ai-observability
Langfuse
Open-source LLM engineering platform — observability, prompts, evals
OSS LLM engineering platform. MIT-licensed. Observability + prompt mgmt + evals + datasets + playground. Free Cloud (50k units) + Core $29 + Pro $199 + Self-host.
Pricing
| Tier | Price | Notes |
|---|---|---|
| Hobby (Cloud Free) | Free | Free. 50k units/month included. 30 days data access. 2 users. Community support. |
| Self-Hosted (OSS) | Free | MIT-licensed. Docker Compose or Kubernetes deployment. Unlimited. |
| Core | $29/mo | $29/month. 100k units included ($8 per 100k overage). 90 days retention. Unlimited users. In-app support. |
| Pro | $199/mo | $199/month. 100k units included + same overage. 3 YEARS retention. Unlimited annotation queues. High rate limits. |
| Teams Add-on | $300/mo | +$300/month. Adds Enterprise SSO + fine-grained RBAC + dedicated Slack support to Pro. |
| Enterprise | $2499/mo | $2,499/month. Everything + custom rate limits, uptime SLA, dedicated support engineer. Yearly options. |
Limits
| Tier | Metric | Value | Notes |
|---|---|---|---|
| — | annotation queues pro | Unlimited on Pro+ | Annotation queues |
| — | billing unit | 1 unit = 1 trace OR 1 observation (span/generation/event) OR 1 eval score | What counts as a unit |
| — | eu region | EU data region available for GDPR | EU hosting |
| — | framework agnostic | Works with ANY LLM stack via decorators / OTel / SDK | Framework support |
| — | graduated pricing | $8/100k (100k-1M), $7/100k (1M-10M), $6.50/100k (10M-50M), $6/100k (50M+) | Graduated pricing |
| — | license | MIT | OSS license |
| — | playground | Built-in multi-provider prompt playground | Playground |
| — | self host parity | Full feature parity between Cloud and self-host | Self-host parity |
Features
- Annotation Queues — Human reviewers rate traces. Unlimited on Pro+.
- Dashboards — Aggregate metrics, cost, quality across projects.
- Datasets — Curate test sets from production traces. Run experiments.
- EU Cloud Region — GDPR-compliant hosting in EU.
- Evaluations — LLM-as-judge, manual scores, custom model-graded evaluators. · docs
- LLM Cost Tracking — Automatic cost calculation per provider/model.
- OpenTelemetry Native — OTel SDK → Langfuse endpoint works out of box.
- Playground — Test prompts + models + variables live.
- Prompt Management — Version, tag, label prompts. Reference from code by label. · docs
- Public API — Full REST API for ingest, query, prompt management.
- Python @observe decorator — One-line decorator to trace any function.
- Self-Hosting — Docker Compose + k8s Helm chart.
- Sessions — Group related traces (conversations, agent runs).
- Tracing — Capture every LLM call, tool call, nested span with inputs/outputs/cost. · docs
- Users Tracking — Segment traces by user ID, track per-user cost.
- Webhooks — Subscribe to trace completion events.
Developer interfaces
| Slug | Name | Kind | Version |
|---|---|---|---|
| dashboard | Langfuse Dashboard | other | — |
| sdk-node | langfuse-js | sdk | 4.x |
| mcp | Langfuse MCP Server | mcp | — |
| sdk-python | langfuse-python | sdk | 3.x |
| rest-api | Langfuse REST API | rest | v1 |
| otel-endpoint | OpenTelemetry endpoint | other | — |
Compare Langfuse with
ai-api
Langfuse vs Anthropic API
Side-by-side breakdown.
ai-api
Langfuse vs AssemblyAI
Side-by-side breakdown.
ai-api
Langfuse vs Deepgram
Side-by-side breakdown.
ai-api
Langfuse vs ElevenLabs
Side-by-side breakdown.
ai-api
Langfuse vs Google Gemini API
Side-by-side breakdown.
ai-api
Langfuse vs Groq
Side-by-side breakdown.
ai-api
Langfuse vs OpenAI API
Side-by-side breakdown.
ai-api
Langfuse vs Replicate
Side-by-side breakdown.
Staxly is an independent catalog of developer platforms. Outbound links to Langfuse are plain references to their official pages. Pricing is verified at publication time — reconfirm on the vendor site before buying.