Together AI

Together AI is a platform that provides access to efficient and scalable large language models (LLMs). The Together AI connector enables you to access Together AI's API to list available models, manage files, and generate content using various LLM models. This connector is particularly useful for applications that need to integrate AI capabilities, generate text content, build AI-powered applications, or leverage multiple LLM models for different use cases.

Power end-to-end data operations for your Together AI API with Nexla. Our bi-directional Together AI connector is purpose-built for Together 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 Together AI or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Together 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 Together AI credential, you'll need to obtain an API key from your Together AI account. Together AI provides API keys for programmatic access to their LLM platform through the Together AI dashboard.

To obtain a Together AI API key:

1. Log in to your Together AI account at https://api.together.xyz or navigate to the Together AI dashboard.

2. Navigate to your account settings or API dashboard. This is typically accessible from the user menu or dashboard navigation.

3. In the API settings or API Keys section, locate the option to create or manage API keys.

4. Click Create API Key or Generate New Key to create a new API key for your application. You may need to provide a name or description for the API key.

5. Copy the API key immediately after generation, as it may only be displayed once for security purposes. Store it securely, as you'll need it to authenticate API requests.

6. Note your Base URL and API Version. The base URL is typically https://api.together.xyz and the API version is typically v1. These values may vary depending on your Together AI deployment.

Together AI API keys are used as Bearer tokens in the Authorization header for all API requests. The API key is sensitive information and should be kept secure. If you've lost your API key, you'll need to generate a new one in your Together AI account settings.

For detailed information about Together AI API authentication and API key management, refer to the Together AI Documentation.

Authenticate

Credentials required

An authentication method that requires sending a unique secret token with each API request on Together AI

Field	Required	Secret	Description
API Key Value	Yes	Yes	An encoded string value used as a secret token to authenticate API requests on Together AI.
Base URL	Yes	Yes	Please enter the base URL for your Together AI API account.
API Version	Yes	Yes	Please enter the API version for your Together AI API requests.

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.

New Credential Overlay – Together AI

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

3. In the API Key Value field, enter the API key that you obtained from your Together AI account. This is the secret API key used to authenticate requests to the Together AI API.

4. In the Base URL field, enter the base URL for your Together AI API account. This is typically https://api.together.xyz but may vary depending on your deployment.

5. In the API Version field, enter the API version for your Together AI API requests. The default value is v1.

   The API key, base URL, and API version are sensitive information and should be kept secure. If you've lost your API key, you'll need to generate a new one in your Together AI account settings. API keys are used as Bearer tokens in the Authorization header for all API requests.

6. 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 Together AI connector tile, then select the credential that will be used to connect to the Together AI API, and click Next; or, create a new Together 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 Together AI API 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.

List models

This endpoint lists models from Together AI's API. Use this endpoint when you need to discover available models, check model availability, or get model information for further API calls.

• This endpoint automatically retrieves all available models from your Together AI account. No additional configuration is required beyond selecting this endpoint template.

The List models endpoint uses GET requests to retrieve model information from the Together AI API. The endpoint returns a list of all models available for use in your Together AI account. For more information about the List models endpoint, refer to the Together AI API Documentation.

List Files

This endpoint lists metadata for all uploaded data files. Use this endpoint when you need to discover uploaded files, check file status, or get file information for further processing.

• This endpoint automatically retrieves all uploaded files from your Together AI account. No additional configuration is required beyond selecting this endpoint template.

The List Files endpoint uses GET requests to retrieve file metadata from the Together AI API. The endpoint returns a list of all files that have been uploaded to your Together AI account. For more information about the List Files endpoint, refer to the Together AI API Documentation.

List files by ID

This endpoint gets the contents of a single uploaded data file. Use this endpoint when you need to retrieve a specific file's content, download file data, or access file contents for processing.

• Enter the file ID in the File ID field. This is the unique identifier for the file you want to retrieve.

The List files by ID endpoint uses GET requests to retrieve file contents from the Together AI API. The endpoint returns the contents of the specified file. For more information about the List files by ID endpoint, refer to the Together AI API documentation.

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

Together AI data sources can also be manually configured to ingest data from any valid Together AI API endpoint, including endpoints not covered by the pre-built templates, chained API calls, or custom request parameters. Together AI API endpoints typically follow the pattern {base_url}/{api_version}/{endpoint}, where {base_url} and {api_version} are configured in your credential; common endpoints include /{api_version}/models and /{api_version}/files. 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 Together 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 Together AI destination, and select the Send to Destination option from the menu. Select the Together AI connector from the list of available destination connectors, then select the credential that will be used to connect to the Together AI instance, and click Next; or, create a new Together AI credential for use in this flow.

Manual configuration

Together AI destinations can be manually configured to send data to any valid Together AI API endpoint, such as the completions, embeddings, rerank, or chat completions endpoints. Together AI API endpoints typically follow the pattern {base_url}/{api_version}/{endpoint}, where {base_url} and {api_version} are configured in your credential. 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.

For most Together AI ingestion endpoints, the default request body template {message.json} sends the entire record as JSON. The Authorization header with the Bearer token is automatically included from your credential.

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

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