Niluxv1.0.11
/models

Models.

Nilux offers two model tiers. Pick the one that fits the task — you can switch mid-session at any time.

Standard

The default. Fast, capable, and cost-effective for most coding tasks.

  • Best for: everyday coding, codebase exploration, bug fixes, feature work
  • Context window: 1M tokens

Pro

Deep reasoning model for complex problems that require thorough analysis.

  • Best for: architecture design, complex debugging, multi-file refactors, security auditing
  • Context window: 1M tokens

Switching models

Use /model inside a session to switch:

bash
❯/model
Select model:
  > Standard
    Pro
✓ Switched to Pro

Your choice is saved in ~/.nilux/config.json and persists across sessions.

Choosing the right model

  • Quick code question → Standard
  • Complex debugging → Pro
  • Architecture planning → Pro
  • Daily development → Standard
  • Security auditing → Pro
  • Simple refactoring → Standard

Pricing

Both models use pay-per-use pricing — you pay only for tokens consumed. Smart caching reduces input costs significantly in active sessions. See the pricing page for current rates and an interactive calculator.

TIP

Start with Standard for most tasks. Switch to Pro when you need deeper reasoning or are working on architecture-level decisions.

← Previous · Permission modesNext · Billing →