Models

Select and configure AI models in Mux

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>.

Model	ID	Aliases	Default
Opus 4.7	anthropic:claude-opus-4-7	opus	✓
Sonnet 4.6	anthropic:claude-sonnet-4-6	sonnet
Haiku 4.5	anthropic:claude-haiku-4-5	haiku
GPT-5.5	openai:gpt-5.5	gpt, gpt-5.5
GPT-5.5 Pro	openai:gpt-5.5-pro	gpt-pro, gpt-5.5-pro
GPT-5.4 Mini	openai:gpt-5.4-mini	gpt-mini
GPT-5.4 Nano	openai:gpt-5.4-nano	gpt-nano
Codex 5.3	openai:gpt-5.3-codex	codex, codex-5.3
Spark 5.3	openai:gpt-5.3-codex-spark	spark
Codex Mini 5.1	openai:gpt-5.1-codex-mini	codex-mini
Codex Max 5.1	openai:gpt-5.1-codex-max	codex-max
Gemini 3.1 Pro Preview	google:gemini-3.1-pro-preview	gemini, gemini-pro
Gemini 3.5 Flash	google:gemini-3.5-flash	gemini-flash
Grok 4 1 Fast	xai:grok-4-1-fast	grok, grok-4, grok-4.1, grok-4-1
Grok Code Fast 1	xai:grok-code-fast-1	grok-code
DeepSeek V4 Pro	deepseek:deepseek-v4-pro	deepseek, deepseek-pro, deepseek-v4, deepseek-v4-pro
DeepSeek V4 Flash	deepseek:deepseek-v4-flash	deepseek-flash, deepseek-v4-flash

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

Command	Effect
/sonnet explain this code	Use Sonnet for one message
/opus+high deep review	Use Opus with high thinking
/haiku+0 quick answer	Use Haiku at its lowest thinking level
/+2 analyze this	Keep 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:

mux run -t 0 "Quick fix"          # Lowest thinking for the model
mux run -t high "Deep analysis"   # Named level

Experimental Image Tools Model

Mux can expose experimental Image Tools for Exec agents. Enable them in Settings → Experiments → Image Tools.

The image model is configured separately from the chat model. The default is openai:gpt-image-2. Image Tools are OpenAI-only in this experiment and require OpenAI provider credentials in Settings → Providers.

image_generate creates raster images from text prompts. It supports prompt, image count, quality, and output format.

image_edit edits one existing PNG, JPEG, or WebP image by path. Because editing uploads the source file to the image provider, including embedded metadata, it is hidden unless you also enable Allow image uploads for editing under the Image Tools settings. Source images are sent as-is; Mux does not automatically redact screenshot contents or strip image metadata.

Generated and edited full-resolution images are saved as runtime artifacts. Copy selected final assets into the workspace when they should become project files.

Next Steps

Configure Providers

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