AI Engineering / Working with LLMs
Cost Estimation & Token Economics
50 lessons in AI Engineering / Working with LLMs
- Reasoning Tokens In Output CostCode Quiz
- Building a Cost Estimation SpreadsheetSlides / Video
- Setting Budgets, Limits, and Spend AlertsSlides / Video
- Cost-per-Task vs Cost-per-TokenSlides / Video
- Batch API Discounts ExplainedSlides / Video
- Embedding Model Pricing and CostSlides / Video
- Cost of Reasoning TokensSlides / Video
- Projecting Monthly LLM CostSlides / Video
- Comparing Model Prices Across ProvidersSlides / Video
- Words-to-Tokens Rule of ThumbSlides / Video
- Calculating Cost Per RequestSlides / Video
- Picking the Cheaper ModelCode Quiz
- Prompt Cache Discount MathCode Quiz
- Conversation History Token GrowthCode Quiz
- Embedding vs Chat Token CostCode Quiz
- Max Output Cost Before the CallCode Quiz
- Input vs Output Token PricingCode Quiz
- Per-1K vs Per-1M PricingCode Quiz
- Monthly Cost From Request VolumeCode Quiz
- Counting Tokens with Tokenizer ToolsSlides / Video
- Estimating Token Count Before SendingSlides / Video
- Input vs Output Token PricingSlides / Video
- Cost of System Prompts and Few-Shot ExamplesSlides / Video
- Cost of Growing Chat HistorySlides / Video
- Approximating Tokens From CharactersCode Quiz
- Batch API Discount Cost CalculationCode Quiz
- Reasoning Model Thinking TokensQuiz
- Embedding Model PricingQuiz
- System Prompt Cost OverheadQuiz
- Conversation History CostQuiz
- Estimating Tokens from TextQuiz
- Batch API Discount PricingQuiz
- Cost of a Single RequestQuiz
- Tokenization Variance Across ModelsQuiz
- Input vs Output Token PricingQuiz
- Budgeting and Cost CeilingsQuiz
- Per-Million-Token Pricing UnitsQuiz
- Building a Cost Estimation ModelFlashcard
- Batch API Discount PricingFlashcard
- RAG Context Injection CostFlashcard
- Embedding Model PricingFlashcard
- Input vs Output Token PricingFlashcard
- Estimating Tokens from TextFlashcard
- Projecting Monthly CostFlashcard
- Cost per User / ConversationFlashcard
- Few-Shot Example CostFlashcard
- Reasoning / Thinking Token CostFlashcard
- Conversation History CostFlashcard
- System Prompt Overhead CostFlashcard
- Cost of a Single RequestFlashcard