Overview
Presets encode provider defaults; dialect names become shell commands. The recommended command name is a convention — each provider can have multiple independently named dialects.
Use codex-sol for GPT-5.6 Sol as both the main and subagent model:
cc-dialect create cc-codex --preset codex-sol
cc-dialect auth cc-codex codex
cc-dialect shim install cc-codex
cc-codex
Use --preset codex instead to make GPT-5.6 the main model while retaining Sol, Terra, and Luna for the opus, sonnet, and haiku menu entries. Both routes authenticate through ChatGPT OAuth.
GLM uses Z.ai's Anthropic-compatible API and current GLM-5.2 flagship:
export ZAI_API_KEY="your_zai_api_key"
cc-dialect create cc-glm --preset glm
cc-dialect shim install cc-glm
cc-glm
Maps opus → glm-5.2, sonnet → glm-5-turbo, haiku → glm-4.5-air. GLM-5.2 accepts high or max effort.
Kimi authenticates through Moonshot's OAuth flow:
cc-dialect create cc-kimi --preset kimi
cc-dialect auth cc-kimi kimi
cc-dialect shim install cc-kimi
cc-kimi
The rolling kimi preset uses Kimi K3 as its main model. Keep effort at auto — K3 uses max by default. sonnet and haiku select Kimi K2.7 Code Highspeed and Kimi K2.6.
Gemini uses Google OAuth through CLIProxyAPI's Antigravity provider:
cc-dialect create cc-gemini --preset gemini
cc-dialect auth cc-gemini antigravity
cc-dialect shim install cc-gemini
cc-gemini
Uses gemini-pro-agent as main and opus model, with Gemini 3.5 Flash variants for lower tiers.
xAI authentication is shared, but each model family gets its own preset and can have its own dialect:
# Grok 4.5
cc-dialect create cc-grok --preset grok
cc-dialect auth cc-grok xai
cc-dialect shim install cc-grok
# Grok Build
cc-dialect create cc-grok-build --preset grok-build
cc-dialect auth cc-grok-build xai
cc-dialect shim install cc-grok-build
# Composer 2.5 Fast (via xAI Grok Build)
cc-dialect create cc-composer --preset composer
cc-dialect auth cc-composer xai
cc-dialect shim install cc-composer
cc-grok # or cc-grok-build / cc-composer
composer uses Cursor Composer 2.5 Fast as exposed by xAI Grok Build — not a Grok foundation model.
export MINIMAX_API_KEY="your_minimax_api_key"
cc-dialect create cc-minimax --preset minimax
cc-dialect shim install cc-minimax
cc-minimax
Maps every Claude Code model alias to MiniMax-M2.7.
export DEEPSEEK_API_KEY="your_deepseek_api_key"
cc-dialect create cc-deepseek --preset deepseek
cc-dialect shim install cc-deepseek
cc-deepseek
Main, subagent, and opus → deepseek-v4-pro; sonnet and haiku → deepseek-v4-flash.
Cursor dialects use a local OpenAI-compatible bridge backed by the official @cursor/sdk:
cc-dialect cursor install
export CURSOR_API_KEY="your_cursor_api_key"
cc-dialect create cc-cursor --preset cursor-composer
cc-dialect shim install cc-cursor
cc-cursor
# Check bridge status
cc-dialect cursor status
cc-dialect models cc-cursor
Available presets:
cursor-composer — Composer 2.5 with Fast/Standard menu mappings
cursor-composer-fast — explicitly forces Composer 2.5 Fast
cursor-grok — Cursor Grok 4.5
cursor-auto — Cursor's auto selection
ℹ SDK bridge details
Each Cursor dialect reserves two localhost ports: one for the embedded proxy and one for the SDK bridge. Tools are forwarded with cc_tool_ schema aliases to prevent Composer from calling Cursor-native schemas. Claude Code permission prompts remain in control.
Install and authenticate the Copilot SDK once:
cc-dialect copilot install
cc-dialect copilot login
cc-dialect copilot status
cc-dialect copilot models
Create a general Copilot dialect:
cc-dialect create cc-copilot --preset copilot-auto
cc-dialect shim install cc-copilot
cc-copilot
Available presets: copilot-auto, copilot-mai (MAI-Code-1-Flash), copilot-codex, copilot-claude, copilot-gemini.
The claude preset routes Claude Code through the embedded proxy with a separate Anthropic OAuth login:
cc-dialect create cc-claude --preset claude
cc-dialect auth cc-claude claude
cc-dialect shim install cc-claude
cc-claude
Unlike a native shortcut, cc-claude has private settings, credentials, and history. Maps main and opus to Claude Fable 5, with Sonnet 4.6 and Haiku 4.5 for lower tiers.