Reasoning Levels and Fast Mode

Last updated 2026-11-14

The shared reasoning scale, how each session sets its level, and the fast-mode toggle.

Reasoning levels

go-llm-router normalizes reasoning onto one scale — none, low, medium (default), high, xhigh, max — and maps it per provider (Claude thinking budgets, Gemini thinking budgets, OpenAI effort, ...). Aliases minimal, extra, and ultra map to low, xhigh, and max. Levels outside a model's supported range are clamped rather than rejected. When a provider still rejects the level (an error that names thinking, reasoning or effort as unsupported or invalid), since v1.3.0 the same model is retried one level away — down from medium and above, up from below medium, keeping that direction — up to three times.
The level is passed explicitly through each Send call; there is no global reasoning setting in config.json. Each session has its own level — auto (the default) or a fixed one — set with /model → reasoning or cycled with Shift+A / Shift+D in the TUI, auto included. With auto, the level comes from the selector's work kind (the LLM dispatcher or the decision model, whichever answers first), falling back to medium when it returned none; this also applies to a session pinned to a model. A level passed with the request (for example reasoning_effort) wins over both.
Auto reasoning (auto_reasoning, v1.0.18 to v1.0.27) was a global TypeSafe-only toggle; it was removed in v1.1.0 and replaced by the per-session auto level above. The auto_reasoning field of POST /v1/model and GET /v1/session/:id is gone.

Fast mode

Shift+F toggles fast mode, which passes core.ModeFast through the router so supported backends request a faster service tier. Support is model-specific (core.SupportFast) — for example recent OpenAI generations, Claude Opus 4.8 / Opus 5, most Grok models, and selected Gemini families. Unsupported models silently fall back to the default tier. Fast mode is process-local and not persisted; since v1.2.0 the TUI sends its fast-mode state with each run to the daemon, so the toggle applies to that window's runs only.