Serverless cloud for AI/ML workloads. Write Python with decorators, Modal handles GPU provisioning and scaling. 2-4s cold starts. Scales to zero. $30/mo free compute.
Modal is a high-performance serverless cloud platform purpose-built for AI, machine learning, and data engineering. You write Python functions with Modal decorators and the platform handles container provisioning, GPU allocation, scaling, and teardown. No Docker, no Kubernetes, no YAML. Cold starts typically range between 2-4 seconds, and it scales back to zero when idle so you only pay for actual compute time. Workload support includes inference, model training, fine-tuning, batch processing, sandboxed code execution, and interactive notebooks. Backed by over $111 million in funding at a $1.1 billion valuation, Modal is the tool for developers who want fine-grained control over GPU compute without the burden of infrastructure management. The $30/month free compute tier is enough to prototype serious workloads.
Deployment platform behind Next.js. Git push to deploy. Edge functions, image optimization, analytics. Free tier is generous.
Run 50,000+ ML models with a simple API. No infrastructure management. Pay-per-second billing. Deploy custom models with Cog. Popular for image generation and audio.
Fastest inference for open-source models. 200+ models via unified API. Ranks #1 on speed benchmarks for DeepSeek, Qwen, Kimi, and Llama. Serverless pay-per-token pricing.
Serverless Postgres with branching. Free tier, instant database branches per PR, autoscaling compute, and scale-to-zero. Acquired by Databricks in 2025.
Serverless cloud for AI/ML workloads. Write Python with decorators, Modal handles GPU provisioning and scaling. 2-4s cold starts. Scales to zero. $30/mo free compute.
Try ModalHonest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeDeployment platform behind Next.js. Git push to deploy. Edge functions, image optimization, analytics. Free tier is generous.
Self-hosted PaaS for deploying apps, databases, and services. Git-based deploys, Docker support, preview environments, and a clean UI.
Reactive backend - database, server functions, real-time sync, cron jobs, file storage. All TypeScript. This site's backend (courses, videos, user data) runs on Convex.

How to set up Entire's regional Git mirrors for AI coding agents. Covers installation, mirroring, integrations with Clau...

A new distributed inference system pools GPU resources across multiple machines and exposes them through a single OpenAI...

A Haskell Foundation board member explains why Scarf moved to Python after 7 years in production. The culprit: LLM-drive...

Cloudflare Research introduces Meerkat, a distributed consensus service using QuePaxa that eliminates leader elections a...

A companion guide to the Agents 101 video: a behind-the-scenes walkthrough of building and deploying AI agents fast on V...

A builder's guide to picking a code-execution sandbox for AI agents - E2B, Daytona, Modal, Cloudflare Sandbox, and Verce...

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.