“Modal made it incredibly easy for us to deploy complex computational jobs that burst up to hundreds of machines. Being able to iterate quickly without having to waste cycles on managing infra was a huge unlock.”
“We used Modal to build an inference server for our model, Chai-1, which allows people to predict molecular structures via a web app. Modal allowed us to build and launch the server in days: our engineers didn't have to worry about maintaining infrastructure, delivering the product in record time.”
“At Phonic, we train our own proprietary models for audio generation. We moved all our large-scale audio processing batch jobs to Modal. Our engineers are ecstatic with the result – we can run at a much larger scale than before, no longer have to babysit our batch jobs, and we can ship much faster.”
Modal as a job queue
Spawn async jobs and poll for the results later; no need to set up a separate job queue.
Integrate with your existing workflow system
Run GPU workers from Airflow or other orchestration tools.
Parallel computation
Distribute your work over thousands of GPUs with a single call to .map().
Cron jobs on demand
Run code on a schedule with a single line of code.
Batch processing for data-intensive workloads
Use Modal for all your data processing needs, from video processing to embedding large datasets.
Rich web interface for data observability
Monitor runs, send email / Slack notifications on failures, and view logs all in your Modal dashboard.
Use Cases