知识库提供英文与简体中文，以下为简体中文。
Codex
算。推理档位越高，消耗的额度越多。
OpenAI 把推理设置列在会增加用量的因素里，并说更高的 effort 会用掉更多额度，且不保证结果更好。ChatGPT 聊天里「高推理不改变每条消息的 credit 单价」是另一套按条计费的规则，不适用于 Codex。
官方原文
Different models can use different amounts of your allowance for the same task. Larger inputs and outputs, higher reasoning settings, Fast mode and tasks with multiple steps can also increase usage.Higher effort can use more of your allowance and does not always produce a better result.Higher reasoning effort can improve results for complex tasks, but it takes longer and uses more tokens.Claude
算。思考 token 按输出 token 计费，你看不到的那部分也算。
所有思考 token 都计入，包括折叠或被隐去的。effort 档位决定 Claude 思考多少；档位越高，越快撞到额度。Fable 模型始终使用扩展思考，关不掉。
官方原文
Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model.You are charged for all thinking tokens generated, even when collapsed or redacted.The effort level controls how much thinking Claude applies to a response. Higher effort means more thorough responses, but they take longer and use more tokens, so you'll reach your usage limits faster.实际影响
- 日常任务用默认档位，只给真正需要的问题调高。
- Claude Code：/usage 能看到最近是什么在消耗额度；effort 设置按会话生效。
官方原文于 2026-09-15 对照在线文档核对。