When should I pick Langfuse over Arize Phoenix?

Pick Langfuse if: You want tracing, prompts and evals in one tool you can self-host for free.

Which do more makers use for LLM observability & evals?

Among makers' products we track: Arize Phoenix 0, Langfuse 33.

How do Arize Phoenix and Langfuse compare in cost as you grow?

Both cost $0 up to 10k traces; from 50k traces Langfuse costs less ($0 vs $50). Cheapest usable plan at each scale, at list prices.

Arize Phoenix vs Langfuse

Q: When should I pick Arize Phoenix over Langfuse?

Pick Arize Phoenix if: You already use OpenTelemetry or want vendor-neutral instrumentation.

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.

Arize PhoenixOpen-source platformllms.txt

LangfuseOpen-source platformllms.txt CLI

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

Which fits you

Choose Arize Phoenix if

You already use OpenTelemetry or want vendor-neutral instrumentation

Use it whenYou already use OpenTelemetry or want vendor-neutral instrumentation.

Trade-offSource-available under the Elastic License rather than a permissive open-source license.

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.

At a glance

	Arize Phoenix	Langfuse
Used by	No maker's product yet · 19 open-source projects	33 makers' products · 43 open-source projects
Cost at default usagetraces 100k traces	Over plan limits	$29/mo Core
Downloads	80.4k/wk+180% vs npm	1.8M/wk+81% vs npm
Pricing	Phoenix is free to self-host; Arize's managed product is Arize AX, with paid plans from $50/month. · paid from $50/mo	Free tier (50k units/mo); usage-based paid plans; fully free to self-host under MIT license. · paid from $29/mo
Free tier	Yes	Yes
Open source	No · self-hostable	Yes · self-hostable
Incidents, 90 daysfrom its status page	no public status feed	15 (1 major)

Cost as you grow

Both cost $0 up to 10k traces; from 50k traces Langfuse costs less ($0 vs $50).

Langfuse Arize Phoenixx: traces per month (trace) · cheapest usable plan at each point, list prices · try your own numbers

The numbers, plan by plan

Traces per month	Arize Phoenix	Langfuse
1,000	$0 AX Free	$0 Hobby
10,000	$0 AX Free	$0 Hobby
50,000	$50 AX Pro	$0 Hobby
100,000	over plan limits	$29 Core
500,000	over plan limits	$61 Core
1,000,000	over plan limits	$101 Core
5,000,000	over plan limits	$421 Core
10,000,000	over plan limits	$821 Core

From each vendor's pricing page: Arize Phoenix, Langfuse.

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 Arize Phoenix

No maker quote about Arize Phoenix for LLM observability & evals yet.

On Langfuse

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

stagewise, the makerSep 2026 ↗

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!

Magic Patterns, the makerSep 2026 ↗

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.

MCP-Builder.ai, the makerSep 2026 ↗

21 more on the Langfuse page →

Loved and watch-outs

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.

Arize PhoenixNothing that recurs in what we collected yet.

Langfuse

Most loved

Detailed traces show each agent call and the context it pulled, which makes debugging agent behaviour much easier. PH PH 2 HN
Token usage and cost are tracked across providers alongside quality, in one place. PH PH 2 HN
Open source and self-hostable, a common default for teams wanting tracing on their own infrastructure. PH HN HN 2 HN 3

Watch-outs

Prompt management and experiments feel basic next to the tracing core. HN HN 2 HN 3
Views are retrospective dashboards, so explaining one run's cost or failure still means reading trace trees by hand. HN HN 2 HN 3 HN 4
The ClickHouse acquisition raised GDPR and data-residency concerns for EU users of the cloud version. HN HN 2

On Product Hunt: 5.0★, 48 reviews · mentioned most: LLM observability, open source, detailed tracing