← All drillsAI on Google Cloud, AWS and Azure: A Map
What you'll be able to do- ✓Match each cloud's service to the job it does — a hosted language model, a ready-made speech service, training your own model, and rented accelerators
- ✓{'Read the same prompt written for Google Cloud, AWS and Azure and say what differs': 'how you sign in, what the model is called, and where the answer sits'}
- ✓Tell a call that answers at once from a job you start and poll, and follow a polling loop
- ✓Walk through a managed training job on each platform in the same seven steps
- ✓Turn a bill's lines into a monthly estimate and name the one that dominates
Answer "which cloud should we use for AI?" with a map of the three, a checklist of what each needs before its first call works, and the habit of asking which line of the bill is the cost.
⌁ Anyone choosing where to run an AI feature meets this comparison, because the three clouds sell the same few jobs under different names and change those names often.
Start this internshipCreate an account to unlock the 4 sections, the workbench, and askThili.
BeginSections
1. Why this course: from the cloud you teach to the cloud AI runs on
🔒 locked2. Calling a Hosted Model on Three Clouds
🔒 locked3. A Ready-Made Service, Three Ways
🔒 locked4. Train Your Own, and Read the Price
🔒 lockedDig deeper
🔗Google Gen AI SDK for Python — documentation
article🔗Amazon Bedrock — Inference using the Converse API
article🔗Azure OpenAI — switch between OpenAI and Azure OpenAI endpoints with Python
article🔗Cloud Speech-to-Text — transcribe with the client libraries
article🔗Amazon Transcribe — StartTranscriptionJob API reference
article🔗Azure AI Speech — speech to text quickstart (Python)
article🔗Azure Machine Learning — train ML models
article🔗Amazon SageMaker AI — train a model
article🔗Google Cloud — create a custom training job
article