PANews, citing OpenAI Developers, said that OpenAI API supports 12-hour prompt caching. PANews said Tibo added that Codex and Work cache for logged-in users will be retained permanently.
Relevant OpenAI teams said they had worked with OpenCode to restore services for affected OpenAI API users and refund credits consumed during the attack. Previously,OpenCode said that its Console suffered a large-scale model-distillation attack, with approximately 1.4%users affected.
