---
title: Examples | Runware Docs
url: https://runware.ai/docs/serverless/examples
description: Apps you can deploy as they are, each one the shortest way to learn a thing the others do not teach.
relatedDocuments:
  - https://runware.ai/docs/serverless/writing-a-model
  - https://runware.ai/docs/serverless/quickstart
---
## 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`](https://github.com/Runware/runware-serverless-examples), where **each one has its own README** with the deploy command and a call for every endpoint.

All

Getting started

Endpoints and routing

Requests and responses

Models and weights

Long-running work

Containers

Hardware and scale

Configuration and credentials

- [![](https://runware.ai/docs/assets/cover.epRCigc8_ZGKBQj.webp)
    
    ### Your first app
    
    The smallest app that runs: two endpoints, no weights, no GPU work. Deploy it to check the platform end to end.
    
    ](https://runware.ai/docs/serverless/examples/echo)
- [![](https://runware.ai/docs/assets/cover.CvM174oj_1gWEgR.webp)
    
    ### Two endpoints in one app
    
    Put two endpoints with different request shapes in one app, and learn where the GPU choice lives.
    
    ](https://runware.ai/docs/serverless/examples/image-tools)
- [![](https://runware.ai/docs/assets/cover.DB8bbfGd_Z2f8RLF.webp)
    
    ### Typed requests and responses
    
    Describe your API with Pydantic models so callers see every field, and so defaults reach your handler instead of nulls.
    
    ](https://runware.ai/docs/serverless/examples/typed-endpoints)
- [![](https://runware.ai/docs/assets/cover.ewMaqzQ-_1250au.webp)
    
    ### Taking an image as input
    
    Accept an image and return one, using the annotations that decode base64 into pixels before your handler runs.
    
    ](https://runware.ai/docs/serverless/examples/watermark)
- [![](https://runware.ai/docs/assets/cover.DuI-Ro3o_2hfabI.webp)
    
    ### Embeddings
    
    Embed many texts in one request, and batch them inside your handler because the platform will not do it for you.
    
    ](https://runware.ai/docs/serverless/examples/embeddings)
- [![](https://runware.ai/docs/assets/cover.hTdvMRU4_Wzu.webp)
    
    ### 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.
    
    ](https://runware.ai/docs/serverless/examples/loading-weights)
- [![](https://runware.ai/docs/assets/cover.B2cRPSCh_pMce9.webp)
    
    ### Compiling a model
    
    Put the compiler's own cache on the volume, so only the first worker pays the compile cost.
    
    ](https://runware.ai/docs/serverless/examples/compiled-model)
- [![](https://runware.ai/docs/assets/cover.nmHtpJjE_AMINM.webp)
    
    ### 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.
    
    ](https://runware.ai/docs/serverless/examples/chained-steps)
- [![](https://runware.ai/docs/assets/cover.Dfq2dOAU_ZywKav.webp)
    
    ### Running a language model
    
    Serve chat completions from your own weights, with a request shape you define, and see where it stops scaling.
    
    ](https://runware.ai/docs/serverless/examples/chat-endpoint)
- [![](https://runware.ai/docs/assets/cover.Bsf1PvIb_ZP5sGK.webp)
    
    ### Folding a protein
    
    Fold a sequence into a structure file, with the weights pinned to a revision so every worker loads the same ones.
    
    ](https://runware.ai/docs/serverless/examples/protein-folding)
- [![](https://runware.ai/docs/assets/cover.CsMq0kEx_1GnPgW.webp)
    
    ### Resuming a long job
    
    Checkpoint to storage every worker can reach, so the next call picks the job up where the last one left it.
    
    ](https://runware.ai/docs/serverless/examples/resumable-job)
- [![](https://runware.ai/docs/assets/cover.CyEZSZaQ_2fSIUk.webp)
    
    ### Running your own container
    
    Deploy a vLLM image as it ships, and declare the port, the probes and the routes your server already answers.
    
    ](https://runware.ai/docs/serverless/examples/container-server)
- [![](https://runware.ai/docs/assets/cover.B0KuyoXv_ZDeMa8.webp)
    
    ### Rendering 3D frames
    
    Run Blender in a container, with the system packages it needs and a request timeout only a container app can set.
    
    ](https://runware.ai/docs/serverless/examples/render-farm)
- [![](https://runware.ai/docs/assets/cover.BJgGe0Y7_ZO11t9.webp)
    
    ### Using more than one GPU
    
    Run a worker across several cards, where every rank executes your handler and only the first one responds.
    
    ](https://runware.ai/docs/serverless/examples/multi-gpu)
- [![](https://runware.ai/docs/assets/cover.BDtPF6NH_Zml3AJ.webp)
    
    ### Secrets and environment variables
    
    Read configuration and credentials on a worker, and see what the platform will and will not give you back.
    
    ](https://runware.ai/docs/serverless/examples/config-and-secrets)