DistantNews
Support us
๐Ÿ‡น๐Ÿ‡ผ Taiwan /Technology

OpenAI lets Codex users save and trigger rate limit resets

From Liberty Times · () Chinese

Translated from Chinese, summarized and contextualized by DistantNews.

At a glance

News Sources not specified New plan
  • OpenAI has introduced a new feature for its AI coding assistant, Codex, allowing users to save and manually trigger rate limit resets.
  • This change offers greater flexibility for heavy users who previously had to wait for automatic resets.
  • Users can also earn rate limit resets by inviting friends to try Codex through a limited-time referral program.

OpenAI is enhancing its AI coding assistant, Codex, with a new feature designed to give users more control over their usage limits. Previously, Codex's rate limit resets were automatically managed by OpenAI, a system that could be inconvenient for users engaged in intensive coding sessions who might hit their limits unexpectedly.

The new mechanism allows users to save their rate limit resets and activate them manually when needed. This permanent change means users are no longer bound by a fixed reset schedule and can instead trigger a reset precisely when they require a significant burst of Codex's capabilities. The feature is available across various ChatGPT subscription tiers, including Go, Plus, Pro, and Business.

To introduce the new system, OpenAI is providing all eligible accounts with one complimentary rate limit reset. Additionally, a two-week promotional campaign offers users the chance to earn additional resets. By inviting friends to experience Codex, users can gain one reset per successful referral, with a maximum of three resets available through this program. Both the referrer and the referred user benefit from this offer, though the invited friend must not have used Codex in the past two months.

DistantNews Editorial

Originally published by Liberty Times in Chinese. Translated, summarized, and contextualized by our editorial team with added local perspective. Read our editorial standards.