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

Unconstrained state-of-the-art model use

Claude Opus 4.7

Faster and cheaper, for small, well-defined tasks

Claude Haiku 4.5

Deep reasoning with extended thinking

Subagents

Bug identification & code review assistance

Fast, accurate codebase retrieval

Oracle

Complex reasoning & planning on code

Librarian

Large-scale retrieval & research on external code

Claude Sonnet 4.6

System Models

Image, PDF, and media file analysis

Image generation and editing

Gemini 3 Pro Image

Fallback context analysis for task continuation

Fast title generation for threads

Claude Haiku 4.5

Model Cards

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

GPT 5.5

GPT-5.5 now powers deep mode. It is more capable, but can cost more.

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