compute

Serverless Compute

Serverless GPU

Serverless GPU is a serverless compute capability available through Replicate, RunPod, Apify and 1 more on Aweb. On-demand GPU compute for ML inference. Access it through a single unified API with automatic failover and intelligent routing.

Try Serverless GPUAPI docs

Best for

Highest quality

RunPod, Apify

Premium tier

Most affordable

RunPod

Economy tier

Contract

Max Latency60000ms

Providers (4)

ProviderScoreQualityPricing
Replicate
75standardstandard
RunPodDEFAULT
85premiumeconomy
Apify
80premiumstandard
Cloudflare Workers
80premiumstandard

Public discovery and orchestration

Inspect the live capability descriptor directly, then route orchestration through a capability filter. Generic public execute examples are intentionally withheld until the canonical public execute contract is normalized.

cURL

curl "https://aweblabs.ai/api/v2/capabilities/compute.serverless"

TypeScript

import Aweb from '@aweb/sdk';

const client = new Aweb({
  baseUrl: 'https://aweblabs.ai/api/v2',
});

const capability = await client.capabilities.get('compute.serverless');

console.log(capability.data.runtime.providers);

Orchestration pipeline

import Aweb from '@aweb/sdk';

const aweb = new Aweb({ apiKey: process.env.AWEB_API_KEY });

const result = await aweb.orchestrate.run({
  query: 'Use Serverless GPU to help with a hello-world task and summarize the output',
  capabilities: ['compute.serverless'],
  policy: 'balanced',
});

console.log(result.data.status);

Related Serverless Compute capabilities

Code Sandbox

compute

Code Execution

compute

Synthetic Data Generation

compute

Data Anonymization

compute

Cloud Browser

compute

Getting started →API reference →All providers →All capabilities →