Stories from the gateway
Fundamentals
Throughput vs Latency: The Trade-off Behind Your Bill
Serving more tokens per second and serving them faster are opposing goals. The knob that reconciles them is batch size, and it decides both speed and price.
· 9 min read
Fundamentals
Time to First Token: What It Measures and What Moves It
TTFT is dominated by prefill compute, queueing and network distance rather than by model speed. What each contributes, and how to measure it without fooling yourself.
· 9 min readFundamentals
Token Costs by Language: Why the Same Text Bills Differently
· 9 min read
Fundamentals
Tokenizer Differences: Why the Same Text Costs Different Amounts
· 8 min read
Fundamentals
Tokens Per Second Explained: Reading the Number Correctly
· 9 min read
Fundamentals
Top-K Sampling Explained, and Why Top-P Replaced It
· 8 min readFundamentals
Transformer Architecture Explained for Working Developers
· 9 min read
Fundamentals
Unicode and Tokenization: Where Text Handling Goes Wrong
· 9 min readFundamentals
Vocabulary Size Trade-offs in Language Model Tokenizers
· 9 min read
Fundamentals
Where Quantised Models Actually Lose Quality
· 9 min readFundamentals
Context Windows: Why More Is Not Always Better
· 8 min readFundamentals
Embeddings Explained: Vectors, Similarity and Where It Breaks
· 9 min readFundamentals
Fine-Tuning vs Prompting vs RAG: How to Adapt a Model
· 9 min readFundamentals
How LLMs Actually Work: Next-Token Prediction, End to End
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.