Evals & observability

Phoenix

Open-source OpenTelemetry-based tracing and evaluation from Arize, runnable in a notebook.

Visit phoenix.arize.com ↗

Pricing
Open source
Runs
Hosted or self-hosted
Languages
Python, TypeScript
Interface
Library, Dashboard
Source
Open source

What Phoenix is

Phoenix is built on OpenTelemetry, so traces flow into tracing infrastructure you may already operate instead of a proprietary silo. It runs locally — including inside a notebook — which makes it unusually good for inspecting a retrieval pipeline while you are still building it.

Best for

Teams standardised on OpenTelemetry, and anyone debugging retrieval quality interactively.

Consider something else if

OpenTelemetry brings concepts and setup that a proxy-based tool does not ask of you.

Phoenix alternatives

The closest options in evals & observability, on the axes that actually separate them.

Phoenix compared with 5 alternatives
ToolBest forPricingRuns
Phoenixopen sourceTeams standardised on OpenTelemetry, and anyone debugging retrieval quality interactively.Open sourceHosted or self-hosted
Langfuseopen sourceTeams who need traces containing customer data to stay inside their own infrastructure.Open sourceHosted or self-hosted
LangSmithLangChain and LangGraph users, who get the deepest integration for the least work.Free tierHosted
BraintrustTeams treating prompt changes as changes that need tests, with evals wired into CI.Free tierHosted
Heliconeopen sourceGetting cost and latency visibility across a codebase quickly, especially one you do not want to instrument.Free tierHosted or self-hosted
W&B Weaveopen sourceOrganisations already on Weights & Biases who want one place for all model work.Free tierHosted

Choosing within evals & observability

Tracing or evaluation first

Some tools lead with tracing and add evals; others are eval-first with tracing attached. If you are debugging today, start with tracing. If you are about to change a prompt that is already in production, start with evals.

How it gets your data

A proxy needs a one-line base-URL change and captures everything. An SDK needs instrumentation and captures more structure. OpenTelemetry-based tools slot into tracing you may already run.

The full guide to evals & observability →

Questions

What is Phoenix?

Phoenix is built on OpenTelemetry, so traces flow into tracing infrastructure you may already operate instead of a proprietary silo. It runs locally — including inside a notebook — which makes it unusually good for inspecting a retrieval pipeline while you are still building it. It is open source and hosted or self-hosted.

What are the alternatives to Phoenix?

The closest alternatives are Langfuse, LangSmith, Braintrust, Helicone, W&B Weave. They sit in the same category — evals & observability — and differ mainly on hosting model, pricing shape, and how much they abstract away.

Is Phoenix the right choice?

Teams standardised on OpenTelemetry, and anyone debugging retrieval quality interactively. The main caveat: OpenTelemetry brings concepts and setup that a proxy-based tool does not ask of you.