Machine learning, generative AI, API AI, automation – these are the building blocks of a smarter future. But accessing their power often requires complex infrastructure and technical expertise. That's where Modal steps in. It's a powerful platform that allows developers and businesses to run or deploy machine learning models, massively parallel compute jobs, task queues, web apps, and even AI assistants, all without needing their own infrastructure. Modal simplifies the process, making it accessible to a wider range of users. Its intuitive interface and comprehensive tools empower you to build and deploy sophisticated AI solutions quickly and efficiently, freeing you to focus on innovation rather than technical hurdles.

Pricing

Pricing Model

Pay-As-You-Go (PAYG)

Pricing Plans

Modal offers a serverless platform focused on AI, ML, and data applications. Their pricing model is consumption-based, meaning you only pay for the resources you use. They offer a generous free tier with $30 of compute per month. GPU instances are priced by the second, ranging from $0.000164 per second for an Nvidia T4 to $0.001097 per second for an Nvidia H100. CPU cores cost $0.000013 per core per second with a minimum of 0.125 cores per container. Key Points: Consumption-based pricing: Pay only for resources used. Free tier: $30 of compute per month. GPU pricing: Varies by GPU type, billed by the second. Nvidia H100: $0.001097/sec Nvidia T4: $0.000164/sec CPU pricing: $0.000013 per core per second (minimum 0.125 cores per container).

$ 30

---