What it's for
Two of our agent notes use it for tracing and evals, so you can show a client the accuracy numbers.
- Tracing LLM apps
- Evals
- Prompt management
Plans and prices
| Plan | Price (USD unless shown) | What you get |
|---|---|---|
| Hobby | $0 | 50k units/month; 30 days data access; 2 users |
| Core | $29/mo | 100k units/month, then $8 per 100k; 90 days data access; unlimited users |
| Pro | $199/mo | 100k units/month, then $8 per 100k; 3 years data access |
| Enterprise | $2,499/mo |
Read on the official pricing page on . Prices change; check before you buy.
Free plan in real output
Hobby is free with 50k units a month, 30 days of data and 2 users. It's open source, so self-hosting is also possible.
- Hobby: 50k units a month covers tracing a demo agent for a client.
- Core at $29/mo adds 90 days of history, useful when a client asks how accuracy changed.
Cost at your stage
| Plan | Monthly cost | |
|---|---|---|
| Month 1 (testing, low volume) | Hobby | $0 |
| Month 12 (working volume) | Core | $29 |
Break-even: Core at $29/mo is covered by any monthly agent-maintenance retainer.
Month-12 plan is our estimate of what a solo seller at steady weekly output needs, based on the plan limits above. Costs exclude tax.
Commercial use and output rights
Not a content generator. An observability tool; your traces stay yours.
Your data and AI training: Not checked.
This is a summary of public terms, not legal advice. Terms change; re-read the clause before client work.
First-hour setup
- Create a free project.
- Add the SDK to your agent.
- Log a test run and inspect the trace.
- Create a small eval dataset.
- Share a dashboard with the client.
Competitors compared
| Tool | Pricing model | Free plan | Starting price | Difficulty | Output rights | Best for |
|---|---|---|---|---|---|---|
| Langfuse | Free plan + paid plans | Yes | $0 · then $29/mo | 3/5 | Not a content generator | Debugging and evaluating LLM apps |
| LangChain | Free, open source | Yes | Free | 4/5 | – | Developers building agents and RAG pipelines |
| LlamaIndex | Free, open source | Yes | Free | 4/5 | – | RAG over documents |
| CrewAI | Free, open source | Yes | Free | 4/5 | – | Multi-agent workflows |
| pgvector | Free, open source | Yes | Free | 4/5 | – | Vector search in an existing Postgres database |
| Pinecone | Free plan + paid plans | Yes | See official site | 3/5 | – | Managed vector search at scale |
| OpenAI Agents SDK | Free, open source | Yes | Free | – | – | Lightweight agents on OpenAI models |
Learning difficulty
3/5: Needs SDK integration.
When not to use it
If you aren't building LLM apps, skip it.
Cheaper or free alternatives:
- LangChain: Developers building agents and RAG pipelines (yes free plan)
- LlamaIndex: RAG over documents (yes free plan)
- CrewAI: Multi-agent workflows (yes free plan)
Which of our hustles use it
- AI agent building for clients: Tracing and evals so you can prove accuracy
- RAG knowledge-base chatbots for companies: Tracing questions and debugging bad answers
Price history
Each monthly check adds rows here. Older rows are never edited, so you can see when prices changed.
Sources
- Langfuse pricing (read 17 October 2026)
Last verified . Anything we couldn't confirm on an official page is marked "not published", "not shown" or "not verified".