Skip to main content
Mux supports multiple AI providers. Configure provider API keys in Settings → Providers — see Providers for setup.

​
First-class Models

Mux ships with curated models kept up to date with the frontier. Use any custom model with /model <provider:model_id>.
ModelIDAliasesDefault
Fable 5anthropic:claude-fable-5fable
Mythos 5anthropic:claude-mythos-5mythos
Opus 4.8anthropic:claude-opus-4-8opus✓
Sonnet 5anthropic:claude-sonnet-5sonnet
Haiku 4.5anthropic:claude-haiku-4-5haiku
GPT-5.6 Solopenai:gpt-5.6-solgpt, sol
GPT-5.6 Terraopenai:gpt-5.6-terraterra
GPT-5.6 Lunaopenai:gpt-5.6-lunaluna
GPT-5.5 Proopenai:gpt-5.5-progpt-pro, gpt-5.5-pro
GPT-5.4 Miniopenai:gpt-5.4-minigpt-mini
GPT-5.4 Nanoopenai:gpt-5.4-nanogpt-nano
Codex 5.3openai:gpt-5.3-codexcodex, codex-5.3
Spark 5.3openai:gpt-5.3-codex-sparkspark
Codex Mini 5.1openai:gpt-5.1-codex-minicodex-mini
Codex Max 5.1openai:gpt-5.1-codex-maxcodex-max
Gemini 3.1 Pro Previewgoogle:gemini-3.1-pro-previewgemini, gemini-pro
Gemini 3.5 Flashgoogle:gemini-3.5-flashgemini-flash
Grok 4 1 Fastxai:grok-4-1-fastgrok, grok-4, grok-4.1, grok-4-1
Grok Code Fast 1xai:grok-code-fast-1grok-code
DeepSeek V4 Prodeepseek:deepseek-v4-prodeepseek, deepseek-pro, deepseek-v4, deepseek-v4-pro
DeepSeek V4 Flashdeepseek:deepseek-v4-flashdeepseek-flash, deepseek-v4-flash

​
Pro reasoning mode (GPT-5.6)

Every GPT-5.6 model (Sol, Terra, and Luna) supports OpenAI’s pro reasoning mode. Toggle the PRO badge next to the thinking slider (or run “Toggle Pro Reasoning Mode” from the Command Palette) to send reasoning.mode: "pro" with each request. The setting is saved per workspace. Pro mode uses the same per-token pricing but consumes more tokens and responses can take noticeably longer. Requests routed through non-passthrough gateways (e.g. OpenRouter, GitHub Copilot) fall back to standard mode.

​
Model Selection

Keyboard shortcuts:
  • Cycle models
    • macOS: Cmd+/
    • Windows/Linux: Ctrl+/
To choose a specific model, click the model pill in the chat footer. Alternatively, use the Command Palette (Cmd+Shift+P / Ctrl+Shift+P):
  1. Type “model”
  2. Select “Change Model”
  3. Choose from available models
Models are specified in the format: provider:model-name

​
One-shot Overrides

Override the model or thinking level for a single message using slash commands. The override applies only to that message — workspace settings stay unchanged.

​
Syntax

CommandEffect
/sonnet explain this codeUse Sonnet for one message
/opus+high deep reviewUse Opus with high thinking
/haiku+0 quick answerUse Haiku at its lowest thinking level
/+2 analyze thisKeep current model, set thinking level 2

​
Thinking levels

Append +level to any model alias. Levels can be named (off, low, medium/med, high, max) or numeric (0–9). Numeric levels are model-relative — they map to the model’s allowed thinking range:
  • 0 = model’s lowest allowed level (e.g., off for Sonnet, medium for GPT-5.5 Pro)
  • Higher numbers select progressively higher levels, clamped to the model’s maximum
This means /sonnet+0 disables thinking while /gpt-pro+0 sets thinking to medium (GPT-5.5 Pro’s minimum). Use /+level (no model) to override thinking on the current model: /+0 quick answer

​
CLI

The mux run CLI accepts the same thinking levels via --thinking:

​
Next Steps

Configure Providers

Set up API keys for Anthropic, OpenAI, Google, and other providers.