Stories from the gateway
Guides
Prompt Templates and Versioning: Treating Prompts as Code
Prompts drift, break silently and get edited in production. How to template them safely, version them properly and know which version produced which output.
· 9 min read
Guides
Proxying LLM Traffic: What a Gateway Has to Get Right
Putting a gateway in front of an inference provider centralises keys, budgets and routing. Here is what breaks if you get streaming, headers or cancellation wrong.
· 9 min read
Cost & Pricing
Quantization Cost Savings and the Quality You Trade Away
· 8 min read
Models
Qwen 3.5 Coder vs DeepSeek V4 Pro: Specialist or Generalist
· 9 min read
Models
Qwen 3.6 27B vs Max: Shipped Model or Preview Tier
· 9 min readModels
Qwen 3.6 Guide: The Frontier Model That Fits on One GPU
· 8 min readModels
Qwen 3.6 Max: How to Plan Around a Preview Model
· 9 min readModels
Qwen 3.6 vs MiniMax M3: Different Benchmarks, Really
· 9 min read
Models
Qwen 3.6 vs Qwen 3.5 Coder: General or Specialised
· 8 min read
Cost & Pricing
Rate Limit Tiers Explained: RPM, TPM and What Binds First
· 12 min read
AI Agents
Rate Limiting Agent Fleets Without Killing Throughput
· 9 min read
Guides
Redacting Secrets From Prompts Before They Leave Your Machine
· 9 min read
Models
Regression Testing a Model Upgrade Before It Bites
· 9 min read
Fundamentals
Repetition Penalties: Why They Break Code Generation
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.