Model in 📝Claude Code refers to the specific 📝Claude model the session runs on — Opus, Sonnet, or Haiku — switched via the /model slash command, with different cost, latency, and context window characteristics per tier.
As of 2026, the active Claude family in Claude Code is Opus 4.7 (claude-opus-4-7), Sonnet 4.6 (claude-sonnet-4-6), and Haiku 4.5 (claude-haiku-4-5). Each model has a base 200K 📝context window; Opus 4.7 additionally ships a 1M-context variant accessed via the [1m] suffix (claude-opus-4-7[1m]) for sessions that need to hold entire large codebases or long-running multi-document workflows.
Choosing the right model is a per-session decision balancing capability, speed, and cost. Opus is the most capable — used for complex reasoning, large refactors, deep planning, and architecture decisions — and the slowest and most expensive. Sonnet is the middle path, fast enough for interactive work and capable enough for most coding tasks, and the default for many practitioners. Haiku is fastest and cheapest, suited for high-volume mechanical tasks, simple edits, and high-throughput scripted automation where deep reasoning isn't needed.
Switching models in-session happens via the /model slash command, which routes future turns to the selected model while preserving conversation state. Some practitioners run multi-model workflows: Opus for planning in 📝Plan Mode, Sonnet for implementation, Haiku for batch operations. The /fast slash command toggles a fast-output mode on Opus 4.6 and 4.7 that delivers Opus quality at improved latency without changing the model selection.