What is Phoenix?
Latest launch
Summary
Phoenix is an Arize-maintained AI observability and evaluation tool with prompt and dataset tooling.
- Category
- Agent infra
- Pricing
- Not stated in the sources on this page.
Phoenix lives in the GitHub repository Arize-ai/phoenix, whose description reads "AI Observability & Evaluation". The repository was created on 2022-11-09 and lists topics including ai-observability, evals, llm-evaluation, langchain, llamaindex, openai and anthropic.
According to its docs, Phoenix covers evaluation and prompt work. Evaluation features include "LLM-based evaluations — Run pre-built or custom evaluators on your data" and evaluator integrations to "Use Phoenix evals, or bring your own from Ragas, Deepeval, or Cleanlab". On the prompt side, the docs list "Prompt Management — Version, store, and deploy prompts", a "Prompt Playground — Experiment with prompts and models side-by-side", and "Span Replay — Debug by replaying LLM calls with different inputs". Datasets and experiments are also covered: "Run Experiments — Compare different versions of your application".
The sources do not state a license, pricing, or MCP support, so those are left open here. For related tools, see the Agent infra category, the guide Opik vs Langfuse: open-source LLM observability compared, and the launch note Langfuse v4.57.0 adds FIPS auth and API key expiration. Source docs: Phoenix docs and the GitHub repository.
Phoenix alternatives
| Tool | License | Pricing note |
|---|---|---|
PhoenixThis pagePhoenix is an Arize-maintained AI observability and evaluation tool with prompt and dataset tooling. | — | Not stated |
LangfuseOpen source platform for tracing, evaluating and improving AI agents and LLM applications. | MIT | Not stated |
OpikOpen-source platform for tracing, evaluating and optimizing LLM applications and agents. | Apache-2.0 | Not stated |
Launches and updates
Phoenix v20.21.0 adds Mistral AI cost tracking
PhoenixArize Phoenix v20.21.0, released October 11, 2026, adds Mistral AI model pricing to cost tracking and fixes evaluator metadata loss.
Category: Agent infra
Pricing: Not stated
Guides covering Phoenix
Questions
What is Phoenix?
The GitHub repository Arize-ai/phoenix is described as "AI Observability & Evaluation". Its docs list features such as LLM-based evaluations, prompt management, a prompt playground, span replay, datasets and experiments.
Is Phoenix open source?
Not stated in the cited sources. The excerpts say the GitHub API does not report a recognized license for the repository, so no license is claimed here.
How is Phoenix used?
According to its docs, you can create datasets by collecting traces or uploading from code/CSV, run experiments to compare different versions of your application, and attach evaluators to datasets so they run automatically during experiments.