Models

Amp uses the best model for each task: leading generalist foundation models for complex reasoning and planning, and smaller specialized models for fast, accurate responses in specific domains.

Agent Modes

Combination of System Prompt + Tools + Model

Low
Fast, low-cost mode for small, well-defined tasks
GLM-5.2
Medium
Balanced intelligence, speed, and cost for most tasks
GPT-5.6 Sol
High
Deep reasoning for hard tasks
GPT-5.6 Sol
Ultra
The most capable mode for hard, open-ended tasks
Claude Fable 5

Which modes are people using in Amp?

Everyone
JUL 11
JUL 12
JUL 13
JUL 14
JUL 15
Amp Team
JUL 11
JUL 12
JUL 13
JUL 14
JUL 15
low
medium
high
ultra

Agent Mode Plugins

Plugins extend Amp with new tools, commands, and first-class agent modes you can select like any built-in mode.

Learn how plugins work

Claude Fable 5

Anthropic's Mythos class coding model

GLM 5.2

Z.ai's open-weight coding model, hosted by Amp

Smart

The deprecated Smart mode: Claude Opus 4.8 with high reasoning

Deep

The deprecated Deep mode: GPT-5.5 with medium reasoning

Rush

The deprecated Rush mode: GPT-5.5 with no reasoning

Large

The deprecated Large mode: long-context Claude Opus 4.8

Model Cards

Evals, caveats, and rollout notes behind Amp’s model choices.

GPT 5.5

It is more capable than GPT-5.4, but can cost more.

Read card

See the Amp Security Reference for more details on model use and inference providers.