⌖ AI Field Guide

Sourced determinations on AI engineering practices · last reviewed 2h ago

  1. Fixed manual budget_tokens thinking budget on every request outdated prompting reviewed 2h ago

    Setting a static thinking.budget_tokens value on every API request to control how much a model reasons before answering -- the original mechanism for extended thinking on Claude 4-era models.

    Superseded by adaptive-thinking-effort-control

    Why this verdict?

    Anthropic has deprecated this on Claude 4.6 models and removed it entirely on Claude 4.7+, where requests using type: 'enabled' now return a 400 error, in favor of adaptive thinking plus the effort parameter. Still required on models that only support extended-thinking mode (Opus 4.5, Haiku 4.5, Sonnet 4.5 and earlier), so not dead everywhere, but no longer the recommended path for new work.