Check whether a model id is in the Plugsky catalogue and what to use instead.
—
Plugsky is OpenAI-compatible with flat-rate plans — see pricing or start on the free plan (2 free models, no card).
The Model Availability Tracker is a free page for following which AI models are active, deprecated or announced across providers. Model line-ups change often, and deprecated endpoints can break production applications without warning. Developers and platform owners use availability information to plan migrations and avoid building on a model that is being retired. The page requires no sign-up, but always confirm current status in the provider's official documentation.
Providers retire models to free capacity, cut maintenance costs, or replace them with cheaper or better versions. Notice periods vary from weeks to over a year, and some providers keep old versions available at higher prices. Track announcements so a shutdown does not catch your application mid-quarter.
Avoid hard-coding a single model name throughout the codebase, route model selection through configuration, and keep an evaluation set that lets you test a replacement quickly. An OpenAI-compatible provider such as Plugsky also lets you switch models by changing one string.
Treat any announced deprecation as a scheduled project rather than an emergency. Build in time to re-run quality tests, check token pricing at your volume, and update rate-limit handling. Waiting until the shutdown date usually forces rushed decisions.
Canonical pricing and plans: plugsky.com/#sec-pricing · Terms · SLA · Docs