Evals & observability
Phoenix
Open-source OpenTelemetry-based tracing and evaluation from Arize, runnable in a notebook.
- Category
- Evals & observability
- 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.
| Tool | Best for | Pricing | Runs |
|---|---|---|---|
| Phoenixopen source | Teams standardised on OpenTelemetry, and anyone debugging retrieval quality interactively. | Open source | Hosted or self-hosted |
| Langfuseopen source | Teams who need traces containing customer data to stay inside their own infrastructure. | Open source | Hosted or self-hosted |
| LangSmith | LangChain and LangGraph users, who get the deepest integration for the least work. | Free tier | Hosted |
| Braintrust | Teams treating prompt changes as changes that need tests, with evals wired into CI. | Free tier | Hosted |
| Heliconeopen source | Getting cost and latency visibility across a codebase quickly, especially one you do not want to instrument. | Free tier | Hosted or self-hosted |
| W&B Weaveopen source | Organisations already on Weights & Biases who want one place for all model work. | Free tier | Hosted |
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.
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.
Whatever you build on, the model is the line item that scales. See what each one costs per million tokens, or price your own workload.