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.


Plugins extend Amp with new tools, commands, and agent modes. These experimental modes are how we evaluate new models, and we're sharing them so you can, too. Fork and modify the plugins to run your own experiments.
Learn how plugins workThinking Machines' open-weight multimodal model
Moonshot AI's agentic coding model
xAI's flagship coding and agent model
Anthropic's Mythos class coding model
Z.ai's open-weight coding model, hosted by Amp
See which models you can use in a custom agent:
Evals, caveats, and rollout notes behind Amp’s model choices.
See the Amp Security Reference for more details on model use and inference providers.