Tutorials
Practical material on AI API relay services: how rates are calculated, how to verify a model has not been downgraded, what enterprises should check before buying, and the pitfalls we ran into while measuring these services ourselves.
Browse by topic
Tutorials (57 articles)
Video generation behind a relay: three API shapes, four billing traps, one acceptance checklist
Video generation has no shared protocol; every vendor ships its own asynchronous task flow. The shape decides how you in…
MCP through a relay: what works, what never will, and how to test it in ten minutes
MCP never touches the model API, so “does this relay support MCP” is the wrong question. Three tool-use behaviours decid…
A relay selection decision tree: working back from your scenario to a site
Selection is not about which site is best, it is about what your scenario demands. This article turns it into a path you…
Logging and reconciliation: attributing token spend to the project level
If you cannot see where the money goes, optimisation is meaningless. This article gives a minimum viable call log design…
Migrating suppliers gradually: replacing an API site without interrupting service
The risk in changing supplier is not the switch itself, it is finding the problems afterwards. This article gives a four…
Build your own probe: twenty lines of script to monitor your API suppliers
You do not need a monitoring platform. One scheduled script plus one alert covers it. This article gives a probe design…
IP allowlists, sub-accounts and permission tiers: a survey of relay governance
Governance decides whether a site is usable for teams and commercial work. This article gives a checklist you can score…
How available niche models like Grok and Llama really are on relay sites
Availability of niche models varies enormously and quality is uneven. This article covers how to judge whether a model i…
Where the value range of domestic models (Qwen, GLM, Kimi, MiniMax) actually sits
Domestic models show a clear cost-performance advantage on specific tasks, but the boundary differs from overseas models…
DeepSeek through a relay: how standard and reasoning variants bill differently
Reasoning models routinely produce bills far above expectations, because the thinking process is billed as output. This…
Gemini through a relay: choosing between Pro, Flash and Flash-Lite
Gemini's three tiers differ more than the names suggest. This article gives selection criteria along context length, lat…
Team budget control: from discovering the overspend at month end to live limits
The biggest problem with a shared team API key is not the cost, it is the invisibility. This article gives a four-step m…
Supporting data & tools
The articles explain the method; the pages below give you measured data and prices to check it against. Reading them together is easier — once you know how to tell whether a rate is real, you can look the official price up in the price list.