Skip to content
InfratoApp
Layers / Observability / Evals / Cost and usage tracking / langfuse

langfuse

UNCLAIMEDClaim this listing

By langfuse

COST AND USAGE TRACKINGEVALUATION AND BENCHMARKINGPROMPT MANAGEMENTTRACING AND MONITORING

langfuse — Langfuse Python SDK - LLM observability/tracing, datasets, experiments, LLM-as-a-judge evaluation, and prompt management. Listed under Cost and usage tracking in the Observability / Evals layer. 9 of 15 comparison attributes are recorded, each with the page it was read from.

Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.

4 OF 4 SIGNALS HELD

WebsiteDocsPricing pagelangfuse/langfuse

What it runs on, and what runs on it

16 cited edges
The differentiator

Computed from the stack graph, both directions. Every cited edge links the page it was read from; a vendor-added one links the vendor’s own source — this is the reason to be here rather than on the vendor’s own site.

RUNS ON / INTEGRATES WITH

  • nothing recorded

USED BY

Agentic surface

2 integrations

MCP servers and agent skills that name langfuse as their official vendor, or that mention wrapping it. Unverified means a mention in the tool’s own description, not a citation.

Open-source signals

DOWNLOADS 30D
7,219,046
LAST COMMIT
not measured

A HOLLOW RING IS UNMEASURED, NOT ZERO · WE DO NOT SUBSTITUTE A PARENT COMPANY’S REPOSITORY FOR A PRODUCT THAT HAS NONE

Price

We hold no price for this product.

The seller publishes a pricing page, linked above, but we read no rate from it. Either it quotes by sales call rather than in public, or the last reading passed 21 days and was hidden rather than shown stale. If that changes — or if you publish /.well-known/pricing.json — it appears here with a capture date.

How we read prices →

What its categories ask

9 answered · 6 unanswered

15 questions declared by Cost and usage tracking and Evaluation and benchmarking and Prompt management and Tracing and monitoring. Most rows across the directory read like these.

ATTRIBUTEANSWEREVIDENCE · SOURCE
Cost attributiontoken spend, cost, and latency
“Monitor cost, latency, and quality with dashboards and automated alerts.”
2026-09-12
Data residencyEU, US
“EU & US Data Regions”
2026-09-12
Deploymentboth2026-09-23
Framework integrations100 frameworks
“100+ integrations Works with any model, any framework, and stack.”
2026-09-12
Human in the loopYes
“Human Annotation Collaborative Human-in the-Loop workflows to review traces and create golden datasets.”
2026-09-22
LicenceMIT
“MIT license All product features MIT licensed”
2026-09-12
LLM-as-judgeYes
“Run fully managed LLM-as-a-judge evaluations on production or development traces.”
2026-09-22
Open sourceYes
“Open source (MIT) Inspect the code. Self-host for free. We are the largest OSS community in our category.”
2026-09-12
OpenTelemetryYes
“OTel native Standard trace format. Works with existing OpenTelemetry instrumentation.”
2026-09-12
Alertingno answer on record
Budget limitsno answer on record
Dataset managementno answer on record
Git-backedno answer on record
Prompt versioningno answer on record
Web UIno answer on record

A ROW WITH NO ANSWER IS NOT A ROW WITH A “NO” · A VENDOR MAY ANSWER A BLANK ONE, MARKED VENDOR CLAIMED WITH ITS SOURCE · A DOCUMENTED VALUE IS DISPUTED, NOT OVERWRITTEN, AND STAYS VISIBLE WHILE WE RE-READ THE SOURCE

Practitioner reviews

Nobody has written one yet.

A review here is structured, not a star: hardware, scale band, what broke in production, and whether you would choose it again.

NO PERCENTAGE IS SHOWN UNDER FIVE REVIEWS · NO STAR RATINGS, EVER

Also in this category

69 products in Cost and usage tracking. Comparison defaults to within the category — pairing this with a GPU cloud would produce a page that means nothing.

LangSmithUSED BY 15COMPARE →
Arize PhoenixUSED BY 4COMPARE →
BraintrustUSED BY 3COMPARE →
RagasUSED BY 2COMPARE →
Weights & Biases WeaveUSED BY 2COMPARE →
opikUSED BY 1COMPARE →
PromptfooUSED BY 1COMPARE →
Traceloop OpenLLMetryUSED BY 1COMPARE →

USED BY = LISTED PRODUCTS DEPENDING ON IT, IN THIS DIRECTORY

Frequently asked

Is langfuse open source?
Yes — it is listed as open source, and its repository is the source for the activity figures on this page rather than anything the project says about itself.
Does langfuse offer human in the loop?
Yes. Read from their own page: “Human Annotation Collaborative Human-in the-Loop workflows to review traces and create golden datasets.”.
Does langfuse offer llm-as-judge?
Yes. Read from their own page: “Run fully managed LLM-as-a-judge evaluations on production or development traces.”.
What does a blank mean on the langfuse page?
That nobody has told us, not that the answer is no. A hollow ring is "no answer on record", which is a different state from a recorded no — and the two look different on purpose. A blank is an absence of evidence, and this page shows how many of its questions are in that state rather than quietly leaving them out.
Where do the langfuse figures come from?
Each one is read from a public page — usually the vendor's own documentation or pricing page — and carries a link to it with the date it was read. Nothing here is estimated, averaged across sources, or inferred from a similar product. If a figure cannot be traced to a page, it is not published.
Can langfuse change what this page says?
They can claim the listing and supply or correct values, which are then labelled as theirs. They cannot remove the page, hide a comparison they are losing, or change a figure somebody else recorded with a source. Nothing on the page is for sale. How the site is paid for is set out under money and independence at /our-data#sec5.
Something here is wrong — how do I fix it?
Dispute the value. Every figure links to the page it was read from, so a dispute names the value and gives a source that contradicts it. That is the only lever anyone has over this page, and it is the same lever for the vendor, a competitor and a reader.
Is this listing run by langfuse?
No. It is built from public sources, and no value on it came from the company. Anyone with an address at langfuse.com can claim it for free. A claim lets the company write the tagline, description and logo, and answer blank questions or add dependencies, each marked as theirs with a source. Prices, licence and OSS figures stay as the directory read them, category changes only through our review, and each can be disputed with a source.

Cite this page

A model that quotes us should quote us correctly. The reading and its date sit inside the citation rather than beside it, because a quotation carrying only a URL goes wrong the week the URL changes.

infratoapp, “langfuse — Cost and usage tracking”, read 12 September 2026. Cost attribution: token spend, cost, and latency as published at langfuse.com. https://www.infratoapp.com/products/langfuse

What langfuse can and cannot change here

Claiming langfuse lets its admins and editors change the tagline, description, logo, docs link and deployment model of every product that org owns — live, labelled as theirs, and logged. Answers to blank questions and dependencies go live too, marked as the owner’s and sourced; a documented answer cannot be overwritten. Everything else on this page is a stated fact with a dispute route: price, licence and OSS figures. Those columns are ungranted at the database level, so they are not a feature we withheld — they are a write that cannot happen. Name, category, website, pricing page and package names can be changed by the owner only through our review. A dispute never deletes a value; it marks it and publishes the correction.

Claim langfuseFree · email at langfuse.com