What it is

Serverless compute for Python: decorate a function and Modal containerises it and runs it on GPUs with fast cold starts and scale-to-zero. It is infrastructure, not a model API — you bring the model, the weights and the code.

Why it earns a slot

For when no hosted endpoint exists: custom fine-tunes, unusual pipelines, batch jobs, or an embedding service you want to own. The $30 of free credits each month covers a real side project.

Know before you commit

You own the ops — model loading, memory sizing and concurrency are your problem, and a container that fails to scale to zero bills GPU seconds continuously. Starter caps you at 10 concurrent GPUs.

Getting started

pip install modal && modal setup

Field notes

0 from the community

Sign in to add a field note. Reading is always open.

Loading notes…

Field check

Unverified

Sign in to confirm this entry is still accurate.

Pricing snapshot

Per second. H100 $0.001097/s (~$3.95/hr), B200 $0.001736/s, A100 40GB $0.000583/s, T4 $0.000164/s; CPU $0.0000131/core-s. Starter $0 with $30/mo free credits; Team $250/mo with $100 credits.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Modal (https://modal.com) for this project, then use it only if it fits what we are already building.
Context: Serverless GPU compute platform. Serverless compute for Python: decorate a function and Modal containerises it and runs it on GPUs with fast cold starts and scale-to-zero. It is infrastructure, not a model API — you bring the model, the weights and the code.
Reviewer notes (general, not written for this codebase): For when no hosted endpoint exists: custom fine-tunes, unusual pipelines, batch jobs, or an embedding service you want to own. The $30 of free credits each month covers a real side project.
Watch out for: You own the ops — model loading, memory sizing and concurrency are your problem, and a container that fails to scale to zero bills GPU seconds continuously. Starter caps you at 10 concurrent GPUs.
Pricing: Per second. H100 $0.001097/s (~$3.95/hr), B200 $0.001736/s, A100 40GB $0.000583/s, T4 $0.000164/s; CPU $0.0000131/core-s. Starter $0 with $30/mo free credits; Team $250/mo with $100 credits.
Setup: pip install modal && modal setup
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/modal

Also in Model APIs, routers & observability

Anthropic API / Claude Platform

platform.claude.com

Frontier model provider API

PaidModel APIs, routers & observability

Per token. Opus 5 $5/$25 per M in/out; Sonnet 5 $2/$10; Haiku 4.5 $1/$5; Fable 5 and Mythos 5 $10/$50. Batch API 50% off; cache reads 0.1x input.

Open dossier

Braintrust

braintrust.dev

LLM eval and experiment platform

Free tier + paidModel APIs, routers & observability

Starter free ($10/mo model credits, 1GB data, 10k scores, 14-day retention), Pro $249/mo ($249 credits, 5GB, 50k scores), Enterprise custom. Overage $3-4/GB and $1.50-$2.50 per 1k scores.

Open dossier

Fal.ai

fal.ai

Generative media inference host

PaidModel APIs, routers & observability

Per output or per second for media models: images ~$0.02-$0.04 at 1MP, video $0.05-$0.40 per second. Serverless GPU rates $1.10-$8.50/hr with committed-use discounts.

Open dossier

Fireworks AI

fireworks.ai

Open-model inference host

Free tier + paidModel APIs, routers & observability

Per token serverless across Standard/Priority/Fast tiers; embeddings $0.008-$0.10/M. On-demand GPUs billed per second: H100/H200 ~$7-8/hr, B200 ~$10-13/hr. Fine-tuning $0.50-$40 per M training tokens. $1 free credit.

Open dossier