Stories from the gateway
Guides
Roo Code Setup: Custom Endpoint and Profiles Per Mode
Configure Roo Code against an OpenAI-compatible base URL, then use API configuration profiles to give each mode its own model. Includes the tool-calling caveat.
· 8 min read
Guides
Running LLMs in CI Without Flaky, Expensive Builds
Putting a model call inside CI adds a non-deterministic network dependency to your build. How to keep it cheap, secret-safe on forks, and incapable of blocking a merge.
· 9 min read
Cost & Pricing
Self-Hosting vs a Managed API: Find Your Break-Even
· 9 min read
Cost & Pricing
Setting an AI Budget for a Small Engineering Team
· 8 min read
Models
Small vs Large Models: Why Parameter Count Stopped Meaning Much
· 10 min read
Fundamentals
Speculative Decoding: Faster Output, Identical Tokens
· 8 min read
Models
Stop Reading Benchmarks. Build a 20-Task Eval Instead.
· 9 min read
Guides
Streaming LLM Responses: SSE, Buffering, and Why Output Stalls
· 8 min read
AI Agents
Structured Outputs: Getting JSON You Can Actually Parse
· 7 min read
AI Agents
Subagents and Delegation: When Splitting an Agent Helps
· 9 min read
Fundamentals
System Prompts: What They Actually Do and How to Write One
· 9 min read
Fundamentals
Temperature, Top-p and Sampling: What the Knobs Really Do
· 8 min read
Models
The Best Model for Refactoring Is the One That Stays in Scope
· 9 min read
Cost & Pricing
The Hidden Costs of AI Coding Tools
· 8 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.