Record your provider's free-tier limits and see what breaks first.
—
Plugsky is OpenAI-compatible with flat-rate plans — see pricing or start on the free plan (2 free models, no card).
The Free API Limits Tracker is a free reference page for comparing free-tier limits across major AI providers. It covers requests per minute, tokens per minute, concurrent request ceilings and whether a credit card is required to start. Developers and students use it to find a free API that fits a prototype without hitting a wall mid-build. The page needs no sign-up. Plugsky's own free plan includes 2 free models.
Free tiers often cap requests and tokens per minute, and some also limit concurrency or total monthly credits. A prototype can work in testing and fail under a slightly larger load. Checking limits before you build avoids rewriting rate-limit handling later.
Requests per minute counts how many API calls you can make, while tokens per minute counts the text volume those calls carry. A handful of long prompts can exhaust TPM while RPM looks fine. Track both and add retry with backoff for rate-limit responses.
It depends on your workload and region, and limits change without notice. Compare current numbers on this page, then verify on the provider's documentation. Plugsky's free plan includes 2 free models with no credit card, and a 14-day full-access trial is available for heavier testing.
Canonical pricing and plans: plugsky.com/#sec-pricing · Terms · SLA · Docs