Knowledge Base

Documentation to help you use the POEditor localization platform effectively

How to get an API key for your AI integration

Owner

To connect your preferred LLM for AI translation, go to Integrations, select your provider, and enter the API key from your provider account.

Below is where to find the API key for each provider, as of October 6, 2026.

Translations through POEditor use the provider's API, which is billed separately by the provider. A ChatGPT or Claude subscription doesn't cover API usage.

Getting your OpenAI API key

  1. Sign in to the OpenAI API platform and open API keys.
  2. Click Create new secret key and fill in the dialog.
  3. Copy the key. OpenAI shows it only once.

To connect the key to POEditor, see the ChatGPT integration article.

Creating a Claude API key

  1. Sign in to the Claude Console and go to Settings > API keys.
  2. Click Create key, name the key, choose an expiration, set Linked account to yourself or a service account and choose a workspace.
  3. Copy the key, which starts with sk-ant-. The Console shows it only once.

Although the workspace is optional in the Console, POEditor only works with keys scoped to a workspace.

The Claude integration article explains how to add the key in POEditor.

Where to find your Gemini API key

  1. Go to the API keys page in Google AI Studio and sign in with your Google account.
  2. Click Create API key and follow the dialog.
  3. Copy the key.

Keys created in AI Studio from May 28, 2026 onwards work in POEditor. The Gemini API rejects older keys that don’t have API restrictions, so if yours is older, create a new one.

For the next steps in POEditor, check the Gemini integration article.

Finding your Azure AI key and endpoint

  1. In the Azure portal, open your Azure OpenAI or Microsoft Foundry resource and select Keys and Endpoint under Resource Management.
  2. Copy KEY 1 or KEY 2 into API key, and the endpoint into Endpoint. The endpoint looks like https://your-resource.openai.azure.com/ or https://your-resource.services.ai.azure.com/.
  3. After connecting, enter the Deployment name. This is the name you gave the model when you deployed it in Microsoft Foundry, not the model’s own name.

For the full setup in POEditor, see the Azure AI integration article.

Generating an Amazon Bedrock API key

  1. Sign in to the Amazon Bedrock console and select API keys in the left navigation pane.
  2. In the Long-term API keys tab, click Generate long-term API keys, choose when the key expires under API key expiration and click Generate.
  3. Copy the key.
  4. In Endpoint, enter the endpoint for your AWS Region, for example https://bedrock-runtime.us-east-1.amazonaws.com/ or https://bedrock-mantle.us-east-1.api.aws/.

POEditor loads the list of models from bedrock-mantle, so choose an AWS Region that has a bedrock-mantle endpoint, even if you enter a bedrock-runtime endpoint. In other Regions, you can't choose a model.

To translate with Claude models, use a bedrock-runtime endpoint. AWS also asks for a one-time use case form before you use Claude models for the first time, which you can submit by selecting a Claude model from the model catalog in the Bedrock console.

Once you have the key and endpoint, go to the Amazon Bedrock integration article to connect them in POEditor.

Additional help

Related articles