博文

目前显示的是 七月, 2026的博文

A Small Reliability Checklist for OpenAI-Compatible AI APIs

Most AI API reliability work is not about adding another provider. It is about making ordinary failure states visible before a Friday deploy turns them into a support thread. Here is the small checklist I keep next to any model change. 1. Resolve the exact model ID before deploy A model name in a launch post is not an API identifier. Copy the exact ID from the live model catalog or models endpoint, put it in configuration, and log the value used by each request. This makes a rollback boring: change one reviewed config value, not several strings scattered through the codebase. 2. Give every request a client-side correlation ID Generate a request ID before calling the API. Carry it through your application logs, background jobs, and user-facing error reports. A client-side ID will not replace provider logs, but it gives your team one stable handle when the request crosses several services. 3. Separate retryable failures from fix-the-request failures Do not put every non-200 respons...

How to Access 200+ AI Models Through a Single API Endpoint

If you've built anything with large language models lately, you've probably hit the same wall many developers do: every provider has its own SDK, its own authentication, its own rate limits, and its own billing dashboard. Wiring up OpenAI is fine. Adding Anthropic means a second integration. Throwing in Google's Gemini or an open model from Meta means yet another. Before long, half your codebase is glue code for switching between providers. This post looks at how an AI API gateway solves that problem, and why routing all your model calls through one endpoint is becoming a common pattern for teams that work with multiple providers. The multi-provider problem Most real applications don't stay loyal to a single model. You might use a fast, cheap model for classification and a stronger one for complex reasoning. You might want a fallback when your primary provider has an outage. You might simply want to compare outputs across models before committing to one. Doing this manu...