Each entry explains the waste, the billing model behind it, how to detect it and how to fix it.
43 inefficiencies
AWS SageMakerCER-0333
SageMaker notebook instances are billed continuously while in an active state - and critically, they do not automatically shut down when idle. Closing a browser tab, shutting down a Jupyter kernel, or simply walking away does not stop the...
AWS S3CER-0330
Machine learning experimentation workflows - particularly those managed through experiment tracking platforms - generate large volumes of artifacts in object storage. Every training run produces model checkpoints, evaluation outputs,...
GCP Vertex AICER-0267
Vertex AI workloads often include low-complexity tasks such as classification, routing, keyword extraction, metadata parsing, document triage, or summarization of short and simple text. These operations do not require the advanced...
AWS BedrockCER-0276
Many Bedrock workloads involve low-complexity tasks such as tagging, classification, routing, entity extraction, keyword detection, document triage, or lightweight summarization. These tasks do not require the advanced reasoning or...
Azure Cognitive ServicesCER-0238
Many Azure OpenAI workloads - such as reporting pipelines, marketing workflows, batch inference jobs, or time-bound customer interactions-only run during specific periods. When PTUs remain fully provisioned 24/7, organizations incur...
Azure Cognitive ServicesCER-0248
Development, testing, QA, and sandbox environments rarely have the steady, predictable traffic patterns needed to justify PTU deployments. These workloads often run intermittently, with lower throughput and shorter usage windows. When PTUs...
Azure Cognitive ServicesCER-0266
When organizations size PTU capacity based on peak expectations or early traffic projections, they often end up with more throughput than regularly required. If real-world usage plateaus below provisioned levels, a portion of the PTU...
AWS BedrockCER-0256
AWS frequently updates Bedrock with improved foundation models, offering higher quality and better cost efficiency. When workloads remain tied to older model versions, token consumption may increase, latency may be higher, and output...
Azure Cognitive ServicesCER-0246
Many production Azure OpenAI workloads - such as chatbots, inference services, and retrieval-augmented generation (RAG) pipelines-use PTUs consistently throughout the day. When usage stabilizes after initial experimentation, continuing to...
Azure Cognitive ServicesCER-0254
Azure releases newer OpenAI models that provide better performance and cost characteristics compared to older generations. When workloads remain on outdated model versions, they may consume more tokens to produce equivalent output, run...
Azure Cognitive ServicesCER-0277
Some workloads - such as text classification, keyword extraction, intent detection, routing, or lightweight summarization - do not require the capabilities of the most advanced model families. When high-cost models are used for these...
AWS SageMakerCER-0383
In SageMaker Studio, each running JupyterLab or Code Editor application runs on an instance that is billed for as long as the application is running, whether or not the user is doing anything. Data scientists routinely leave spaces running...
Showing 12 of 43
