← back to the directory
Hosted Service Inference & ServingAutomation & Integration

Modal

1Run 2Python 3code 4and 5models 6serverlessly.

the six Ws · specification

W1 Who

By Modal Labs.

W2 What

Serverless cloud for running Python functions and model inference on GPUs.

W3 Where

A hosted platform driven from Python.

W4 When

When you need on-demand GPU compute.

W5 Why

Deploy GPU workloads without managing servers.

W6 With

A Modal account and the Python SDK.

W7 Watch

Commercial serverless platform, account required; your code runs on Modal's cloud.

alternatives

works with

ServerlessGPUPython

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.