Amazon Translate vs Smartcat

Amazon Translate

IAM policies scope access per action and resource, with a TranslateReadOnly managed policy, and CloudTrail logs each call. AWS may store and use text to improve Amazon AI services unless the organisation sets an opt-out policy.

Smartcat

Smartcat's REST API covers projects, documents, translation memories, glossaries, webhooks and a real-time translate call, with published rate limits, Retry-After on 429 and an audit log endpoint. Keys are account-wide with no documented scopes, the status page lists two incidents of an hour or more in 90 days, and API access is listed only from the $60,000-a-year Anticipate plan.

Amazon Translate

1. Chunk real-time text under 10,000 bytes, not characters, so multibyte scripts fit less per call
2. Pass SourceLanguageCode auto to detect the source language, and handle DetectedLanguageLowConfidenceException
3. Read AppliedSettings in the response, since unsupported formality or profanity settings are dropped without an error
4. Retry TooManyRequestsException with backoff, which the AWS SDKs do by default
5. Set the AI services opt-out policy before sending private text

Smartcat

1. Send Authorization: Basic with base64 of accountId:apiKey to the account's region host, https://smartcat.ai, https://us.smartcat.ai or https://ea.smartcat.ai.
2. On 429, wait the seconds in Retry-After before retrying. The 429 itself carries no x-rate-limit-* headers.
3. Create a smart translation profile in the web app first and pass its ID as profile to smartTranslation/translate.
4. Store each requestUid and look charges up later with smartTranslation/charges, since the translate response doesn't include the cost.
5. Treat callbacks as hints and poll project, document or export status as a fallback, because failed deliveries are dropped after the last retry.