Modal

Modal · Infra
✓ Verified listing Free plan API

Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.

Visit Modal ↗

Overview

Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.

Pricing

Starter $30/mo free credits Free
Pay as you go Metered
Team + compute $250/mo

Usage-based plans are shown as Metered and are excluded from stack totals.

Compare Modal

Price history

  • Team recorded at $250 · 13 Nov 2026
  • Pay as you go recorded at metered · 17 Aug 2026
  • Starter recorded at $0 · 17 Aug 2026

Facts

CategoryInfra
CompanyModal
Free planYes
Starting price$250/mo
Top plan$250/mo
Pricing modelfreemium
APIYes
Open weightsNot verified
Commercial useNot verified
RatingNot rated — we do not publish scores we cannot source.

Data

Last verified: 13 Nov 2026
Pricing source: modal.com
Listing status: Unclaimed, verified

Report outdated information

Are you the owner of Modal? Claim this listing.

Alternatives to Modal

Same category and tags

RunPod

RunPod
✓ 22 Aug 2026

Per-second GPU rental across Community and Secure Cloud tiers, plus serverless inference workers.

GPUPer-secondServerless

Lambda

Lambda
✓ 22 Aug 2026

On-demand GPU instances billed by the minute with no egress fees, from a company that also builds the hardware.

GPUTrainingNo egress

Fireworks AI

Fireworks
✓ 13 Nov 2026

Low-latency open-model serving with tuned deployments and function calling.

InferenceLow latency

Groq

Groq
✓ 17 Aug 2026

Custom silicon delivering very high tokens-per-second on open models.

Ollama

Ollama
✓ 13 Nov 2026

Run open models locally on your own machine.

LocalPrivate

OpenRouter

OpenRouter
✓ 13 Nov 2026

One API key, hundreds of models, automatic failover.

RouterMulti-model

Cheaper than Modal

By entry price

Fireworks AI

Fireworks
✓ 13 Nov 2026

Low-latency open-model serving with tuned deployments and function calling.

InferenceLow latency

Groq

Groq
✓ 17 Aug 2026

Custom silicon delivering very high tokens-per-second on open models.

Ollama

Ollama
✓ 13 Nov 2026

Run open models locally on your own machine.

LocalPrivate

OpenRouter

OpenRouter
✓ 13 Nov 2026

One API key, hundreds of models, automatic failover.

RouterMulti-model
✓ 13 Nov 2026

Commercially safe generation trained on licensed content, built into Photoshop and Illustrator.

LicensedPhotoshop

Augment Code

Augment
✓ 13 Nov 2026

A context engine that indexes large codebases so its agent answers against your real repository rather than the open file.

AgentContextLarge codebase