
by Modal
Modal is a serverless cloud platform for running AI workloads, including inference, training, batch jobs and sandboxes. Infrastructure is defined in code and billed per second of use.
APIUsage-based
Step 1: Create an account at modal.com.
Step 2: Run pip install modal.
Step 3: Run modal setup to authenticate.
Step 4: Write a Python function with the app.function decorator and choose a GPU if needed.
Step 5: Run it with modal run, or deploy it as an app.
Step 6: Monitor logs and metrics and set a workspace budget if you want to cap spend.
No. Starter and Team usage is pay-as-you-go and does not require pre-purchasing compute. You can set a workspace budget to limit monthly spend.
Modal bills during application load time and while your container processes inputs. Containers stay alive 60 seconds after the last input by default, which is also billed and configurable.
Python is the primary language for building Modal apps. JavaScript, TypeScript and Go can call functions, run Sandboxes and manage resources.
Yes. The docs state a valid payment method on file is required to use a GPU.
AssemblyAIAssemblyAI is a voice AI platform with APIs for speech-to-text, text-to-speech, speech understanding and LLM access. Developers use it to build voice agents, notetakers and call analytics.
Ocean ProtocolOcean Protocol is an open-source, decentralized stack for sharing, selling and computing on data and AI models while the data owner keeps control. It is for data owners, data scientists and developers building data and AI applications on Web3.