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)
Tool use compatibility across relay sites, and how to self-test it
Tool calling is the capability most likely to pass a test and fail in production. This article covers the structural dif…
Six kinds of streaming (SSE) failure on relay sites, and how to pin down each one
Streaming is where relay site quality shows through most clearly. This article lists six observable failure patterns, ea…
How Sub2API works and where its compliance line sits
Projects like Sub2API turn a web subscription account into an API and reach a tenth of the official price. This article…
New API's protocol conversion: why it can be reached with Anthropic's official SDK
The dialect differences between vendors are the biggest technical pain point for relay services. This article explains w…
Choosing between One API and New API: an operations view, not a feature list
Feature comparison tables are everywhere, but what really decides which one suits you is who maintains it and whether yo…
Official resale, mixed routing, reverse-engineered: a three-way split of upstream sources and how to identify them
Two sites are both relay services, but different upstream sources give them entirely different stability floors and pric…
Common error codes explained: what 401, 403, 404, 429 and 500 each mean
A lookup table you can consult directly: the common causes of each error code, who to contact, and what to check first.…
After you have chosen: how to keep monitoring your API provider
Choosing a site is not the end of the job. This article gives a lightweight way to keep monitoring a provider: what to p…
Configuring multiple API providers for failover
A single point of dependency is the last thing a production system should have. This article gives a failover setup that…
OpenAI protocol compatibility: chat/completions vs responses
The two endpoints look like they do the same thing, but using the wrong one gives you an immediate 404. This article exp…
What the /v1/models endpoint is, and why it can verify a relay service
This is the easiest endpoint in the OpenAI protocol to verify, and the easiest to overlook. This article explains what i…
Sharing one API key across a team: how to manage it
A shared key creates two problems: usage cannot be attributed, and incidents cannot be traced. This article sets out the…
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.