Source-available LLM tracing and evaluation tool built on OpenTelemetry and OpenInference; run it locally, in a notebook or on your servers to inspect traces and score outputs.
Pricing and hosting
- Pricing
- Free
- Open source
- Source available (Elastic-2.0)
- Self-hosted
- Yes
- Launched
- 2023
- Status
- Active
- Website
- arize.com
Plans and prices change; check the tool's own site before you decide.
What it does
LLM and AI observability checklist
9 of 10 confirmed in Arize Phoenix's own documentation. The same checklist is used for every tool in LLM observability.
- LLM call tracing Yes
- Agent and multi-step traces Yes
- Token and cost tracking Yes
- Prompt management Yes
- Evaluations Yes
- Datasets and experiments Yes
- User feedback Yes
- OpenTelemetry support Yes
- Playground Yes
- Alerts Not confirmed
No alerting documented in open-source Phoenix (monitors are in Arize AX).
Checked against: github.com, arize.com
Alternatives to Arize Phoenix
Other llm and ai observability tools. See all 22.
-
AgentOps Observability for AI agents: records agent sessions with LLM calls, tool use and costs so you can replay and debug runs; SDK and app are open source. -
Arize AX Arize's hosted AI observability and evaluation platform for agents and ML models: tracing, online evals, monitors and dashboards. -
Braintrust Evaluation and observability platform for AI products: logs production traces, runs evals and scorers, and offers a prompt playground and datasets. -
Confident AI Evaluation and observability platform from the makers of the open source DeepEval library: LLM tracing, regression tests in CI, and red teaming. -
Future AGI Open source platform to trace, evaluate, simulate and guard LLM and agent apps, including an AI gateway. -
Galileo AI evaluation and observability platform with tracing, evaluation metrics and real-time guardrails for agents; hosted, VPC or on-prem. -
Helicone Open source LLM proxy and logging: point your provider base URL at it to record every request with cost, latency and user, plus caching and rate limits. -
HoneyHive Observability and evaluation platform for AI agents: OpenTelemetry-based tracing, automated and human evals, prompt versioning and production monitoring. -
Laminar Open source observability for AI agents: OpenTelemetry-based tracing, evaluations and analysis of agent runs, self-hostable or cloud. -
Langfuse Open source LLM engineering platform: traces LLM and agent calls, manages prompts, runs evaluations and tracks cost and latency. Self-host or use the cloud; acquired by ClickHouse in 2026. -
LangSmith LangChain's platform for tracing, evaluating and monitoring LLM apps and agents, usable with or without LangChain; also hosts agent deployments. -
LangWatch Open source LLMOps platform: traces LLM and agent runs, runs evaluations and agent simulations, and helps optimize prompts; cloud or self-managed.