Marketers
See which channels and pages bring visitors who convert.
Review Langfuse daily trace counts, observations, latency, cost and evaluation scores in a read-only data source.
Updated November 2026
| Date | Traces | Observations |
|---|---|---|
| 2026-11-13 | 4210 | 18900 |
| Oct 28 | 640 | 640 |
| Oct 29 | 210 | 210 |
See which channels and pages bring visitors who convert.
Get a weekly traffic summary without opening another dashboard.
Send each client the same clean traffic report every month.
Read daily metrics, traces and scores using your Langfuse Public and Secret Keys.
Datapipe reads Langfuse data for reports. It never changes anything in Langfuse.
Traces and prompts are never modified.
Combine daily metrics, trace latencies and score trends in one report.
An API key or token from your Langfuse account.
Read access only. Datapipe never changes anything in Langfuse.
Read-only. Traces and scores are never changed, prompt text is not included, and only Langfuse Cloud regions are supported.
Daily LLM metrics, execution traces, and evaluation scores from Langfuse.
Read-only reporting access using your Langfuse Public and Secret Keys. Traces and prompts are never modified.
Read-only. Traces and scores are never changed, prompt text is not included, and only Langfuse Cloud regions are supported.
4 reporting datasets, each with its own fields. Pick one in the app, then choose your columns.
Daily trace counts, observation counts, scores, and model costs.
Langfuse daily trace counts, observation counts, and total model cost.
Langfuse LLM execution traces with name, user ID, latency, and cost.
Langfuse evaluation scores linked to traces.
15 report fields across 3 datasets.
Hover or tap a field to see what it means. Custom fields from your own account appear after you connect.
No fields match. Try another search or choose All.
Claude or ChatGPT can read the same numbers. You ask in a normal sentence, and the answer stays with your report.
Summarize Langfuse daily trace volume, model cost, and evaluation scores.
Langfuse logged 28,400 traces and $194.20 in model cost with an average quality score of 0.91.
Langfuse daily trace counts, observation counts, and total model cost.
Use this template →Langfuse LLM execution traces with name, user ID, latency, and cost.
Use this template →Langfuse evaluation scores linked to traces.
Use this template →Daily trace counts, observation counts, scores, and model costs.
Use this template →Create a project and choose Langfuse in Data sources.
Pick where it goes. This one sends the numbers to Data Studio.
Pick where it goes. Choose daily metrics, traces or scores and a destination.
| Date | Traces | Observations | Total cost (USD) | Trace name | User ID | Latency (s) | Total cost (USD) |
|---|---|---|---|---|---|---|---|
| 2026-11-13 | 4210 | 18900 | $31.20 | 1,240 | 1024 | 1,240 | $31.20 |
| Oct 28 | 640 | 640 | $125.50 | 640 | 1025 | 640 | $125.50 |
| Oct 29 | 210 | 210 | $42.00 | 210 | 1031 | 210 | $42.00 |
Sample numbers, so you can see the shape. Your report uses your accounts.
Add both to the same project. Each keeps its own report, so you can check them side by side or ask ChatGPT or Claude a question that needs both.
Free to start. Paid plans add more data sources and refresh faster.
Free and Starter refresh once a day. Pro refreshes every hour. Agency refreshes every 15 minutes on the first 50 data sources.
No. Name a project, add a data source, then choose a report and destination.
OAuth means you sign in with the service and grant access, without pasting an API key. Datapipe works with multiple partners to provide that sign-in. Some partners already provide it. Some integrations are API-only at present, so you paste a key or token. OAuth is coming soon for some. Some partners do not provide OAuth at all. The setup steps on each integration page say how that source connects. Signing in is only how the connection is made. It is not permission to change records. Where a source supports changes, those writes stay off until the workspace owner turns specific actions on and approves each one. We do not promise OAuth on every source, and we do not share dates.
This integration is read-only in Datapipe. You can report on Langfuse, send the reports to your destinations and ask an AI assistant about them. Datapipe never changes anything in Langfuse. Read-only reporting access using your Langfuse Public and Secret Keys. Traces and prompts are never modified.
This page lists 15 report fields across 3 datasets. You pick the columns when you build the report.
Daily LLM metrics, execution traces, and evaluation scores from Langfuse. Account permissions and the records available from the provider determine which rows can be read.
One for each Langfuse account you add to a project. Adding the same account to another project counts again. Reports and destinations do not use extra data sources.
Yes. The same numbers can go to a sheet, a chart, a warehouse, or an assistant.
Build the report first, then add Langfuse when you are ready.