LLM observability & evaluation · Langfuse

Langfuse

Open-source LLM tracing and evaluation platform, available self-hosted for free or as a metered hosted cloud service.

Visit Langfuse Alternatives

Langfuse is an open-source platform for tracing LLM application calls (prompts, completions, latency, cost, and tool/agent steps), managing prompt versions, and running evaluations against datasets using human review, custom scoring functions, or LLM-as-judge. The core tracing and evaluation engine is open source and can be self-hosted for free via Docker Compose or Kubernetes with no usage limits beyond infrastructure capacity. Langfuse Cloud is the same software run as a hosted service, billed by monthly 'observability units' (traces, scores, and related events) with a free Hobby tier, then Core, Pro, and Enterprise plans that add longer data retention, higher rate limits, and enterprise controls such as SSO, SCIM, and audit logs. This split lets a team start self-hosted and move to the managed cloud without changing tooling.

At a glance

Vendor Langfuse
Pricing model Free tier + paid plans
Free tier Yes
Deployment Cloud, Self-hosted
Open source Yes (MIT)
Best for Teams that want open-source tracing they can self-host for free and later scale onto a managed cloud plan.

Pricing

Free to self-host indefinitely; Langfuse Cloud has a free Hobby tier plus Core, Pro, and Enterprise monthly plans metered by observability units, with graduated per-unit overage pricing.

Plan Price Notes
Hobby (Cloud) $0/month 50k units/month, 30-day data access, 2 users, community support
Core (Cloud) $29/month 100k units/month base, 90-day data access, unlimited users; overage from $8/100k units
Pro (Cloud) $199/month 100k units/month base, 3-year data access, unlimited annotation queues; optional Teams add-on $300/month for SSO/RBAC
Enterprise (Cloud) $2,499/month Everything in Pro + Teams, audit logs, SCIM API, custom rate limits and SLAs

Prices read from the vendor's own page on September 21, 2026. Vendors change prices; check the source before you budget.

Features

  • Distributed tracing for LLM calls, chains, and agent steps
  • Prompt management with versioning
  • Dataset-based evaluation with human, custom, or LLM-as-judge scoring
  • Production monitoring dashboards and cost tracking
  • Free, unlimited self-hosting via Docker Compose or Kubernetes
  • SDKs and OpenTelemetry-compatible instrumentation

Integrations

Profile last reviewed September 21, 2026

Head to head

Alternatives

LangSmith Tracing, evaluation, and deployment platform for LLM applications, built by the team behind LangChain and LangGraph. Helicone Open-source LLM observability platform that logs and analyzes requests via a proxy or async SDK, with a free-tier hosted cloud. Lunary GDPR-focused LLM observability platform for tracing, prompt management, and human review, hosted in Europe or self-hosted. OpenLLMetry Apache-2.0 open-source instrumentation library extending OpenTelemetry to LLM calls, usable with any OpenTelemetry-compatible backend.

Langfuse in the index now

Terms to know

Data observability Continuous automated monitoring of pipelines and datasets to catch freshness, volume and quality problems early. Machine learning Building models that learn patterns from data to make predictions or decisions, rather than following hand-coded rules. LLM observability Monitoring a language model's live behavior in production, tracking its inputs, outputs, latency, cost, and failure patterns. Distributed tracing Following a single request across multiple services in a distributed system to see where time was spent or an error occurred.

Related guides

How to choose an LLM observability tool Pick an LLM tool by whether you need tracing, scoring or a gateway first — most teams eventually need all three, rarely from one vendor. How to evaluate LLM applications Offline evals, LLM-as-judge, human review and production monitoring, aimed at the whole pipeline rather than the model alone.