Models

Esan runs on three model tiers. You don’t have to choose — Esan picks the right one for each task, using the light model for routine steps and reaching for a stronger one when the work needs it. You can always push a task to a more capable model.

Esan Mini

Fast and light

The quick one. Instant answers, short drafts, simple lookups and the routine steps inside a bigger task. Low cost, so it does the everyday work without you thinking about it.

Best for

  • Quick questions and rewrites
  • Simple lookups and summaries
  • The routine steps of a larger job

Esan Pro

The everyday workhorse

Strong reasoning for real work — research, coding, analysis, planning. The default for most tasks: capable enough to be trusted, efficient enough to run all day.

Best for

  • Research and multi-step tasks
  • Writing and editing code
  • Turning data into clear takeaways

Esan Max

The most capable

Reserved for the hardest, longest, highest-stakes work — deep reasoning, long autonomous runs, and the moments where getting it exactly right matters more than speed.

Best for

  • Complex, long-running work
  • The trickiest reasoning
  • High-stakes output you can’t redo

Which tiers you can reach depends on your plan. See plans →

Models — Esan