ThinkingTokenBudget
Maximum number of thinking tokens before the model must answer (-1 means no limit). Self-hosted backends only. vLLM rejects values other than -1 unless the model is started with `--reasoning-parser`.
Maximum number of thinking tokens before the model must answer (-1 means no limit). Self-hosted backends only. vLLM rejects values other than -1 unless the model is started with --reasoning-parser.
This type has no documented properties.
We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.