Stories from the gateway
Models
GDPval Explained: Benchmarking Real Professional Work
GDPval scores models on deliverables from real occupations, graded by experts. What that measures, why it is not a coding benchmark, and how to read it.
· 9 min read
Guides
Generating API Clients With an LLM Without Silent Drift
Where a model beats openapi-generator, where it quietly loses, and how to build a generate-compile-test loop that catches the hallucinated field before you ship it.
· 9 min read
Guides
Generating Regular Expressions With an LLM, Carefully
· 9 min readGuides
GitHub Actions LLM Setup: A Workflow That Reviews PRs
· 9 min read
Guides
GitLab CI LLM Setup: Masked Variables and MR-Only Jobs
· 9 min read
Models
GLM-5.2 vs DeepSeek V4 Flash: Ten Times the Price
· 9 min read
Models
GLM-5.2 vs MiniMax M3: Long-Horizon Code or Cheap Multimodal
· 9 min read
Models
GLM-5.2 vs Qwen 3.6: Sparse and Huge, or Dense and Small
· 8 min readGuides
Goose Setup Guide: Providers, Extensions and Safe Defaults
· 8 min read
Fundamentals
GPU Memory for Inference: What Actually Fills the Card
· 9 min read
Cost & Pricing
GPU Rental Cost Math: Utilisation Decides Everything
· 8 min read
Fundamentals
Grouped-Query Attention: Why Long Context Got Affordable
· 9 min readGuides
Handling SSE Disconnects Without Losing the Response
· 9 min readModels
How to Read a Model Card Without Being Misled
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.