- Home
- Machine Learning Model Monitoring Software
- Arize Phoenix
Arize Phoenix
What it is
Arize Phoenix helps teams trace, evaluate, debug, and improve AI applications. It captures model calls, retrieval, tool use, and custom logic in traces that can be sent through OpenTelemetry. Teams can score traces and spans using LLM-based evaluators, code checks, or human labels, then rerun datasets across application versions to compare results. Prompt tools support versioning, side-by-side testing, and replaying calls to inspect output changes. Documented integrations include LlamaIndex, LangChain, DSPy, OpenAI, Bedrock, and Anthropic; evaluation libraries include Harbor, Ragas, Cleanlab, and MLflow. Phoenix can run locally or be self-hosted with Docker, Kubernetes, or a cloud environment. Arize says self-hosting keeps traces in the user’s environment. The project is free and open source under the ELv2 license, with users managing trace spans, ingestion volume, projects, and retention. Self-hosted authentication supports OAuth2 identity providers with an OpenID Connect well-known configuration endpoint. Phoenix is built by Arize AI and the open-source community.
For and against
For
- Free and open source
- Supports OpenTelemetry trace ingestion
- Includes prompt versioning and call replay
- Can run locally or be self-hosted
Against
- Users manage ingestion volume and retention
- Self-hosted OAuth2 providers need an OpenID Connect configuration endpoint
The verdict
Phoenix offers tracing, evaluation, and prompt tools without a listed price. Teams choosing self-hosting should plan to manage their own usage limits and retention.
Who it suits
Phoenix suits teams that need to inspect AI application traces and compare evaluation results across versions. It also fits teams that want to run locally or keep traces in their own self-hosted environment.
Plans and prices
Phoenix
Free and open source · self-hosted · user-managed trace spans, ingestion, projects, and retention
Read 5 Oct 2026 · arize.com
On the record
- Authentication
- Self-hosted Phoenix supports authentication and OAuth2 identity providers that expose an OpenID Connect well-known configuration endpoint.arize.com · read 5 Oct 2026
- Data control
- Arize says self-hosting keeps traces in the user’s own environment.arize.com · read 5 Oct 2026
- Deployment
- Phoenix can run locally or be self-hosted using Docker, Kubernetes, or a cloud environment.arize.com · read 5 Oct 2026
- Evaluation integrations
- Phoenix can use evaluation libraries including Harbor, Ragas, Cleanlab, and MLflow.arize.com · read 5 Oct 2026
- Evaluations
- Teams can score traces and spans with LLM-based evaluators, code checks, or human labels.arize.com · read 5 Oct 2026
- Experiments
- Teams can rerun datasets through different application versions and compare evaluation results.arize.com · read 5 Oct 2026
- Integrations
- Documented integrations include frameworks and providers such as LlamaIndex, LangChain, DSPy, OpenAI, Bedrock, and Anthropic.arize.com · read 5 Oct 2026
- License
- The Phoenix page describes the project as ELv2 licensed.arize.com · read 5 Oct 2026
- Maker
- Phoenix is built by Arize AI and the open-source community.arize.com · read 5 Oct 2026
- Prompt tools
- Phoenix supports prompt versioning, side-by-side testing, and replaying calls to inspect how changes affect outputs.arize.com · read 5 Oct 2026
- Purpose
- Phoenix helps teams trace, evaluate, debug, and improve AI applications.arize.com · read 5 Oct 2026
- Support
- The Phoenix documentation points users to a Slack community for questions and developer discussion.arize.com · read 5 Oct 2026
- Tracing
- It captures model calls, retrieval, tool use, and custom logic in traces that can be sent over OpenTelemetry.arize.com · read 5 Oct 2026
- Usage limits
- Arize describes Phoenix as free and open source, with user-managed trace spans, ingestion volume, projects, and retention.arize.com · read 5 Oct 2026
