Skip to main content

​
Overview

Global options can be used with any Codex CLI command. They are processed before subcommands and affect the behavior of the entire CLI session.

​
Configuration Override

​
-c, --config
string
Override configuration values using key=value pairs. Can be specified multiple times.Examples:
codex -c model=gpt-4.1 -c sandbox_mode=workspace-write
codex exec -c features.js_repl=true "test the app"
Common configuration keys:
  • model - Override the AI model
  • sandbox_mode - Control sandbox restrictions
  • approval_policy - Set approval mode
  • features.<name> - Toggle feature flags

​
Profile Selection

​
-p, --profile
string
Select a configuration profile from config.tomlExample:
codex --profile production
codex exec --profile experimental "refactor utils"
Profiles allow you to maintain different sets of configuration for different use cases (development, production, experimental, etc.).

​
Working Directory

​
-C, --cwd
path
Change the working directory before executing the commandExample:
codex -C /path/to/project "fix tests"
codex --cwd ~/projects/app exec "run linter"

​
Model Selection

​
-m, --model
string
Specify the AI model to use for the sessionExample:
codex -m gpt-4.1
codex --model o4-mini "explain this code"
Common models:
  • o4-mini - Fast, efficient reasoning model (default)
  • gpt-4.1 - Advanced reasoning and coding
  • o3 - Advanced reasoning model with extended thinking

​
Open Source Models

​
--oss
boolean
Use open-source models instead of proprietary modelsExample:
codex --oss "help me debug"

​
Sandbox Control

​
--sandbox
enum
Control the sandbox mode for command executionOptions:
  • workspace-write - Allow writes within the workspace directory
  • full-access - Allow full filesystem access (use with caution)
Example:
codex --sandbox workspace-write
codex exec --sandbox full-access "system diagnostic"

​
Approval Policy

​
--ask-for-approval
enum
Set when the agent should ask for approval before executing commandsOptions:
  • on-request - Ask for approval when the agent requests it
  • always - Always ask before executing any command
  • never - Never ask (use with caution)
Example:
codex --ask-for-approval always
codex exec --ask-for-approval never "run tests"
​
--full-auto
boolean
Enable fully automatic mode (equivalent to --ask-for-approval never)Example:
codex --full-auto "create a todo app"
In full-auto mode, commands execute automatically. Use in sandboxed environments or Git-tracked directories.
​
--dangerously-bypass-approvals-and-sandbox
boolean
Bypass both approval prompts and sandbox restrictions
DANGEROUS: This option removes all safety guardrails. Only use in completely isolated test environments.
​
--search
boolean
Enable web search capabilities for the agentExample:
codex --search "find the latest React best practices"

​
Image Input

​
-i, --images
string
Provide image files as input (comma-separated paths)Example:
codex -i screenshot.png "implement this UI"
codex --images "design.png,mockup.png" "create components"

​
Directory Context

​
--add-dir
string
Add directories to the agent’s context (can be specified multiple times)Example:
codex --add-dir src --add-dir tests
codex --add-dir lib "explain the architecture"

​
Version Information

​
--version
boolean
Display the Codex CLI versionExample:
codex --version
​
--help
boolean
Display help informationExample:
codex --help
codex exec --help

​
Combining Options

Global options can be combined to create powerful workflows: 
codex -m gpt-4.1 --profile dev -C ~/project --search

​
Order of Precedence

When the same option is specified in multiple places, Codex uses this priority:
  1. Command-line flags (highest priority)
  2. -c config overrides
  3. Environment variables
  4. Profile settings (from --profile)
  5. config.toml base configuration
  6. Built-in defaults (lowest priority)

Feature Flags

Enable experimental features

Configuration

Learn about config.toml