Stories from the gateway
Fundamentals
Speculative Decoding in Practice: When It Pays Off
Speculative decoding is standard in serving stacks now, but the speedup is workload-dependent. What decides whether it helps you, and how to tell.
· 9 min read
Fundamentals
Stop Sequences Explained: Ending Generation on Purpose
How stop sequences work, why they interact badly with tokenisation and streaming, and the finish_reason check most integrations forget to make.
· 8 min read
Guides
Streaming an OpenAI-Compatible API in TypeScript
· 9 min read
Guides
Streaming in Python: Reading SSE From an LLM API
· 9 min read
AI Agents
Summarisation in Agent Loops: Compressing Without Forgetting
· 8 min read
Models
SWE-bench Explained: What the Percentage Actually Measures
· 9 min read
Models
SWE-bench Leaders Compared: Reading the Scores Correctly
· 9 min readFundamentals
Synthetic Training Data: What It Does and Where It Fails
· 9 min read
Models
Terminal-Bench Explained: Scoring Agents That Run Commands
· 9 min read
Models
Terminal-Bench Leaders: The Benchmark That Predicts Agents
· 9 min read
Fundamentals
Test-Time Compute: Buying Accuracy With Tokens Instead of Size
· 9 min readModels
The Artificial Analysis Index Explained: What It Does Measure
· 9 min readModels
The Best Model for Students on a Real Budget
· 9 min read
Models
The Cheapest Frontier Models, Priced Honestly
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.