Zotgpt Rate Limits
UC Irvine publishes no numeric request-rate table for either ZotGPT API — no requests-per-minute, no tokens-per-minute, no burst ceiling. What it publishes instead is a SPEND ceiling: usage is governed by dollar-denominated credits, per-key spend limits, and workspace budget enforcement, tiered by affiliation and by whether a funding source has been validated. That is a meaningful design choice rather than an omission — for an internal AI utility the scarce resource is budget, not concurrency, and metering in dollars lets one control surface span models whose per-token costs differ by an order of magnitude.
Zotgpt Rate Limits is the machine-readable rate-limit profile for ZotGPT (UC Irvine) on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 6 rate-limit definitions, measuring usd-spend, usd-credits, usd-budget, and requests-per-minute.
The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.
Tagged areas include Generative AI, Rate Limiting, Budget, and Higher Education.