Claude Code /model: switch models, aliases (opus, sonnet, haiku, opusplan), ANTHROPIC_MODEL and effort
How do I change the model Claude Code uses?
Run /model inside a session to open the picker, or /model sonnet to switch directly. At startup use claude --model opus, or set ANTHROPIC_MODEL or the model key in settings.json for a lasting default. Use /effort to trade reasoning depth for speed and cost.
Ways to set the model, in priority order
- During a session: /model <alias|name>, or /model with no argument to open the picker
- At startup: claude --model <alias|name>
- Environment variable: ANTHROPIC_MODEL=<alias|name>
- Settings: the model field in your settings file
- Default for new sessions: ANTHROPIC_DEFAULT_MODEL=<alias|name> (v2.1.236 or later)
In the /model picker, Enter switches and saves the choice as your default. Press s on a row to switch for this session only.
Start with Opus
claude --model opus
Switch mid-session
/model sonnet
settings.json
{
"model": "opus"
}Model aliases
- default: clears any override and returns to your account's default
- sonnet: latest Sonnet, for daily coding
- opus: latest Opus, for complex reasoning
- haiku: fast and efficient, for simple tasks
- sonnet[1m], opus[1m]: 1 million token context window variants
- opusplan: Opus during plan mode, then Sonnet for execution
- fable: the Fable model for your provider, for your hardest and longest-running tasks
- best: the model fable resolves to where Fable is available to you, otherwise the same model as opus
On the Anthropic API, opus, sonnet and haiku currently resolve to Opus 5.5, Sonnet 5.5 and Haiku 5.5. Some other providers resolve them to earlier versions. To pin a version, use the full model name such as claude-opus-5-5.
Pin aliases with environment variables
Each value must be a full model name or your provider's identifier.
- ANTHROPIC_DEFAULT_OPUS_MODEL: model for opus, and for opusplan in plan mode
- ANTHROPIC_DEFAULT_SONNET_MODEL: model for sonnet, and for opusplan outside plan mode
- ANTHROPIC_DEFAULT_HAIKU_MODEL: model for haiku and background functionality
- CLAUDE_CODE_SUBAGENT_MODEL: default model for subagents that are not assigned one
Shell
export ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-5-5
Adjust effort level
Opus 5.5, Sonnet 5.5 and Haiku 5.5 support low, medium, high, xhigh and max, and default to medium. Set it with /effort, --effort, CLAUDE_CODE_EFFORT_LEVEL, or the effortLevel settings key. /effort auto clears the saved level. max is session-only unless set through CLAUDE_CODE_EFFORT_LEVEL, and is not accepted by effortLevel.
Inside Claude Code
/effort high
Restrict models for a team
Admins can limit choices with availableModels in managed or policy settings. Add enforceAvailableModels to also restrict the Default option (v2.1.175 or later).
Managed settings
{
"availableModels": ["sonnet", "haiku"],
"enforceAvailableModels": true
}Sources
More Claude Code guides
- How to allow Claude Code to run all commands: permission modes, allow rules and skip permissions
- Claude Code permissions: allow, ask and deny rules, rule syntax and allowed tools
- Claude Code telemetry and data retention: what is sent and how to turn it off
- CLAUDE.md: where it goes, how it loads, and how it works with AGENTS.md
- Claude Code hooks: all events, exit codes, PreToolUse and PermissionRequest JSON, examples
- Claude Code subagents: create one, limit its tools, and call it
- Add MCP servers to Claude Code (claude mcp add, .mcp.json, scopes)
- Claude Code custom slash commands and skills (SKILL.md)
- Claude Code settings.json: file locations, precedence, and key settings
- Claude Code plugins and marketplaces: install, create, and share
- Claude Code headless mode: claude -p, --output-format json, --bare and CI flags
- Claude Code statusline: custom status bar in settings.json with context %, cost and git branch
- Claude Code /cost and /usage: check token spend, usage limits and reduce costs
- Claude Code VS Code extension: install, shortcuts, settings and /ide (works in Cursor too)
- MCP 2026-07-28 Migration Guide: Stateless Protocol, No Sessions, server/discover, MRTR, and SDK v2 Upgrade
- Subagents and Custom Agents Compared: Claude Code vs Codex vs Cursor vs Gemini CLI vs GitHub Copilot (2026)
- Allow all commands in any AI coding agent: Cursor, Claude Code, Codex, Gemini CLI, Copilot CLI and 7 more (2026)
- How to deploy a remote MCP server (Streamable HTTP): Cloudflare Workers, Vercel, Railway and more (2026)
- Claude Code sandbox: /sandbox, sandbox.enabled, allowedDomains, excludedCommands and strict mode
Reviewed Oct 18, 2026. Settings change often; the linked vendor docs are the source of truth.
Built an MCP server? Get it listed everywhere →
Shipping an Android app? Google Play needs 12 testers for 14 days first. Get them with Tester Exchange →