To send user-generated data to Moderation Dashboard, you must send a request to the Moderation Dashboard API. The API will return a response outlining which rules were auto-triggered, along with additional data depending on your needs.
The v1 submission endpoint remains in maintenance mode. Existing users should refer to the v1 API documentation and migrate before the endpoint is deprecated.
What is multi-model submission?
- Multi-model submission allows you to send content to multiple models in a single API request, streamlining your moderation process.
- For instance, when handling a video task, you can simultaneously submit it to our Visual Moderation, Audio Moderation, Demographics, and AI-Generated Content Detection models.
- This then enables you to create sophisticated rules that leverage signals from each of the models.
- For example, you can automatically remove a video and ban the user if the Visual Moderation model detects sexual content AND the Demographics model identifies individuals under 18 years old.
- This page has detailed guidance on how to submit to the v2 submission endpoint to fully utilize the capabilities of the multi-model feature.
Authentication
When you submit an API request, you will need to include the API key associated with your Moderation Dashboard application. The API key will be sent via email after you get access to Moderation Dashboard.
Each application you create can have multiple API keys associated with it. However, all API keys are unique to whichever application they are associated with.
AuthenticationInclude the API Key in the header of your POST request ('authorization: token <YOUR_API_KEY>')
Submitting a Task to Moderation Dashboard via API
Moderation Dashboard supports both synchronous (sync) and asynchronous (async) API interface protocols. Our technical team is happy to help you determine the submission process that best fits your use case.
As a general guideline:
| Sync API | Async API |
|---|---|
A synchronous endpoint is preferred for users who have real-time needs, low latency requirements, and are submitting continuous / cyclical requests. The synchronous endpoint keeps the HTTP request open until results have finished processing and then sends the results directly in the response message. | The asynchronous endpoint is preferred for users who are submitting their volume in large batches, or users submitting tasks containing large files (i.e. longer videos or audio clips). The asynchronous endpoint immediately sends a response acknowledging receipt of the task, along with a unique ‘task_id’. It then closes the connection. Once the task is completed, Hive will send a POST request to the provided callback_url containing the completed task’s results. |
