tools
Arize Phoenix
Open-source platform for tracing, evaluating, and improving AI agents and LLM applications.
In inglese
Arize Phoenix traces prompts, retrieval, tool calls, outputs, latency, and token usage. It supports evaluations, human annotations, datasets, experiments, prompt iteration, and OpenTelemetry-based integrations.
Developers and AI engineering teams can run it locally, in Docker, Kubernetes, notebooks, or Phoenix Cloud. Phoenix is self-hosted and open source; managed Arize AX plans and dedicated support are separate offerings.
Features
- Trace prompts, retrievals, tool calls, outputs, and agent steps
- Evaluate AI outputs with code evaluators or LLM-as-judge
- Create datasets from traces and run repeatable experiments
- Annotate traces with human feedback or automated labels
- Compare and manage prompt versions in the Prompt IDE
- Support OpenTelemetry and OpenInference tracing standards
- Run locally, in Docker, Kubernetes, notebooks, or Phoenix Cloud
- ELv2-licensed open-source core
Use cases
- Debug failed agent runs by inspecting traces and tool calls
- Evaluate retrieval quality and generated responses before release
- Create benchmark datasets from production traces
- Compare prompt or model changes through controlled experiments
- Monitor token usage, latency, errors, and AI application behavior
Pros
Cons
Latest updates
- Get Alyx help tailored to your experience
Alyx adapts how it helps based on your experience level in each part of Arize AX.
- Pick up where you left off with Alyx long-term memory
Alyx remembers context across conversations, including preferences, goals, project and asset learnings, team conventions, and decisions.
- Add and annotate entire sessions and traces in annotation queues
Send sessions and traces to an annotation queue and review them at session or trace granularity.
- Inspect remote evaluator runs as traces
Remote evaluator runs emit a trace for each evaluated row into your evaluations project, with spans capturing request, response, status code, and latency.
- Select OpenAI GPT-6 in the prompt playground
Select OpenAI’s gpt-6-astra in the prompt playground model picker and run prompts against it.
Capabilities
- Command line — “Get Started Locally $ uvx arize-phoenix serve” source
- Self-hosted — “Self-host Phoenix and keep sensitive data on your own infrastructure.” source
- API — “Docs Quickstarts, API reference, and integration guides” source
- Traces and evaluates — “Phoenix shows every step your agent takes so you know what went wrong.” source
Get it
Security
- SOC 2 Type II — “Arize AI Announces SOC 2 Type II Certification” source
- SOC 2 — “Arize AI Announces SOC 2 Type II Certification” source
- ISO 27001 — “ISO/IEC 27001 Certified” source
- GDPR — “GDPR Compliant” source
- HIPAA — “HIPAA Compliant” source
- Data kept in the EU — “Arize AI: Support for EU Data Residency” source
Pricing
- Starting price
- $50/mo
- Prices checked
- 2026-09-25
AX Free
Free
- 10 issues per month
- 25k spans per month
- 1 GB per month
- 15 days retention
- SaaS deployment
- Unlimited users and evals
AX Pro
- $50 per month
- 25 issues per month
- 50k spans per month
- 10 GB per month
- 30 days retention
- SaaS deployment
- Unlimited users and evals
AX Enterprise
Price on request
- Unlimited issues
- Custom span volume
- Custom ingestion volume
- Custom retention
- SaaS or Self-Hosted deployment
- Unlimited users and evals