The whole hunk
from line 304, old and new numbered
/
lines
from line 304
304304
305305### Adjust extended thinking
306306
307Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model. For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, disabling thinking in `/config`, or, on models with a [fixed thinking budget](/docs/en/model-config#adaptive-reasoning-and-fixed-thinking-budgets), lowering the budget by setting the `MAX_THINKING_TOKENS` [environment variable](/docs/en/env-vars), for example `MAX_THINKING_TOKENS=8000`. Adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead. Disabling thinking is not available on Fable models, which always use extended thinking.
307Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the default budget can be tens of thousands of tokens per request depending on the model.
308
309For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, or by disabling thinking in `/config`. You can't turn off thinking on Fable models, which always use extended thinking.
310
311On models with a [fixed thinking budget](/docs/en/model-config#adaptive-reasoning-and-fixed-thinking-budgets), you can also lower the budget by setting the `MAX_THINKING_TOKENS` [environment variable](/docs/en/env-vars), for example `MAX_THINKING_TOKENS=8000`. Adaptive-reasoning models ignore nonzero budgets, so use effort levels there instead.
308312
309313### Delegate verbose operations to subagents
310314