Serverless compute platform for AI and Python workloads - GPUs, distributed jobs, web endpoints, and cron - billed per second with no idle cost.

Overview

Modal is a serverless compute platform aimed at engineers who want GPUs, distributed batch jobs, and web endpoints without managing a single VM. You write a Python function, decorate it with resource hints (GPU type, memory, concurrency), and Modal handles scheduling, autoscaling, and teardown - you pay only for the seconds your code actually runs. In our hands-on use, the standout is the programming model: a training job, an inference API, and a scheduled scraper can all live in one script and share the same deploy flow. Because it autoscales to zero, a rarely used endpoint costs nothing between calls, which is hard to match on a reserved-instance cloud. It shines for spiky ML workloads, inference serving, and data pipelines, and it exposes raw containers when you need custom images. The trade-off is lock-in: workloads are expressed in Modal’s decorator API rather than portable Kubernetes manifests, so moving off later means rewriting.

Key Features

  • Per-second billing with autoscale-to-zero - no cost for idle resources
  • Wide GPU menu from T4 to B200/H100, allocated by a single decorator argument
  • Distributed map and queue primitives for fan-out batch and pipeline jobs
  • Web endpoints and cron schedules deployed from the same Python script
  • Custom container images and secrets for reproducible, production-grade runs
  • Volumes and observability (metrics, logs, rollbacks) included per workspace

Pricing

PlanPriceForNotes
Starter$0Indie devs and small teams$30/mo free credits, 3 seats, 100 containers, 10 GPU concurrency
Team$250/mo + usageStartups scaling up$100/mo credits, 5000 containers, 50 GPU concurrency, custom domains
EnterpriseCustomSecurity- and scale-critical orgsVolume discounts, SSO, audit logs, HIPAA, private Slack support
On-demand computePay-as-you-goAny workloadH100 ~$0.0011/s, A100 80GB ~$0.00069/s, CPU $0.0000131/core/s

Comparison

Against Together AI and Replicate, which are model-serving platforms, Modal is general compute: you bring any code or model rather than calling a hosted inference endpoint. Versus fal.ai, which optimizes media inference (image/video) behind fast APIs, Modal is broader but leaves more to you. Pick Modal when you need arbitrary Python jobs, training, or web services on GPUs; pick the others when you just want a specific model served with minimal code.

Compare alternatives

Side-by-side with the 3 closest alternatives.

ToolCategoryPricingVisit
Modal (this) code, agentsFrom $0/mo Site ↗
Together AIcode, agentsFree $1-$5 signup · From $0.06/mo Site ↗
Replicatecode, image, videoFree $5 sign-up · From $0.000225/mo Site ↗
fal.aiimage, videoFree $1 on signup · From $0.003/mo Site ↗
Modal Current

Serverless compute platform for AI and Python workloads - GPUs, distributed jobs, web endpoints, and cron - billed per second with no idle cost.

codeagents
From $0/mo

Together AI is a developer platform for running, fine-tuning, and deploying 200+ open-source models through one OpenAI-compatible API, with serverless inference, dedicated endpoints, and GPU cloud.

codeagents
Free $1-$5 signup · From $0.06/mo

Cloud platform to run thousands of open-source ML models through a single API — no GPU infrastructure to manage, pay only for compute time.

codeimagevideo
Free $5 sign-up · From $0.000225/mo

fal.ai is a serverless inference platform that gives developers fast, pay-per-use API access to leading image and video generation models like FLUX, SDXL, Nano Banana, and Kling.

imagevideo
Free $1 on signup · From $0.003/mo
Editor’s Review
4.4/5
Pros
  • +Autoscale-to-zero means you rarely pay for idle GPU time
  • +One Python script deploys batch jobs, APIs, and cron together
  • +Broad GPU selection with simple, per-second pricing
Cons
  • Modal-specific decorator API creates platform lock-in
  • Team plan's $250/month base plus usage can surprise smaller teams
  • Less control than raw Kubernetes for exotic networking needs

Modal is the fastest way we know to get a GPU job or inference API live without touching infrastructure. The lock-in is real, but for spiky or experimental workloads the per-second billing and zero idle cost are compelling.

See all reviews →