Langfuse vs MLflow
Of the 117 makers' products we know the LLM observability & evals of, 35 chose Langfuse (30%) and 0 MLflow (0%). Among the 33 launched in 2025, Langfuse is in 45% and MLflow in 0%.
Two open-source platform options for LLM observability & evals. When each fits, what it costs, who moves from one to the other, and what makers who chose it say.
Which fits you
- 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.
- Tracing, evaluating and versioning prompts for LLM apps in the same open-source platform many teams already use for ML experiments.
Use it whenYou already use MLflow or Databricks for models, or want OpenTelemetry-based tracing and evals you can self-host.
Trade-offGrew out of classic ML tooling, so the UI and concepts are broader than an LLM-only tool; you run the tracking server yourself unless you use a managed version.
At a glance
| Used by | 35 makers' products · 58 open-source projects | No maker's product yet · 19 open-source projects |
|---|---|---|
| Cost at default usagetraces 100k traces | $29/mo Core | — |
| Downloads | 1.7M/wk+57% vs npm | 9.1k/wk |
| Pricing | Free tier (50k units/mo); usage-based paid plans; fully free to self-host under MIT license. · paid from $29/mo | Free (open source); managed versions are offered by Databricks and cloud providers. |
| Free tier | Yes | Yes |
| Open source | Yes · self-hostable | Yes · self-hostable |
| Incidents, 90 daysfrom its status page | 14 (1 major) | no public status feed |
Which makers on your framework pick
Makers' products built with each framework that chose either one, for LLM observability & evals.
| Framework | |||
|---|---|---|---|
| 12 | 0 | All 48 Next.js products' picks → |
New launches vs older products
A tool that came first has products from every year since, so its total runs ahead. Here is what products launched each year chose, as a share of those that made the LLM observability & evals decision (by the year they launched on Product Hunt).
| Launched | Products | ||
|---|---|---|---|
| 2024 | 38% 8 | 0% 0 | 21 |
| 2025 | 45% 15 | 0% 0 | 33 |
Cost as you grow
Both cost $0 up to 50k traces; from 100k traces MLflow costs less ($0 vs $29); and still does at 10M traces ($0 vs $821).
The numbers, plan by plan
| Traces per month | Langfuse | MLflow |
|---|---|---|
| 1,000 | $0 Hobby | $0 Self-hosted (open source) |
| 10,000 | $0 Hobby | $0 Self-hosted (open source) |
| 50,000 | $0 Hobby | $0 Self-hosted (open source) |
| 100,000 | $29 Core | $0 Self-hosted (open source) |
| 500,000 | $61 Core | $0 Self-hosted (open source) |
| 1,000,000 | $101 Core | $0 Self-hosted (open source) |
| 5,000,000 | $421 Core | $0 Self-hosted (open source) |
| 10,000,000 | $821 Core | $0 Self-hosted (open source) |
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.
Marc 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
Observability for LLM apps and agents Langfuse helps us trace, debug, and improve agent quality across the platform.
We use it to trace every model call in Flowstep, super useful for debugging
No maker quote about MLflow for LLM observability & evals yet.
Loved and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.
- 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
- 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
Who uses each
What makers pair each with
Neither quite right?
See the whole LLM observability & evals decision →Questions
Langfuse or MLflow: which do makers choose?
Of the 117 makers' products we know the LLM observability & evals of, 35 chose Langfuse (30%) and 0 MLflow (0%). Among the 33 launched in 2025, Langfuse is in 45% and MLflow in 0%. Choose Langfuse if you want tracing, prompts and evals in one tool you can self-host for free; choose MLflow if tracing, evaluating and versioning prompts for LLM apps in the same open-source platform many teams already use for ML experiments.
When should I pick Langfuse over MLflow?
Pick Langfuse if: You want tracing, prompts and evals in one tool you can self-host for free.
How do Langfuse and MLflow compare in cost as you grow?
Both cost $0 up to 50k traces; from 100k traces MLflow costs less ($0 vs $29); and still does at 10M traces ($0 vs $821). Cheapest usable plan at each scale, at list prices.

