Nebius AI

Nebius AI Studio is a managed inference platform for running large language, embedding, and image-generation models. Its OpenAI-compatible REST API supports LLM inference, vector embeddings, image generation, file management, asynchronous batch processing, and fine-tuning. The Nexla connector lets you read model, file, batch, and fine-tuning metadata as a data source and submit inference, upload, and job-management requests as a destination.

Power end-to-end data operations for your Nebius AI API with Nexla. Our bi-directional Nebius AI connector is purpose-built for Nebius AI, 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 Nebius AI or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Nebius AI 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 Nebius AI credential, you need a Nebius AI Studio API key. The API uses Bearer token authentication, with the key passed in the Authorization header as Bearer <your-api-key>.

To obtain your API key, follow these steps:

1. Sign in to the Nebius AI Studio console.

2. Open the API keys section of the console.

3. Select the option to create a new API key and provide a descriptive name for it.

4. Create the key, then copy and securely store the value that is displayed. The key is shown only once and cannot be retrieved later.

You will also need the Base URL for your Nebius AI Studio API endpoint. The connector defaults to https://api.studio.nebius.ai; confirm the correct base URL for your account in the Nebius AI Studio API reference. Keep your API key confidential, and revoke and regenerate it from the console if it is ever exposed. For details, see the Nebius AI Studio API reference.

Authenticate

Credentials required

Field	Required	Secret	Description
API Key	Yes	Yes	Your Nebius AI Studio API key (Bearer token).
Base URL	Yes	No	The base URL for the Nebius AI Studio API.

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 Nebius AI Studio API key in the API Key field. This value is sent as a Bearer token in the Authorization header for all API requests and must be kept confidential.

4. Enter your API endpoint in the Base URL field. If you are unsure, use the default value https://api.studio.nebius.ai.

   If your API key is compromised, revoke it in the Nebius AI Studio console and generate a new one. The API key grants access to your Nebius AI Studio resources and should be treated as sensitive information.

   For detailed information about authentication and available endpoints, see the Nebius AI Studio API reference.

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 Nebius AI connector tile, then select the credential that will be used to connect to Nebius AI Studio, and click Next; or, create a new Nebius AI 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 Nebius AI 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 Models

Returns a list of available AI models in the Nebius API.

Use this endpoint to enumerate the models available to your account. For details, see the Nebius AI Studio API reference.

[Rest API] Get Model Metadata

Retrieve metadata for a specific model by its ID.

• This endpoint requires a model Id to identify the model whose metadata to retrieve.

For details, see the Nebius AI Studio API reference.

[Rest API] List Files

Returns a list of files available in the Nebius API.

For details, see the Nebius AI Studio API reference.

[Rest API] Get File Metadata

Retrieve metadata for a specific file (name, size, purpose, status).

• This endpoint requires a file Id to identify the file whose metadata to retrieve.

For details, see the Nebius AI Studio API reference.

[Rest API] Get File Contents

Retrieves the contents of a specific file by its ID.

• This endpoint requires a File ID to identify the file whose contents to retrieve.

For details, see the Nebius AI Studio API reference.

[Rest API] List Batches

Returns a list of batch processing jobs in the Nebius API.

• This endpoint is paginated; Nexla automatically follows the cursor to fetch subsequent pages of data.

For details, see the Nebius AI Studio API reference.

[Rest API] Get Batch Job

Retrieve the status and metadata of a specific batch job.

• This endpoint requires a batch Id to identify the batch job to retrieve.

For details, see the Nebius AI Studio API reference.

[Rest API] List Fine-Tuning Jobs

List all fine-tuning jobs and their statuses.

• This endpoint is paginated; Nexla automatically follows the cursor to fetch subsequent pages of data.

For details, see the Nebius AI Studio API reference.

[Rest API] Get Fine-Tuning Job

Retrieve the status and metadata of a specific fine-tuning job by its ID.

• This endpoint requires a Job ID to identify the fine-tuning job to retrieve.

For details, see the Nebius AI Studio API reference.

[Rest API] List Fine-Tuning Checkpoints

Returns a list of checkpoints for a specific fine-tuning job.

• This endpoint requires a Job ID to identify the fine-tuning job whose checkpoints to list. It is paginated; Nexla automatically follows the cursor to fetch subsequent pages of data.

For details, see the Nebius AI Studio API reference.

[Rest API] List Dedicated Endpoints

Returns a list of dedicated inference endpoints for the project.

For details, see the Nebius AI Studio API reference.

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

Nebius AI data sources can also be manually configured to ingest data from any valid Nebius AI Studio 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 Nebius AI 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 Nebius AI destination, and select the Send to Destination option from the menu. Select the Nebius AI connector from the list of available destination connectors, then select the credential that will be used to connect to Nebius AI Studio, and click Next; or, create a new Nebius AI 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 Nebius AI 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] Submit Chat/LLM Inference Request

Submit a chat/LLM inference request — the primary use-case of Nebius AI Studio.

• Each record from your Nexset is sent as a JSON request body to the chat completions endpoint. The record should contain the model and messages fields expected by the Nebius AI Studio API.

For details, see the Nebius AI Studio API reference.

[Rest API] Generate Vector Embeddings

Generate vector embeddings from input text using a Nebius embedding model.

• Each record from your Nexset is sent as a JSON request body containing the model and input text to embed.

For details, see the Nebius AI Studio API reference.

[Rest API] Generate Images

Generate images from a text prompt using Nebius image generation models.

• Each record from your Nexset is sent as a JSON request body containing the model and prompt used to generate images.

For details, see the Nebius AI Studio API reference.

[Rest API] Upload File

Upload a file (e.g. JSONL batch input file) to Nebius AI Studio storage.

• This endpoint sends data using multipart/form-data. Each record from your Nexset is uploaded as a file to Nebius AI Studio storage.

For details, see the Nebius AI Studio API reference.

[Rest API] Delete File

Delete a file from Nebius AI Studio storage.

• This endpoint requires a file Id to identify the file to delete.

For details, see the Nebius AI Studio API reference.

[Rest API] Create Batch Job

Create a new batch job for asynchronous LLM processing.

• Each record from your Nexset is sent as a JSON request body describing the batch job to create.

For details, see the Nebius AI Studio API reference.

[Rest API] Cancel Batch Job

Cancel a running batch job.

• This endpoint requires a batch Id to identify the batch job to cancel.

For details, see the Nebius AI Studio API reference.

[Rest API] Create Fine-Tuning Job

Create a fine-tuning job to train a custom model on uploaded data.

• Each record from your Nexset is sent as a JSON request body describing the fine-tuning job to create.

For details, see the Nebius AI Studio API reference.

[Rest API] Create Dedicated Endpoint

Create a new dedicated inference endpoint for a specified model.

• Each record from your Nexset is sent as a JSON request body describing the dedicated endpoint to create.

For details, see the Nebius AI Studio API reference.

Manual configuration

Nebius AI destinations can also be manually configured to send data to any valid Nebius AI Studio 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.

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 Nebius AI endpoint, open the destination resource menu, and select Activate.

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