Skip to content
Blackbird docs

Anthropic

View on Github

A next-generation AI assistant for your tasks, no matter the scale

Before setting up

Before you can connect you need to make sure that:

  • Anthropic API token connection type: You have an Anthropic account and have access to the API keys.
  • Amazon Bedrock (AWS Credentials) connection type: You have AWS Access key and Secret key and the Region code where the models were enabled. The IAM user must have these policies enabled: bedrock:InvokeModel, bedrock:ListFoundationModels.
  • Amazon Bedrock (API Key) connection type: You have a Bedrock API token generated in the AWS console under Bedrock -> Settings -> API keys, and you have the Region code.

Note: For Amazon Bedrock connection types, you also need to have access to the specific Anthropic models. Go to AWS Bedrock Console -> Model access -> Manage model access and check the boxes for the Anthropic models.

Connecting

Navigate to apps and search for Anthropic. If you cannot find Anthropic then click Add App in the top right corner, select Anthropic and add the app to your Blackbird environment. Click Add Connection and name your connection for future reference e.g. ‘My connection’.

Anthropic API token

  1. Fill in your API key. You can create a new API key under API keys. The API key has the shape sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.
  2. Click Connect.

Anthropic API token

Amazon Bedrock (AWS Credentials)

  1. Fill in your Access key, Secret key and Region.
  2. Click Connect.

Amazon Bedrock AWS Creds

Amazon Bedrock (API Key)

  1. Fill in your API token and Region.
  2. Click Connect.

Amazon Bedrock API Key

Actions

Chat actions

  • Chat action has the following input values in order to configure the generated response:
  1. Model (All current and available models are listed in the dropdown)
  2. Prompt
  3. Max tokens to sample
  4. Temperature
  5. top_p
  6. top_k
  7. System prompt
  8. Stop sequences

For more in-depth information about action consult the Anthropic API reference.

XLIFF actions

  • Translate Translate file content retrieved from a CMS or file storage. The output can be used in compatible actions.
  • Edit Edit a translation. This action assumes you have previously translated content in Blackbird through any translation action.
  • Review Review translation. This action assumes you have previously translated content in Blackbird through any translation action.
  • Process XLIFF processes the XLIFF file and returns updated XLIFF with the translated content. By default it will translate source and place the translation in the target field. But you can modify behavior by providing your custom prompt. Deprecated: use the ‘Translate’ action instead.
  • Post-edit XLIFF file action is used to post-edit the XLIFF file. Deprecated: use the ‘Edit’ action instead.
  • Get Quality Scores for XLIFF file action is used to get quality scores for the XLIFF file by adding extradata attribute to the translation unit of the file. Default criteria are fluency, grammar, terminology, style, and punctuation, but you can add your own by filling prompt optional input. Deprecated: use the ‘Review’ action instead.
  • Get MQM report from XLIFF Perform an LQA Analysis on a translated file. The result will be in the MQM framework form.

Batch actions

Note: Currently, batch actions are not supported for Amazon Bedrock connection types.

  • (Batch) Process XLIFF file asynchronously process each translation unit in the XLIFF file according to the provided instructions (by default it just translates the source tags) and updates the target text for each unit.
  • (Batch) Post-edit XLIFF file asynchronously post-edit the target text of each translation unit in the XLIFF file according to the provided instructions and updates the target text for each unit.
  • (Batch) Get Quality Scores for XLIFF file asynchronously get quality scores for each translation unit in the XLIFF file.
  • (Batch) Get XLIFF from the batch get the results of the batch process. This action is suitable only for processing and post-editing XLIFF file and should be called after the async process is completed.
  • (Batch) Get XLIFF from the quality score batch get the quality scores results of the batch process. This action is suitable only for getting quality scores for XLIFF file and should be called after the async process is completed.

Token usage

For all actions you can configure the ‘Max tokens’ optional input. This value limits the number of tokens generated in the response. If left empty, the default value will be the maximum number of tokens allowed by the model. For example, Claude Sonnet 4 has a maximum of 64,000 output tokens - leaving this field empty means 64,000 will be used as the value. To limit the tokens generated in the response, set this value to a lower number.

Model Comparison

The following table compares the key characteristics of Claude models:

ModelMax OutputContext Window
Claude Opus 4.132,000 tokens200K tokens
Claude Opus 432,000 tokens200K tokens
Claude Sonnet 464,000 tokens200K / 1M (beta) tokens
Claude Sonnet 3.764,000 tokens200K tokens
Claude Haiku 3.58,192 tokens200K tokens
Claude Haiku 34,096 tokens200K tokens

Max output is the most important metric to consider when choosing a model for translation tasks, as it determines how much text can be generated in a single response. The context window is also important, especially for tasks that require understanding of larger documents or conversations like glossaries.

Feedback

Do you want to use this app or do you have feedback on our implementation? Reach out to us using the established channels or create an issue.