# Modal Documentation

- **URL:** https://modal.com/docs
- **Summary:** AI infrastructure that developers love.

Modal Documentation
===================

Modal provides a serverless cloud for engineers and researchers who want to build compute-intensive applications without thinking about infrastructure.  
  
Run generative AI models, large-scale batch workflows, job queues, and more, all faster than ever before.

[Get Started](https://modal.com/docs/guide)

![Modal container](https://modal-cdn.com/marketing-website-assets/docs.png)

[Guide\
\
Everything you need to know to run code on Modal. Dive deep into all of our features and best practices.](https://modal.com/docs/guide)
[Examples\
\
Powerful applications built with Modal. Explore guided starting points for your use case.](https://modal.com/docs/examples)
[Reference\
\
Technical information about the Modal API. Quickly refer to basic descriptions of various programming functionalities.](https://modal.com/docs/sdk/py/latest)
[Playground\
\
Interactive tutorials to learn how to start using Modal. Run serverless cloud functions from your browser.](https://modal.com/playground/get_started)

[Guide\
\
Everything you need to know to run code on Modal. Dive deep into all of our features and best practices.](https://modal.com/docs/guide)

[Examples\
\
Powerful applications built with Modal. Explore guided starting points for your use case.](https://modal.com/docs/examples)

[Reference\
\
Technical information about the Modal API. Quickly refer to basic descriptions of various programming functionalities.](https://modal.com/docs/sdk/py/latest)

[Playground\
\
Interactive tutorials to learn how to start using Modal. Run serverless cloud functions from your browser.](https://modal.com/playground/get_started)

Featured Examples
-----------------

[All examples](https://modal.com/docs/examples)

[### Deploy an OpenAI-compatible LLM service\
\
Run large language models with a drop-in replacement for the OpenAI API](https://modal.com/docs/examples/llm_inference)

[### Optimize tokens per second\
\
Maximize throughput in batch LLM processing](https://modal.com/docs/examples/vllm_throughput)

[### Deploy OpenCode agents\
\
Run coding agents at scale in secure Sandboxes](https://modal.com/docs/examples/opencode_server)

[### Design protein binders with ESMFold2\
\
Propose and evaluate thousands of binders in parallel](https://modal.com/docs/examples/esmfold2_binder_design)

[### Transcribe speech in batches with Whisper\
\
Turn audio bytes into text at scale](https://modal.com/docs/examples/batched_whisper)

[### Voice chat with LLMs\
\
Build an interactive voice chat app](https://modal.com/docs/examples/llm-voice-chat)

[### Deploy vibe coding at scale\
\
Build an AI coding platform for thousands of users](https://modal.com/docs/examples/modal-vibe)

[### Custom pet art from Flux with Hugging Face and Gradio\
\
Fine-tune an image generation model on pictures of your pet](https://modal.com/docs/examples/diffusers_lora_finetune)

[### Deploy really big language models\
\
Serve models with hundreds of billions of parameters](https://modal.com/docs/examples/very_large_models)

[### Edit images with Flux Kontext\
\
Transform images with SotA diffusion models](https://modal.com/docs/examples/image_to_image)

[### Fold proteins with Boltz-2\
\
Predict molecular structures and binding affinities from sequences with SotA open source models](https://modal.com/docs/examples/boltz_predict)

[### Serverless WebRTC\
\
Stream YOLO detections on webcam footage in real time](https://modal.com/docs/examples/webrtc_yolo)

[### Sandbox a LangGraph agent's code\
\
Run an LLM coding agent that runs its own language models](https://modal.com/docs/examples/agent)

[### Serve diffusion models\
\
Serve Flux on Modal with optimizations for blazingly fast inference](https://modal.com/docs/examples/flux)

[### Low latency SGLang\
\
Run interactive language model applications](https://modal.com/docs/examples/sglang_low_latency)

[### Transcribe speech with Kyutai STT\
\
Stream transcripts at the speed of speech](https://modal.com/docs/examples/streaming_kyutai_stt)

[### Star in custom music videos\
\
Fine-tune a Wan2.1 video model on your face and run it in parallel](https://modal.com/docs/examples/music-video-gen)

[### Make music\
\
Turn prompts into music with ACE-Step](https://modal.com/docs/examples/generate_music)

[### RAG Chat with PDFs\
\
Use ColBERT-style, multimodal embeddings with a Vision-Language Model to answer questions about documents](https://modal.com/docs/examples/chat_with_pdf_vision)

[### Bring images to life\
\
Prompt a generative video model to animate an image](https://modal.com/docs/examples/image_to_video)

[### Build a protein folding dashboard\
\
Serve a web UI for a protein model with ESM3, Molstar, and Gradio](https://modal.com/docs/examples/esm3)

[### Deploy a Hacker News Slackbot\
\
Periodically post new Hacker News posts to Slack](https://modal.com/docs/examples/hackernews_alerts)

[### Fold proteins with Chai-1\
\
Predict molecular structures from sequences with SotA open source models](https://modal.com/docs/examples/chai1)

[### Retrieval-Augmented Generation (RAG) for Q&A\
\
Build a question-answering Web Function that can cite its sources](https://modal.com/docs/examples/potus_speech_qanda)

[### Document OCR job queue\
\
Use Modal as an infinitely scalable job queue that can service async tasks from a web app](https://modal.com/docs/examples/doc_ocr_jobs)

[### Parallel processing of Parquet files on S3\
\
Analyze data from the Taxi and Limousine Commission of NYC in parallel](https://modal.com/docs/examples/s3_bucket_mount)