Langfuse

Langfuse is an open-source LLM engineering platform for tracing, evaluation, prompt management, and metrics for LLM applications. Its Public API exposes all Langfuse data and features over REST, letting you read traces, observations, sessions, scores, datasets, prompts, and metrics, and write telemetry and configuration back into your project.

Power end-to-end data operations for your Langfuse API with Nexla. Our bi-directional Langfuse connector is purpose-built for Langfuse, making it simple to ingest data, sync it across systems, and deliver it anywhere — all with no coding required. Nexla turns API-sourced data into ready-to-use, reusable data products and makes it easy to send data to Langfuse or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Langfuse workflows fast, secure, and fully governed.

Features

Type: API

SourceDestination

• Seamless API Integration: Connect to any endpoint as source or destination without coding, with automatic data product creation
• Visual Composition & Chaining: Build complex integrations using visual templates, chain API calls, and compose workflows with data validation and filtering
• API Proxy: Expose curated slices of your data securely with a secure and customizable API proxy that validates and transforms data on the fly
• Request optimization with intelligent batching, retry, and caching to minimize API calls and costs

Prerequisites

Before creating a Langfuse credential, you need a Langfuse project API key pair (a Public Key and a Secret Key) and the base URL for your Langfuse data region. The Langfuse Public API authenticates with HTTP Basic Auth, using the Public Key as the username and the Secret Key as the password.

To obtain your Langfuse credentials, follow these steps:

1. Sign in to Langfuse at your data region (for example, https://cloud.langfuse.com for the EU region), or to your self-hosted instance.

2. Select the project you want to connect to.

3. Open Project Settings, then go to the API Keys section.

4. Click Create new API keys to generate a key pair. Langfuse displays a Public Key (used as the Basic Auth username) and a Secret Key (used as the Basic Auth password).

5. Copy the Secret Key immediately and store it securely. Langfuse shows the Secret Key only once, and it cannot be retrieved again after you leave the page. If it is lost or compromised, delete the key pair and create a new one.

6. Note your data region base URL. Langfuse Cloud uses https://cloud.langfuse.com (EU), https://us.cloud.langfuse.com (US), or https://hipaa.cloud.langfuse.com (HIPAA); self-hosted deployments use your own instance URL.

Some endpoints (for example, organization- and project-management endpoints) require an organization-scoped API key rather than a project key pair. For detailed information about authentication, data regions, and available endpoints, see the Langfuse Public API documentation.

Authenticate

Credentials required

Field	Required	Secret	Description
Public Key	Yes	No	Langfuse Public Key from Project Settings -> API Keys. Used as the Basic Auth username.
Secret Key	Yes	Yes	Langfuse Secret Key from Project Settings -> API Keys. Used as the Basic Auth password. Treat as a secret.
Data Region Base URL	Yes	No	Base URL for your Langfuse data region: EU (default) https://cloud.langfuse.com, US https://us.cloud.langfuse.com, HIPAA https://hipaa.cloud.langfuse.com, or your self-hosted instance URL.

Create a credential in Nexla

1. After selecting the data source/destination type, click the Add Credential tile to open the Add New Credential overlay.

2. Enter a name for the credential in the Credential Name field and a short, meaningful description in the Credential Description field.

3. Enter your Langfuse Public Key and Secret Key in their respective fields. These form the HTTP Basic Auth pair (Public Key as username, Secret Key as password) that authenticates every request to the Langfuse Public API.

4. Enter your Data Region Base URL. Use the base URL that matches the region or self-hosted instance where your Langfuse project lives.

   The Secret Key is sensitive and is shown only once when the key pair is created in Langfuse. If it is lost or compromised, delete the key pair in Project Settings and create a new one.

   For detailed information about authentication, data regions, and available endpoints, see the Langfuse Public API documentation.

5. Click the Save button at the bottom of the overlay. The newly added credential will now appear in a tile on the Authenticate screen during data source/destination creation.

Use as a data source

To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Select the Langfuse connector tile, then select the credential that will be used to connect to the Langfuse instance, and click Next; or, create a new Langfuse credential for use in this flow.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Langfuse endpoints. Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below.

[Rest API] List Traces

List traces matching the given filter criteria.

[Rest API] List Observations (v2)

List observations (spans/generations/events) with field-group filtering and cursor pagination.

[Rest API] List Sessions

List sessions grouping related traces.

[Rest API] List Scores (v2)

List scores attached to traces/observations/sessions matching the given filter criteria.

[Rest API] List Scores (v3)

List scores using the newest v3 schema with cursor pagination.

[Rest API] List Score Configs

List score configuration definitions (the allowed value ranges/categories for scores).

[Rest API] List Datasets

List datasets used for evaluation and experimentation.

[Rest API] List Dataset Items

List items (input/expected-output pairs) belonging to a dataset.

[Rest API] List Dataset Run Items

List run items produced when a dataset run is executed against a dataset.

[Rest API] List Dataset Runs

List runs of a specific dataset by dataset name.

[Rest API] List Prompts

List managed prompt templates.

[Rest API] List Comments

List comments left on traces, observations, sessions, or prompts.

[Rest API] List Models

List model price/tokenizer definitions used for cost calculation.

[Rest API] Get Metrics (v2)

Run a custom metrics query (aggregations/time series over traces, observations, and scores).

[Rest API] Health Check

Check the health/version of the Langfuse API.

[Rest API] List LLM Connections

List configured LLM provider connections used for evaluators/playground.

[Rest API] List Annotation Queues

List human-annotation queues.

[Rest API] List Annotation Queue Items

List items assigned to a specific annotation queue.

[Rest API] List Projects

List projects accessible to the calling API key.

[Rest API] List Project API Keys

List API keys for a specific project (organization-scoped keys only).

[Rest API] List Organization Projects

List all projects in the calling organization (organization-scoped keys only).

[Rest API] List Organization Memberships

List memberships (users and roles) of the calling organization.

[Rest API] List Project Memberships

List memberships (users and roles) of a specific project.

[Rest API] List Experiments

List experiments (dataset runs with evaluation scores) with cursor pagination.

[Rest API] List Experiment Items

List individual experiment items with cursor pagination.

[Rest API] List Blob Storage Integrations

List configured blob storage export integrations for the organization (requires organization-scoped API key).

[Rest API] List Organization API Keys

List organization-scoped API keys (organization-scoped keys only).

[Rest API] List Dashboards (Beta)

List custom dashboards. Beta/unstable API - subject to change.

[Rest API] List Evaluators (Beta)

List configured LLM-as-a-judge evaluators. Beta/unstable API - subject to change.

[Rest API] List Evaluation Rules (Beta)

List evaluation rules that trigger evaluators on new traces. Beta/unstable API.

Once the selected endpoint template has been configured, click the Test button to the right of the endpoint selection menu to retrieve a sample of the data that will be fetched. Sample data will be displayed in the Endpoint Test Result panel on the right, allowing you to verify that the source is configured correctly before saving.

Manual configuration

Langfuse data sources can also be manually configured to ingest data from any valid Langfuse Public API endpoint, including endpoints not covered by the pre-built templates, chained API calls, or custom request parameters. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, endpoint URL, date/time and lookup macros, path to data, metadata, and request headers.

Once all of the relevant settings have been configured, click the Create button in the upper right corner of the screen to save and create the new Langfuse data source. Nexla will now begin ingesting data from the configured endpoint and will organize any data that it finds into one or more Nexsets.

Use as a destination

Click the + icon on the Nexset that will be sent to the Langfuse destination, and select the Send to Destination option from the menu. Select the Langfuse connector from the list of available destination connectors, then select the credential that will be used to connect to the Langfuse instance, and click Next; or, create a new Langfuse credential for use in this flow.

Endpoint templates

Nexla provides pre-built templates that can be used to rapidly configure destinations to send data to common Langfuse endpoints. Select the endpoint to which data will be sent from the Endpoint pulldown menu. Then, click on the template in the list below to expand it, and follow the instructions to configure additional endpoint settings.

[Rest API] Ingest Events (Batch)

Batch-ingest tracing events (traces, observations/spans/generations, scores) into Langfuse. This is the primary way to write telemetry data into Langfuse.

[Rest API] Create Comment

Create a comment on a trace, observation, session, or prompt.

[Rest API] Create Dataset Item

Create or upsert an item (input/expected-output pair) in a dataset.

[Rest API] Create Dataset Run Item

Record a dataset run item, linking a dataset item to a trace/observation produced by a run.

[Rest API] Create Dataset

Create a new dataset for evaluation/experimentation.

[Rest API] Create Prompt

Create a new prompt version (text or chat) under a managed prompt name.

[Rest API] Update Prompt Version Labels

Update the labels (e.g. 'production', 'latest') on a specific prompt version.

[Rest API] Create Score Config

Create a new score configuration (categorical/numeric/boolean value range) for scoring.

[Rest API] Create Model

Create a custom model price/tokenizer definition for cost calculation.

[Rest API] Create Score (Legacy v1)

Attach a score to a trace, observation, or session. Legacy v1 endpoint, still fully supported.

Manual configuration

Langfuse destinations can also be manually configured to send data to any valid Langfuse Public API endpoint. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, data format, endpoint URL, request headers, attribute exclusions, record batching, and response webhooks.

Langfuse Public API endpoints expect JSON request bodies. Ingestion is handled through the batch ingestion endpoint, which accepts multiple events per request.

Save & activate

Once all endpoint settings have been configured, click the Done button in the upper right corner of the screen to save and create the destination. To send the data to the configured Langfuse endpoint, open the destination resource menu, and select Activate.

The Nexset data will not be sent to the Langfuse endpoint until the destination is activated. Destinations can be activated immediately or at a later time, providing full control over data movement.