Arize Phoenix vs Langfuse

Pick two tools from the same category to compare side-by-side.

	Arize Phoenix Open-source LLM tracing and evaluation platform from Arize AI, built on OpenTelemetry.	Langfuse Open-source LLM observability, eval, prompt mgmt.
Category	observability	observability
Vendor type	hybrid	open source
Pricing	freemium	freemium
Strengths	+ OpenTelemetry-based instrumentation works across frameworks and providers + Built-in evals, datasets, and experiments alongside tracing + Self-hostable via pip, Docker, or Helm in addition to hosted cloud + Prompt playground for replaying and comparing traced LLM calls	+ Open source; full self-host option + Broad coverage (trace + eval + prompts) + Provider-agnostic
Tradeoffs	− Elastic License 2.0 (ELv2) restricts offering Phoenix itself as a managed service − Self-hosting means operating and scaling the collector and storage yourself − Advanced enterprise monitoring features live in the separate commercial Arize platform	− Self-host adds ops burden vs SaaS
Used in stacks	0	4