Modal

Serverless containers for Python functions, model servers and sandboxes on CPUs or GPUs.

Provider: default
Kind: ML inference
Category: Compute
Official docs: https://modal.com/docs/guide/cold-start
Also known as: Modal Sandboxes

Properties · 3 set by this component

property	type	values	required	kind default	this component
accelerator	enum	none \| gpu \| asic	no	none	inherited
acceleratorModel · advanced	enum	nvidia-h100 \| nvidia-h200 \| nvidia-b200 \| nvidia-l4 \| nvidia-a100 \| amd-mi300x \| aws-trainium \| aws-inferentia \| google-tpu \| intel-gaudi \| groq-lpu \| cerebras-wse	no	—	inherited
embeddingSyncMinutes · advanced	integer	—	no	—	inherited
inputs	enum	live \| historical \| both	no	live	▸ live
instances	integer	—	no	—	inherited
managed	boolean	—	no	false	▸ true
minContainers · component property	integer	—	no	0	inherited
sandbox · component property	boolean	—	no	false	inherited
scaledownWindowSeconds · component property	integer	—	no	60	inherited
snapshotToObjectStore · advanced	boolean	—	no	false	inherited
timeoutSeconds · component property	integer	—	no	300	inherited
training	enum	batch \| online	no	batch	▸ batch

Rules that apply · 1

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

Stateful node without zone redundancyerror

stateful-node-without-zone-redundancy

A stateful compute node pinned to exactly one availability zone disappears with that zone, and its state goes with it. Nodes inside a cell are exempt, because there the cell is deliberately single-zone and redundancy comes from the other cells.

— all of these hold:
— the node's `stateless` is false
— the node sits inside exactly 1 availability-zone group
— this does not hold:
— the node sits inside at least one cell group

Use it in a design

nodes:
  - { id: "modal", component: "modal" }

Other ML inference products · 37

SageMaker endpointsagemaker-endpointawsml-inference Azure ML endpointazure-ml-endpointazureml-inference Workers AIcloudflare-workers-aicloudflareml-inference Anyscale Endpointsanyscale-endpointsml-inference Bananabanana-devml-inference Basetenbasetenml-inference Beambeam-cloudml-inference BentoMLbentomlml-inference Hugging Face Inference Endpointshuggingface-inferenceml-inference Infinityinfinity-embeddingsml-inference Janjanml-inference KServekserveml-inference llama.cpp serverllama-cpp-serverml-inference llm-dllm-dml-inference LM Studiolm-studioml-inference LMDeploylmdeployml-inference LocalAIlocalaiml-inference Generic ML inferenceml-inferenceml-inference MLC LLMmlc-llmml-inference Mystic AImystic-aiml-inference NVIDIA NIM (self-hosted)nvidia-nimml-inference OctoAIoctoaiml-inference Ollamaollamaml-inference Ray Serveray-serveml-inference Seldon Coreseldon-coreml-inference SGLangsglangml-inference TensorFlow Servingtensorflow-servingml-inference TensorRT-LLMtensorrt-llmml-inference Text Embeddings Inferencetext-embeddings-inferenceml-inference Text Generation Inferencetext-generation-inferenceml-inference TorchServetorchserveml-inference NVIDIA Tritontritonml-inference vLLMvllmml-inference Xinferencexinferenceml-inference Vertex AI endpointvertex-ai-endpointgcpml-inference OCI Data Science Model Deploymentoci-data-science-model-deploymentociml-inference OCI Generative AI Dedicated AI Clusteroci-generative-ai-clusterociml-inference

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Modal: serverless platform that runs Python functions and model servers in containers on CPUs or GPUs, billed per
3# second. Per "Cold start performance", containers scale to zero (min_containers 0) and shut down after a 60-second
4# scaledown_window; per the App.function reference a call times out after 300 seconds. Modal Sandboxes (secure
5# containers for untrusted or agent-written code, 5-minute default lifetime) are this component with sandbox: true.
6schemaVersion: "1"
7type: "component"
8id: "modal"
9kind: "ml-inference"
10provider: "default"
11docs: "https://modal.com/docs/guide/cold-start"
12aliases: ["Modal Sandboxes"]
13defaults:
14  training: "batch"
15  inputs: "live"
16  managed: true
17properties:
18  minContainers:
19    type: "integer"
20    default: 0
21  scaledownWindowSeconds:
22    type: "integer"
23    default: 60
24  timeoutSeconds:
25    type: "integer"
26    default: 300
27  sandbox:
28    type: "boolean"
29    default: false

The same page as markdown, for an agent: /catalogue/components/modal.md