/upscale.ts"
import { compute, type ComputeRunOptions } from "mainsdk/experimental/compute";

type StoredFile = NonNullable<ComputeRunOptions["files"]>[number];   // a file stored with `files`

export async function upscale(image: StoredFile) {
  const { jobId } = await compute.run("upscale", { scale: 4 }, { files: [image] });
  return jobId;
}
```

The job is `queued` when the call returns. If price times timeout could pass `maxCost`, the call is refused first with `MAIN-COMPUTE-0002` and nothing is sent.

## 3. Watch, cancel and read

```ts
import { compute } from "mainsdk/experimental/compute";

declare const jobId: string;

const job = await compute.get(jobId); // state, progress, cost, result
await compute.cancel(jobId, { reason: "user changed their mind" });
```

Progress is also published on the realtime channel `compute:<jobId>`. A job with no sign of life for three heartbeats becomes `lost` and is cancelled at the provider.

## 4. Use it inside a workflow

```ts
import { compute } from "mainsdk/experimental/compute";

const result = await compute.step("upscale-step", "upscale", { scale: 4 });
```

The step waits for the job and returns its result, and the workflow survives a restart in between.

## Test it

Use `FakeComputeProvider` and `ParkingFlows` from `mainsdk/testing` to run a job without a provider account, and `computeConformance` to check a driver of your own.