Set and apply per-model thinking levels from Pi's native settings.

Auto-set thinking levels per model/provider in pi

Set and apply per-model thinking levels from Pi's native settings.

Native /effort, /continue, /sessions (/recap) commands for pi — set thinking levels, resume interrupted steps, cross-session directory recap, and redirect git worktrees

DSH host plugin: thinking-level (reasoning_effort) control for dsh — auto-adjust per tool round, with optional manual lock and per-tool timing telemetry.

DSH plugin: auto-detect thinking levels (reasoningEfforts) for custom models in llm-pi-ai settings.

DeepInfra provider for pi: dynamic model catalog, reasoning-effort thinking levels, vision, session usage + monthly billing footer

Shared, machine-local model profiles (ordered model candidates with thinking levels) for Pi extensions.

Model Capability Manager for DSH Web: per-model thinking levels, context window, output caps, input modalities, gateway compat, route defaults, one-click presets, EN/中文 UI.

Pi extension: a model picker that shows context size, price, thinking levels, and key state, with starred models in your own order

Pi extension to set global or per-session models and thinking levels for subagents.

Switch and persist thinking levels for pi models

Complete model providers for pi — Alibaba Model Studio (Plan subscription + Cloud pay-per-token, Anthropic + OpenAI + Responses API shapes, native thinking levels. Qwen 3.8/3.7/3.6, DeepSeek V4, Kimi K2.6/K2.7, GLM-5.1/5.2, MiniMax M2.5) and DeepSeek offi

Per-model default thinking levels for pi: auto-apply a pinned thinking level whenever you switch models (Ctrl+P, /model, selector, session restore).

Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models

The complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.8 Max, Qwen 3.7/3.6, DeepSeek V4 Pro, Kimi K3, GLM-5, MiniMax M3.

Manage multiple OpenAI/Anthropic-compatible API relays in pi: switch relays, pull model lists, manage API keys, and wire thinking levels (shift+tab) through to the relay.

Pi coding agent extension — interactive table of your scoped models with pricing, context window, thinking levels, modalities, and coding benchmarks

A keyboard-first Pi extension for switching GPT-5.6 capability models and thinking levels within the active provider.

dsh web 插件「模型定制工作台」: per-route/per-model model customization UI (input modalities, thinking levels, extra request params) over the llm-pi-ai / llm-deepseek settings sections