Examples
Apps you can deploy as they are, each one the shortest way to learn a thing the others do not teach.
Introduction
Every example here is a working app rather than an excerpt. The code on each page is read from the file that is deployed and tested, so what you copy is what runs.
Each one earns its place by teaching something the others do not.
They live in runware-serverless-examples, where each one carries its own README with the deploy command and a call for every endpoint.
Your first app
The smallest app that runs: two endpoints, no weights, no GPU work. Deploy it to check the platform end to end.
Two endpoints in one app
Put two endpoints with different request shapes in one app, and learn where the GPU choice actually lives.
Typed requests and responses
Describe your API with Pydantic models so callers see every field, and so defaults reach your handler instead of nulls.
Taking an image as input
Accept an image and return one, using the annotations that decode base64 into pixels before your handler runs.
Running a model with weights
Load a real model on a GPU: where the imports go, how to declare dependencies, and why weights belong on a volume.
Generating an image and removing its background
Run two models in one request so the image between them never leaves the worker, which no managed API can do.
Running a language model
Serve chat completions from your own weights, with a request shape you define, and see where it stops scaling.
Using more than one GPU
Run a worker across several cards, where every rank executes your handler and only the first one answers.
Secrets and environment variables
Read configuration and credentials on a worker, and see what the platform will and will not give you back.