GEPA vs GEPAzilla
GEPA
gepa-ai.github.ioGEPAzilla
gepazilla.comSide by side
| Figure | GEPA | GEPAzilla |
|---|---|---|
| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 0 |
| Spec score · AI Prompt Generators | 8.6 (#4) | 7.3 (#20) |
| License | The GitHub repository lists the project under the MIT license. | The repository states that GEPAzilla is released under the MIT License. |
| Model access | GEPA can optimize API-only models such as GPT, Claude, and Gemini without requiring access to model weights. | The project requires users to supply an AI Gateway API key for GEPA runs, scorer previews, and model discovery; its README specifies Vercel AI Gateway. |
| Purpose | GEPA is a framework for optimizing prompts, code, agent architectures, configurations, and other text parameters against evaluation metrics. | GEPAzilla is an open-source GEPA prompt optimizer that uses datasets and custom metrics to find stronger prompts. |
Plans
In their own words
GEPA
GEPA is a free, open-source Python package for optimizing prompts, code, configurations, agent architectures, policies, and other text-based artifacts. Its optimize_anything API connects to any system through an evaluator you write, so DSPy or another framework is not required. GEPA examines execution traces and evaluator feedback, uses language-model reflection to diagnose problems and propose targeted mutations, then selects candidates with Pareto-aware criteria. It can optimize API-only GPT, Claude, and Gemini models without model-weight access. Human-readable traces explain changes and support agent debugging. Built-in adapters cover Default, Confidence, DSPy Full Program, Generic RAG, MCP, TerminalBench, AnyMaths, and LangChain, with integrations including MLflow, Comet ML Opik, Pydantic AI, and cookbook projects. You can limit metric calls and set several stopping conditions. GEPA works through API or self-hosted deployment, installs with pip, and uses the MIT license.