Arize AX vs Arize Phoenix
Arize AX
arize.comArize Phoenix
arize.comSide by side
| Figure | Arize AX | Arize Phoenix |
|---|---|---|
| Price from | $50/mo | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 3 | 1 |
| Spec score · Machine Learning Model Monitoring Software | 8.3 (#6) | 8.0 (#8) |
| Spec score · Llm Monitoring | 8.4 (#10) | 8.1 (#12) |
| Spec score · AI Agent Observability Tools | 8.3 (#12) | 8.0 (#19) |
| Spec score · AI LLM Observability Tools | 8.4 (#9) | 8.1 (#14) |
| Spec score · LLM Observability Tools | 8.4 (#11) | 8.1 (#16) |
| Spec score · Model Monitoring Software | 8.4 (#11) | 8.1 (#16) |
| Purpose | Arize AX is a platform for continuous improvement of AI agents that turns production behavior into better agents. | Phoenix helps teams trace, evaluate, debug, and improve AI applications. |
| Support | AX Free includes community troubleshooting support, AX Pro includes email support and AX Enterprise includes dedicated support. | The Phoenix documentation points users to a Slack community for questions and developer discussion. |
Plans
In their own words
Arize AX
Arize AX is a platform for improving AI agents by turning production behavior into investigations, evaluations, and experiments. Signal surfaces important issues, helps identify causes, and prepares fixes for review. Managed Agents can investigate failing traces, fix repository bugs, automate recurring checks, or be created from scratch. Swarm Observability tracks status and performance across an agent swarm in real time. Agent-as-a-Judge uses telemetry to produce scalable evaluations that can surface unknown failures, while end-to-end experiments help validate changes. Integrations include OpenAI, Anthropic, Google GenAI, Amazon Bedrock, LangChain, LangGraph, LlamaIndex, CrewAI, and Vercel AI SDK; tracing follows OpenInference conventions and OpenTelemetry. AX Free costs nothing and includes 10 Signal issues/month, 25k trace spans/month, 1 GB ingestion/month, and 15-day retention. AX Pro costs $50 a month, with 25 Signal issues/month, 50k trace spans/month, 10 GB ingestion/month, and 30-day retention. Enterprise pricing is custom. Self-hosted deployment keeps observability data, authentication, APIs, and UI within customer infrastructure; air-gapped deployment is available.
Arize Phoenix
Arize Phoenix is free, open-source software for tracing, evaluating, debugging, and improving AI applications. It captures model calls, retrieval, tool use, and custom logic as OpenTelemetry traces. Teams can score traces and spans with LLM evaluators, code checks, or human labels. Prompt tools provide versioning, side-by-side testing, and call replay, while dataset experiments compare evaluation results across application versions. Documented integrations include LlamaIndex, LangChain, DSPy, OpenAI, Bedrock, and Anthropic, plus evaluation libraries such as Harbor, Ragas, Cleanlab, and MLflow. Phoenix runs locally or can be self-hosted with Docker, Kubernetes, or a cloud environment; Arize says self-hosting keeps traces in the user’s environment. Self-hosted authentication supports OAuth2 identity providers with an OpenID Connect well-known endpoint. The Phoenix plan costs nothing and leaves trace spans, ingestion, projects, and retention under user management. The project is ELv2 licensed and built by Arize AI and the open-source community.