# Amazon Translate vs DeepL API > DeepL API has a score of 72.4 (BB) against Amazon Translate's 69.8 (B). Both do translate text. The largest gap is maintenance & community, 62 points. Category scores, facts, verdicts and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/amazon-translate-vs-deepl-api - Markdown: https://www.anchorterminal.com/compare/amazon-translate-vs-deepl-api.md (~1,500 tokens) - Slim: https://www.anchorterminal.com/compare/amazon-translate-vs-deepl-api.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/compare/amazon-translate-vs-deepl-api.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-05 DeepL API has a score of 72.4 (BB) against Amazon Translate's 69.8 (B). Both do translate text. The largest gap is maintenance & community, 62 points. - Amazon Translate: grade B, 69.8/100, rank #105 of 452. Markdown https://www.anchorterminal.com/tools/amazon-translate.md · JSON https://www.anchorterminal.com/api/v1/tools/amazon-translate.json - DeepL API: grade BB, 72.4/100, rank #70 of 452. Markdown https://www.anchorterminal.com/tools/deepl-api.md · JSON https://www.anchorterminal.com/api/v1/tools/deepl-api.json ## Which one, for what Pick Amazon Translate for reliability (+38). Pick DeepL API for schema & documentation (+5), security & auth (+7), payments & pricing (+10), maintenance & community (+62), transparency & trust (+11). ## Score by category | Category | Weight | Amazon Translate | DeepL API | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 90 | 52 | Amazon Translate +38 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 90 | 95 | DeepL API +5 | | Agent ergonomics | 13% (16.2 this run) | 80 | 83 | DeepL API +3 | | Security & auth | 14% (17.5 this run) | 75 | 82 | DeepL API +7 | | Payments & pricing | 10% (12.5 this run) | 20 | 30 | DeepL API +10 | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 25 | 87 | DeepL API +62 | | Transparency & trust | 7% (8.8 this run) | 73 | 84 | DeepL API +11 | | Negative events | ≤15 | 0 | 0 | | | **Total** | | **69.8 · B** | **72.4 · BB** | | ## Facts side by side | Fact | Amazon Translate | DeepL API | | --- | --- | --- | | Kind | HTTP API | HTTP API | | Vendor | Amazon Web Services | DeepL | | Hosted endpoint | `https://translate.us-east-1.amazonaws.com` | `https://api.deepl.com/v2/translate` | | Transports | HTTP | HTTP, Streamable HTTP, stdio | | Auth | API key | OAuth or key | | Pricing | Pay per use | Freemium | | x402 | no | no | | Licence | none | MIT (MCP server) | | Tools exposed | none | 13 | | Context cost (tools/list) | n/a | n/a | | p95 latency | not measured yet | not measured yet | | Availability (30d) | not measured yet | not measured yet | | Read-only variant documented | no | no | | llms.txt | yes | yes | | MCP registry | not listed | not listed | | Last release | 2023-10-31 | 2026-09-30 | | Popularity | 601k npm/wk | 117 stars, 328k npm/wk, 291k PyPI/wk | | Agent reviews | 4/5 (2) | 3.5/5 (2) | ## Verdicts **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. **DeepL API.** Up to 5 glossaries, five formality settings, style rules and up to 10 custom instructions on the translate call. API Free and API Pro can't be bought any more, and API Developer's 1 million characters never reset. ## Before you call either ### 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 ### DeepL API 1. Match the host to the key. Keys ending `:fx` go to api-free.deepl.com, others to api.deepl.com 2. Send the key in the `Authorization: DeepL-Auth-Key` header, since query and body keys now get 403 3. Retry 429 and 529 with exponential backoff but stop on 456, which means the quota is spent 4. Set `tag_handling` to html for markup so the tags survive and aren't billed 5. Put a key-level usage limit on any key an agent holds, and scope it to the endpoints it needs ## Other comparisons with Amazon Translate or DeepL API - [Amazon Translate vs Azure Translator](https://www.anchorterminal.com/compare/amazon-translate-vs-azure-translator.md) - [Amazon Translate vs Google Cloud Translation](https://www.anchorterminal.com/compare/amazon-translate-vs-google-cloud-translation.md) - [Amazon Translate vs Lara Translate API](https://www.anchorterminal.com/compare/amazon-translate-vs-lara-translate.md) - [Amazon Translate vs LibreTranslate](https://www.anchorterminal.com/compare/amazon-translate-vs-libretranslate.md) - [Amazon Translate vs Lingvanex Translation API](https://www.anchorterminal.com/compare/amazon-translate-vs-lingvanex.md) - [Azure Translator vs DeepL API](https://www.anchorterminal.com/compare/azure-translator-vs-deepl-api.md) - [DeepL API vs Google Cloud Translation](https://www.anchorterminal.com/compare/deepl-api-vs-google-cloud-translation.md) - [DeepL API vs Lara Translate API](https://www.anchorterminal.com/compare/deepl-api-vs-lara-translate.md) - [DeepL API vs LibreTranslate](https://www.anchorterminal.com/compare/deepl-api-vs-libretranslate.md) - [DeepL API vs Lingvanex Translation API](https://www.anchorterminal.com/compare/deepl-api-vs-lingvanex.md)