Tips: GPT-6 不计算 「缓存写入」费用，并且 1M 上下文不加价

GPT-6 Astra usage in Codex does not incur additional long-context multipliers above 272K input tokens. Codex does not charge for cache writes.


https://help.openai.com/en/articles/20001415-chatgpt-rate-card-enterprise-token-based-pricing
OpenAI Help Center
ChatGPT Rate Card (Enterprise token-based pricing) | OpenAI Help Center
Learn how token rates work for ChatGPT models and features across Chat, ChatGPT Work and Codex
 
 
Back to Top