Skip to content
SPECIFICTION
Get listed

Arize Phoenix

arize.com

Free plan WebAPISelf-hosted
Visit arize.com
Spec score 8.2 #7 of 26 in Llm Developer Tools

What it is

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.

Spec sheet

Purpose
Phoenix helps teams trace, evaluate, debug, and improve AI applications.Read 5 Oct 2026 · arize.com
Deployment
Phoenix can run locally or be self-hosted using Docker, Kubernetes, or a cloud environment.Read 5 Oct 2026 · arize.com
Integrations
Documented integrations include frameworks and providers such as LlamaIndex, LangChain, DSPy, OpenAI, Bedrock, and Anthropic.Read 5 Oct 2026 · arize.com
Support
The Phoenix documentation points users to a Slack community for questions and developer discussion.Read 5 Oct 2026 · arize.com
License
The Phoenix page describes the project as ELv2 licensed.Read 5 Oct 2026 · arize.com
Maker
Phoenix is built by Arize AI and the open-source community.Read 5 Oct 2026 · arize.com
Authentication
Self-hosted Phoenix supports authentication and OAuth2 identity providers that expose an OpenID Connect well-known configuration endpoint.Read 5 Oct 2026 · arize.com
Data control
Arize says self-hosting keeps traces in the user’s own environment.Read 5 Oct 2026 · arize.com
Evaluation integrations
Phoenix can use evaluation libraries including Harbor, Ragas, Cleanlab, and MLflow.Read 5 Oct 2026 · arize.com
Evaluations
Teams can score traces and spans with LLM-based evaluators, code checks, or human labels.Read 5 Oct 2026 · arize.com
Experiments
Teams can rerun datasets through different application versions and compare evaluation results.Read 5 Oct 2026 · arize.com
Prompt tools
Phoenix supports prompt versioning, side-by-side testing, and replaying calls to inspect how changes affect outputs.Read 5 Oct 2026 · arize.com
Tracing
It captures model calls, retrieval, tool use, and custom logic in traces that can be sent over OpenTelemetry.Read 5 Oct 2026 · arize.com
Usage limits
Arize describes Phoenix as free and open source, with user-managed trace spans, ingestion volume, projects, and retention.Read 5 Oct 2026 · arize.com

Plans and prices

Phoenix Free Free and open source · self-hosted · user-managed trace spans, ingestion, projects, and retention Read 5 Oct 2026 · arize.com

Every Arize Phoenix plan and price →

Strong points and limits

Strong points

  • Traces model, retrieval, and tool activity
  • Supports LLM, code, and human evaluations
  • Provides prompt versioning and replay
  • Compares experiments across application versions
  • Runs locally or self-hosted

Limits

  • Self-hosting requires managing deployment and data
  • Uses the ELv2 license
  • Trace ingestion and retention are user-managed

Who it suits

It suits teams operating AI applications that need model, retrieval, tool, prompt, and evaluation tracing. It also fits organizations wanting local or self-hosted deployment with control over trace data and retention.

Verdict

Phoenix brings tracing, evaluation, prompt workflows, and experiment comparison into a self-hostable AI observability project. Its free plan leaves usage volumes and retention decisions with the user.

Where Specifiction places it

Alternatives to Arize PhoenixAll alternatives →