| Price from | $99/mo | — |
| Free plan | — | — |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 3 | 0 |
| Spec score · Prompt Management Software | 8.2 (#9) | 7.3 (#23) |
| Caching | The service offers configurable caching for repeated inputs, with cache TTL set per endpoint. | Request caching can be enabled with the X-Pezzo-Cache-Enabled header; cached requests expire after three days by default, and that duration is not configurable. |
| Integrations | The site lists Next.js, Vercel AI SDK, LangChain, and OpenAI as integrations. | Pezzo documents LangChain integration for observability and monitoring, with Node.js and Python examples. |
| Observability | Request logs include prompt hash, model, tokens, cost, and latency, and requests can be replayed. | Pezzo traces requests and collects LLM metrics including execution time, cost, and error rate. |
| Product | Endprompt provides versioned, tested, and observable LLM endpoints with typed input and output schemas. | Pezzo is an open-source toolkit for AI development. |
| Prompt management | Prompt changes are automatically versioned, can be promoted from draft to live, and can be rolled back. | Pezzo provides centralized prompt management, editing, testing, and versioning. |