starter.wiki

Open-source AI tracing and evaluation

Arize Phoenix

An open-source observability and evaluation project built around OpenTelemetry, OpenInference, traces, evaluations, datasets, and experiments.

Visit official site

Editorial verdict

Choose Arize Phoenix when an open-source and OpenTelemetry-oriented tracing and evaluation stack justifies owning deployment, storage, access, upgrades, and evaluation-model cost.1234

Best for

  • OpenTelemetry and OpenInference tracing
  • Teams wanting an OSS evaluation workflow
  • Organizations able to operate observability storage
1234

Not ideal for

  • Teams wanting a fully managed default
  • Buyers conflating Phoenix with Arize AX
  • Organizations unable to operate storage, access, backup, and upgrades
1234
Main trade-off

Open-source tracing and evaluation maximize inspectability and control while transferring data infrastructure, access, retention, upgrade, evaluation-model, and support responsibility.1234

Product boundary

Whether the Phoenix open-source project provides the required tracing and evaluation primitives at an acceptable storage and operating cost.

This page evaluates the Arize Phoenix open-source project, not the managed Arize AX enterprise platform. Phoenix supplies tracing and evaluation software; deployment, storage, access, backups, upgrades, evaluation models, and availability remain the operator's responsibility.1234

For: Teams that want open-source, OpenTelemetry-oriented AI observability and can operate the selected Phoenix deployment

  • The production workload, language, model, provider, or deployment boundary changes
  • Current pricing, retention, data use, policy, or regional support changes
  • Measured quality, latency, reliability, or operating cost no longer fits

Why teams consider Arize Phoenix

  • Open standardsPhoenix uses OpenTelemetry and OpenInference concepts for AI tracing.1234
  • Evaluation primitivesTraces, datasets, experiments, and evaluators can share a workflow.1234
  • Source availabilityThe repository and license allow teams to inspect and operate the software.1234

Pricing

The Phoenix open-source software has no represented vendor subscription price; infrastructure, storage, evaluation-model, operations, support, and any separate Arize product remain external costs.4

Current official route

Open-source self-operated software

Verified 2026-07-27: the Phoenix repository and license support an open-source deployment route. This page does not invent a hosted price or treat Arize AX pricing as Phoenix pricing.4

Software route
Open-source Phoenix repository and license4
Operator cost
Compute, database, storage, access, backup, upgrades, monitoring, and support4
Evaluation cost
Judge-model and dataset operations remain separate4
Pricing checked View official pricing

Arize Phoenix vs alternatives

Langfuse

Choose when
Choose Langfuse when open-source portability or self-hosting materially affects the observability decision, after modeling ingestion units, retention, storage, evaluation models, and platform operations.
Avoid when
Teams unwilling to operate self-hosted data infrastructure
Compared with Arize Phoenix
Open-source deployment choice increases control and portability while adding ingestion, retention, storage, ClickHouse, upgrade, evaluation-model, and edition responsibility.56

LangSmith

Choose when
Choose LangSmith when its tracing and evaluation workflow aligns with the development stack and the team accepts its usage-unit, retention, data, and deployment boundaries.
Avoid when
Teams requiring an OSS-first observability core
Compared with Arize Phoenix
Framework-aligned managed evaluation reduces integration work while adding usage-unit, trace-tier, retention, platform, and Enterprise self-hosting dependence.78

Braintrust

Choose when
Choose Braintrust when evaluation-led development is the operating model and its processed-data, scoring, retention, collaboration, and deployment boundaries fit.
Avoid when
Teams primarily seeking an OSS tracing backend
Compared with Arize Phoenix
A focused evaluation workflow improves repeatability while adding dataset, scoring, processed-data, retention, collaboration, and hosted-platform dependence.910

Resources and sources

Official product, documentation, pricing, and policy sources

  • Arize Phoenix documentation
    Open
  • Arize Phoenix self-hosting configuration
    Open
  • Arize Phoenix repository
    Open
  • Arize Phoenix license
    Open
  • Langfuse Cloud pricing
    Open
  • Langfuse self-hosted pricing and editions
    Open
  • LangSmith pricing
    Open
  • LangSmith administration and retention
    Open
  • Braintrust pricing
    Open
  • Braintrust tracing and instrumentation
    Open

Related tasks

  1. 1
    Arize Phoenix documentation

    Arize · Accessed Official

  2. 2
    Arize Phoenix self-hosting configuration

    Arize · Accessed Official

  3. 3
    Arize Phoenix repository

    Arize · Accessed Official

  4. 4
    Arize Phoenix license

    Arize · Accessed Official

  5. 5
    Langfuse Cloud pricing

    Langfuse · Accessed Official

  6. 6
    Langfuse self-hosted pricing and editions

    Langfuse · Accessed Official

  7. 7
    LangSmith pricing

    LangChain · Accessed Official

  8. 8
    LangSmith administration and retention

    LangChain · Accessed Official

  9. 9
    Braintrust pricing

    Braintrust · Accessed Official

  10. 10
    Braintrust tracing and instrumentation

    Braintrust · Accessed Official