> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/nebius-token-factory.md).

# Nebius Token Factory

Generate chat responses, embeddings, images, and batch inference jobs with Nebius Token Factory.

### Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector            | Authentication |
| -------------------- | -------------- |
| Nebius Token Factory | API Key        |

#### Nebius Token Factory

Connect to Nebius Token Factory to generate chat responses, embeddings, images, and batch inference jobs.

**Set up in Nebius Token Factory**

1. Prepare the Nebius Token Factory account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create an API key in the Nebius Token Factory console.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Nebius Token Factory**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                                    |
| ------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------- |
| API Key       | Yes      | Create an API key in the Nebius Token Factory console. [Provider instructions](https://docs.tokenfactory.nebius.com/quickstart). |

#### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

### Use an action

1. Add the required **Nebius Token Factory** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

### Actions

#### Create Chat Completion

Generate a Nebius assistant response from a user message.

**Inputs**

| Field                 | Type            | Required | Description                                                                                    |
| --------------------- | --------------- | -------- | ---------------------------------------------------------------------------------------------- |
| Model                 | select (string) | Yes      | Nebius model used to generate the response. Options load from the selected connection.         |
| Message               | textarea        | Yes      | The request or prompt for the assistant.                                                       |
| System Message        | textarea        | No       | Optional instructions that guide how the assistant responds.                                   |
| Conversation History  | textarea        | No       | Optional earlier user and assistant turns to continue.                                         |
| Maximum Output Tokens | integer         | No       | Maximum number of tokens Nebius may generate. Minimum: 0.                                      |
| Temperature           | number          | No       | Controls response randomness from focused to varied. Minimum: 0. Maximum: 2.                   |
| Response Format       | select (string) | No       | Return normal text or a valid JSON object. Available values: Text, JSON Object. Default: text. |

**Outputs**

| Field             | Type     | Description                          |
| ----------------- | -------- | ------------------------------------ |
| Response ID       | string   | Nebius identifier for the response.  |
| Model             | string   | Model that generated the response.   |
| Response Text     | textarea | Text generated by Nebius.            |
| Finish Reason     | string   | Why the model stopped generating.    |
| Prompt Tokens     | integer  | Input tokens reported by Nebius.     |
| Completion Tokens | integer  | Generated tokens reported by Nebius. |
| Total Tokens      | integer  | Total tokens reported by Nebius.     |

#### Generate Text Embeddings

Convert one or more text values into vector embeddings.

**Inputs**

| Field      | Type            | Required | Description                                                                                   |
| ---------- | --------------- | -------- | --------------------------------------------------------------------------------------------- |
| Model      | select (string) | Yes      | Nebius embedding model used to create the vectors. Options load from the selected connection. |
| Texts      | textarea        | Yes      | Text values to turn into embeddings, one non-empty value per line.                            |
| Dimensions | integer         | No       | Optional vector size when the selected model supports it.                                     |

**Outputs**

| Field         | Type    | Description                                      |
| ------------- | ------- | ------------------------------------------------ |
| Model         | string  | Model that generated the embeddings.             |
| Embeddings    | array   | Float vectors aligned with the input text order. |
| Prompt Tokens | integer | Input tokens reported by Nebius.                 |
| Total Tokens  | integer | Total tokens reported by Nebius.                 |

#### Generate Image from Text

Generate one image from a text prompt.

**Inputs**

| Field            | Type            | Required | Description                                                                                                           |
| ---------------- | --------------- | -------- | --------------------------------------------------------------------------------------------------------------------- |
| Model            | select (string) | Yes      | Nebius image model used to generate the image. Options load from the selected connection.                             |
| Prompt           | textarea        | Yes      | Description of the image to create.                                                                                   |
| Negative Prompt  | textarea        | No       | Details the generated image should avoid.                                                                             |
| Width            | integer         | No       | Generated image width in pixels. Minimum: 64. Maximum: 2048. Default: 1024.                                           |
| Height           | integer         | No       | Generated image height in pixels. Minimum: 64. Maximum: 2048. Default: 1024.                                          |
| Generation Steps | integer         | No       | Number of refinement steps used to create the image. Minimum: 1. Maximum: 80. Default: 30.                            |
| Seed             | integer         | No       | Optional seed for reproducible generation. Minimum: -1.                                                               |
| Response Format  | select (string) | No       | Return a temporary image link or base64 image data. Available values: Temporary URL, Base64 Image Data. Default: url. |

**Outputs**

| Field        | Type     | Description                                   |
| ------------ | -------- | --------------------------------------------- |
| Request ID   | string   | Nebius identifier for the generation request. |
| Image URL    | string   | Temporary URL for the generated image.        |
| Base64 Image | textarea | Base64 image data when requested.             |

#### List Models

List models available to the connected Nebius project.

**Inputs**

No input fields are required in this catalog entry.

**Outputs**

| Field       | Type          | Description                                |
| ----------- | ------------- | ------------------------------------------ |
| Models      | object\_array | Models available to the connected project. |
| Model Count | integer       | Number of models returned.                 |

#### Create Batch Inference Job

Start chat or embedding inference over an existing Nebius dataset.

**Inputs**

| Field                 | Type            | Required | Description                                                                                                                    |
| --------------------- | --------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------ |
| Dataset ID            | string          | Yes      | Existing Nebius Data Lab dataset to process.                                                                                   |
| Task Type             | select (string) | No       | Run chat completion or embedding inference for each dataset row. Available values: Chat Completion, Embeddings. Default: chat. |
| Model                 | select (string) | Yes      | Nebius model used for each dataset row. Options load from the selected connection.                                             |
| Input Column          | string          | No       | Dataset column containing messages or embedding input. Default: messages.                                                      |
| Maximum Output Tokens | integer         | No       | Maximum generated tokens for every chat row. Default: 1024.                                                                    |
| Dimensions            | integer         | No       | Optional vector size for every embedding row.                                                                                  |
| Custom ID Column      | string          | No       | Optional dataset column used to correlate input and output rows.                                                               |

**Outputs**

| Field                  | Type    | Description                                         |
| ---------------------- | ------- | --------------------------------------------------- |
| Operation ID           | string  | Nebius identifier for the new batch operation.      |
| Status                 | string  | Initial state of the batch operation.               |
| Source Dataset ID      | string  | Dataset submitted for processing.                   |
| Source Dataset Version | string  | Current dataset version resolved before submission. |
| Destination Dataset ID | string  | Dataset where Nebius will write batch results.      |
| Created At             | integer | Unix timestamp when the operation was created.      |

### Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/nebius-token-factory.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
