Langfuse vs LangSmith
Two sides of the LLM observability & evals decision: open-source platform and hosted eval platform. When each fits, what it costs, who moves from one to the other, and what makers who chose it say.
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗
Which fits you
Choose Langfuse if- You want tracing, prompts and evals in one tool you can self-host for free
Use it whenYou want to own your trace data or keep costs flat as volume grows.
Trade-offSelf-hosting means running Postgres, ClickHouse, Redis and object storage alongside it; otherwise it's a usage-based cloud plan.
Choose LangSmith if- Your app is built on LangChain or LangGraph
Use it whenYou already use the LangChain stack.
Trade-offPaid per seat beyond the free tier; self-hosting is enterprise-only.
At a glance
| Langfuse | LangSmith | |
|---|---|---|
| Used by | 33 makers' products · 43 open-source projects | 11 makers' products · 49 open-source projects |
| Cost at default usagetraces 100k traces | $29/mo Core | $475/mo Developer |
| Moved to it on GitHubpull requests since Oct 2024 | 9 from LangSmith | fewer than 3 |
| Downloads | 1.8M/wk+81% vs npm | 6.1M/wk−4% vs npm |
| Pricing | Free tier (50k units/mo); usage-based paid plans; fully free to self-host under MIT license. · paid from $29/mo | Free tier with a monthly trace limit; paid per-seat plan with usage overage; custom Enterprise, including self-hosted. · paid from $39/seat/mo |
| Free tier | Yes | Yes |
| Open source | Yes · self-hostable | No |
| Incidents, 90 daysfrom its status page | 15 (1 major) | 0 |
Cost as you grow
Both cost $0 up to 1k traces; from 10k traces Langfuse costs less ($0 vs $25); and still does at 10M traces ($821 vs $49,975). They're different kinds of tool — open-source platform and hosted eval platform — so the prices don't buy the same thing.
The numbers, plan by plan
| Traces per month | Langfuse | LangSmith |
|---|---|---|
| 1,000 | $0 Hobby | $0 Developer |
| 10,000 | $0 Hobby | $25 Developer |
| 50,000 | $0 Hobby | $225 Developer |
| 100,000 | $29 Core | $475 Developer |
| 500,000 | $61 Core | $2,475 Developer |
| 1,000,000 | $101 Core | $4,975 Developer |
| 5,000,000 | $421 Core | $24,975 Developer |
| 10,000,000 | $821 Core | $49,975 Developer |
Who moves from one to the other
Public pull requests on GitHub since Oct 2024 whose title says "Langfuse to LangSmith" or the reverse — real code changes, by developers in general rather than makers only.
LangSmith → Langfuse9 PRs- Migrate observability from LangSmith to Langfuse and trim logged fieldsHOSH19/HarnessLab · 2026-08-29
- feat: migrate observability from LangSmith to Langfuse Cloud (v4 SDK)icekarim/momo-assistant · 2026-08-05
- feat(trace): migrate LangSmith to Langfuse v4 and fix env key priority1935494577/Xiaoxin-Agentic-RAG-System · 2026-08-01
- [codex] Migrate from LangSmith to Langfuse, remove Python legacy, fix review issuesBunnyRabbit8mile/codex-tee · 2026-07-14
- Reapply "feat: migrate observability from LangSmith to Langfuse"sinuarlowbaby/RAG-PDF-Chatbot · 2026-07-14
- refactor: migrate observability from LangSmith to Langfusewei-yiting/fin-lab-x · 2026-03-18
- Migrate observability from LangSmith to LangfuseAneeshPulukkul/hybrid-rag-solution · 2026-03-14
- feat:migrate LLM observabilty from LangSmith to LangFuse100-hours-a-week/17-JinyUs-Q-Feed-AI · 2026-02-26
- Refactor: Migrate from Langsmith to Langfusedylangamachefl/fantasy-football-chatbot-v2 · 2025-12-01
Fewer than 3 pull requests move from Langfuse to LangSmith.
What makers say
Makers on using it for LLM observability & evals, from Product Hunt and Starter Story interviews, each linked to the source. Products with a page of their own and fuller notes first.
On LangfuseMarc gave me an in-person onboarding in SF - I found an issue in our LLM provider config just 30 minutes after the onboarding thanks to Langfuse. 10/10 recommendation
Langfuse powers our LLM observability. Without Langfuse, our AI agent would not be best-in-class. We have been using Langfuse since nearly the beginning: 2+ years!
We use Langfuse to keep track of our LLM prompts while building MCP-Builder.ai. It’s a great tool that makes it easy to monitor and analyze prompt performance, helping us improve quickly and efficiently.
On LangSmithLangSmith’s real-time analytics and versioning keep our AI agents rock-solid -- so everything just works better.
You can't build AI agents without monitoring. Metadata filtering is strong.
I deployed the manage Pig agent on LangGraph and it's been smooth sailing!
Loved and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.
LangfuseMost loved
- Detailed traces show each agent call and the context it pulled, which makes debugging agent behaviour much easier. PHPH 2HN
- Token usage and cost are tracked across providers alongside quality, in one place. PHPH 2HN
- Open source and self-hostable, a common default for teams wanting tracing on their own infrastructure. PHHNHN 2HN 3
Watch-outs
On Product Hunt: 5.0★, 48 reviews · mentioned most: LLM observability, open source, detailed tracing- Prompt management and experiments feel basic next to the tracing core. HNHN 2HN 3
- Views are retrospective dashboards, so explaining one run's cost or failure still means reading trace trees by hand. HNHN 2HN 3HN 4
- The ClickHouse acquisition raised GDPR and data-residency concerns for EU users of the cloud version. HNHN 2
LangSmithMost loved
Watch-outs
On Product Hunt: 4.8★, 19 reviews · mentioned most: monitoring AI model performance, chain sequence debugging, evals- It keeps pulling users toward the LangChain platform, and LangChain docs push LangSmith, which feels like lock-in. HNHN 2HN 3HN 4
- Traces show which agent failed but not why, so root-cause analysis stays manual. HNHN 2HN 3HN 4
- Viewing your own traces requires a cloud account, with no local-first option. HNHN 2
Who uses each
Langfuse33 makers' products
Agentplace.io
Conduit
Finyuus
giselle
Imagine
Magic Patterns
Manufact (mcp-use)LangSmith11 makers' products
lmChatGPTtfy
Watchman AI
Meet-TingWhat makers pair each with
With LangfuseTransactional Email
OpenFunnel(YC F24)
stagewise
Outlit AI
Productlane
Relay.app
THEO Growth
Pebbles Ai
GoMarbleDatabase
Langfuse + Supabase:
Flowstep
Lamatic.ai
Lingo.dev
MCP-Builder.ai
Minicule
Symvol Video AI for Education
Yapify
Sendbird
FlowstepLamatic.aiLingo.devMCP-Builder.aiMiniculeSymvol Video AI for EducationYapifySendbirdLangfuse + Neon:
cognee
Draft Alpha
cogneeDraft Alpha
Orango
TruvaWith LangSmithLLM API
LangSmith + Claude:
Astrid
Pig
Traycer AI
AstridPigTraycer AIHosting
LangSmith + Amazon Web Services:Astrid
NeuralAgentTraycer AI
AstridNeuralAgentTraycer AILangSmith + Google Cloud Platform:NeuralAgentTraycer AI
NeuralAgentTraycer AITransactional Email
LangSmith + Resend:DryMerge
GitLawTraycer AI
GitLawTraycer AILangSmith + SendGrid:GitLaw
IntrycTraycer AI
GitLawIntrycTraycer AINeither quite right?
See the whole LLM observability & evals decision →
Arize PhoenixOpen-source platformOpenTelemetry-based tracing and evals you can start locally in a notebook, then self-host or move to its cloud.vs Langfuse →vs LangSmith →
HeliconeProxy loggingGetting request logs, costs and latency by changing one base URL, with no SDK instrumentation.vs Langfuse →vs LangSmith →
BraintrustHosted eval platformEval-driven work — scoring outputs and comparing prompts and models side by side in experiments.vs Langfuse →vs LangSmith →