Serverless GPU compute. $30 free monthly.
// At a glance
Free Tier
$30/month free compute · no card
// Free tier details
Available Models
Any custom model
Monthly Requests
$30/month free compute
// Quick start
300">"text-purple-400">import modal
app = modal.App(300">"example")
@app.function(gpu=300">"A10G")
300">"text-purple-400">def predict():
print(300">"Running on GPU!")
300">"text-purple-400">return 300">"done"
// Overview
Run any ML model on GPUs with a Pythonic interface. $30/month free compute credit, no card required.
// Pros
- $30/month free compute
- Any model supported
- Pythonic DX
// Cons
- Not an API per se
- Compute-focused
// Score breakdown
Reliability (35%) (from 2m ago health check)100/100
Free Tier Generosity (30%) (computed from quota, no-CC, no-phone fields)85/100
Documentation (20%) (human rating)88/100
Popularity (15%) (GitHub stars (log-normalised), or manual baseline)80/100
Methodology: apivault.dev/methodology
// Best for
Custom model hostingBatch GPU jobsInference endpoints