The wiki is available in English and Simplified Chinese. Showing English.
Codex
Yes. Higher reasoning effort uses more of your allowance.
OpenAI lists reasoning settings among the things that raise usage, and says a higher effort can use more allowance without guaranteeing a better result. The ChatGPT chat rule that a higher reasoning effort does not change the per-message credit rate is a separate scheme and does not apply to Codex.
What the official docs say
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
Yes. Thinking tokens are billed as output tokens, even the ones you never see.
Every thinking token counts, including collapsed or redacted ones. The effort level sets how much thinking Claude applies; higher effort reaches the limit faster. Fable models always use extended thinking and cannot turn it off.
What the official docs say
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.In practice
- Keep the default effort for routine work and raise it only for the problem that needs it.
- Claude Code: /usage shows what has been drawing on your limits; the effort setting is per session.
Quotes checked against the live docs on 2026-09-15.