Langfuse's own 200,000-unit Core example
This reproduces the default values displayed by Langfuse's official pricing calculator.
Langfuse
$37- Core base
$29$29 - Additional units
(200K − 100K included) ÷ 100K × $8$8
Comparison
Logfire vs Langfuse
Logfire brings LLM tracing and evaluation into full-stack observability, with PostgreSQL-compatible SQL across the surrounding application, infrastructure, traces, logs, and metrics.
Quick comparison
| Feature | Logfire | Langfuse |
|---|---|---|
| Observability scope | AI and application telemetry across traces, logs, and metrics | LLM tracing, prompts, evaluation, and datasets |
| LLM Tracing | Yes | Yes |
| Token/Cost Tracking | Yes | Yes |
| Prompt Playground | Yes | Yes |
| Human annotations & queues | Annotations on production runs + annotation queues | Annotations on production runs + annotation queues |
| Hosted evaluation | LLM judges and deterministic evaluators on live traffic | Model-based and custom evaluators |
| Continuous improvement | Scheduled proposals and model-swap recommendations | Evaluation and prompt workflows |
| Full-stack workflow | Traces, logs, metrics, and infrastructure views | Trace-oriented LLM observability |
| Database/API context | Native OTel integrations and service context | Can ingest arbitrary OTel spans within traces |
| Query Interface | PostgreSQL-compatible SQL | Product UI, metrics API, and public API |
| MCP server | SQL queries over production telemetry from your editor or AI agent | Query observations, metrics, scores, datasets, and annotation queues |
| OpenTelemetry | Native across full-stack telemetry | Native OTLP trace ingestion |
| Self-Hosting | Enterprise | Open Source |
| Free Tier | 10M logs, spans, and metrics | 50K units |
| Python SDK | Native OpenTelemetry SDK | Native OpenTelemetry SDK |
| JavaScript SDK | Native OpenTelemetry SDK | Native OpenTelemetry SDK |
| Any OTel Language | Yes | Yes |
How each product meters usage
| Pricing dimension | Logfire | Langfuse |
|---|---|---|
| Usage meter | Logs + spans + metrics | Traces + observations + scores |
| Free cloud allowance | 10M records/month | 50K units/month |
| Paid cloud base | $49/month Team | $29/month Core |
| List-price overage | $2/million records | Starts at $8/100K units; volume discounts |
See the exact pricing math and sources
Calculation scope
Published cloud meters and one vendor-calculator example. No cross-vendor total is claimed because a Langfuse trace, observation, and score each count as units while Logfire meters telemetry records.
Basis: USD; public monthly list price. Prices checked .
Published inputs
- Logfire Team base
- $49/month Pydantic Logfire source
- Logfire included telemetry
- 10,000,000 records/month Pydantic Logfire source
- Logfire additional telemetry
- $2 per 1,000,000 records Pydantic Logfire source
- Langfuse Hobby allowance
- 50,000 units/month Langfuse source
- Langfuse Core base
- $29/month Langfuse source
- Langfuse Core allowance
- 100,000 units/month Langfuse source
- Langfuse usage from 100,000 to 1,000,000 units
- $8 per 100,000 units Langfuse source
Assumptions
- Equivalent total
- Not calculated The products' units are not one-to-one without specifying the number of observations and scores per trace.
Calculations
Source ledger
- Pydantic Logfire — Pricing and plans for Pydantic Logfire https://pydantic.dev/pricing
“Covers 10 million logs, spans, and metrics every month.”
The official calculator shows 20 million records and no extra seats totaling $69/month on Team.
- Langfuse — Langfuse pricing and calculator https://langfuse.com/pricing?calculatorOpen=true
“100k units / month included, additional: $8/100k units.”
The official calculator shows a $37 Core total at 200,000 monthly units: $29 base plus $8 usage.
What this calculation does not include
- Langfuse applies lower graduated rates above one million units; the visible table deliberately says the overage starts at $8 per 100,000.
- Provider and model charges are excluded from both products.
Why teams choose Logfire
Full-stack scope
Agent behavior depends on the application around it. Logfire makes model calls, tools, browser RUM and session replay, database queries, APIs, services, logs, metrics, and infrastructure available in the same product, instead of centering the investigation on LLM observations alone.
OpenTelemetry across the whole stack
Logfire applies OpenTelemetry across the entire application, including model and tool calls, databases, APIs, services, logs, metrics, and infrastructure. That keeps instrumentation portable while preserving the context needed to explain production behavior.
SQL query interface
Query telemetry with PostgreSQL-compatible SQL, including joins, aggregations, and ad hoc questions that were not anticipated by a saved dashboard. The same interface is available to coding agents through Logfire's MCP server.
Improve from production evidence
Run hosted LLM judges and deterministic evaluators on sampled production traffic, route low-scoring runs to human review, and turn the resulting evidence into scheduled optimization proposals and model-swap recommendations.
Which should you choose?
Choose Logfire if
- You want agent traces connected to the surrounding application and infrastructure
- You want PostgreSQL-compatible SQL and MCP over production telemetry
- You want hosted evals, human review, and optimization connected to production traces
- You want one OpenTelemetry-native workflow across languages and frameworks
Choose Langfuse if
- Your team is already standardized on Langfuse and wants to keep its existing LLM workflow
Common questions
What is the main difference between Logfire and Langfuse?
Logfire puts LLM tracing, prompts, evaluation, and optimization inside full-stack observability, so model and tool calls stay connected to browser RUM and session replay, databases, APIs, services, logs, metrics, and infrastructure.
Is Logfire more expensive than Langfuse?
The meters are different. Logfire includes 10 million records a month on its free plan; paid plans start at $49 a month and charge $2 per million additional records. Langfuse includes 50,000 units on Hobby or 100,000 on Core, then applies graduated per-unit pricing. In Langfuse, traces, observations, and scores each count as units.
Can I use Logfire with LangChain?
Yes. Logfire provides auto-instrumentation for LangChain, LlamaIndex, OpenAI, Anthropic, and many other AI frameworks. You can visualize complex chains and retrieval flows automatically.
Can I migrate from Langfuse to Logfire?
Yes. Logfire accepts standard OpenTelemetry traces, so you can send the same telemetry to Logfire while you compare production investigations and move integrations incrementally.
Can I self-host Logfire?
Yes. Logfire is available as a managed cloud service or as an Enterprise self-hosted deployment, and its SDK is open source.
Can Logfire evaluate live traffic?
Yes. Run hosted LLM judges or deterministic evaluators without supplying a model key, sample live production traffic, and route low-scoring runs to a human annotation queue. Scores become telemetry you can query, dashboard, and alert on.
Ready to switch from Langfuse?
Get started with 10 million free spans, logs, and metrics per month. No credit card required.