Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Deploying your Microsoft Foundry custom translation model makes it available for use with the Azure Translator API. A language pair might have one or many successfully trained models. You can only deploy one model per language pair; however, you can deploy a model to one or multiple regions depending on your needs. For more information, see Translator pricing.
Deploy your trained model
You can deploy one model per language pair to one or multiple regions.
Select Deploy model from the menu on the left.
Select the model name under Name and check the button then select Deploy model.
Check the desired regions. Later, you can add or remove regions by selecting Update regions.
Select Deploy model. The status should transition from Updating_deployment to Deployed_region_names.
Replace a deployed model
To replace a deployed model, you can exchange the deployed model with a different model in the same region:
Select the model name under Name then select Deploy model.
Select Swap model.
The redeployment takes several minutes to complete. In the meantime, deployed model continues to be available for use with the Translator API until this process is complete.
