# i18n-llm-translate


### Compare Engines

- Claude Sonnet 3.7, translates whole namespace file, so it can be most accurate, but sloooow, check for pricing 
    - maybe implement chunking
- OpenAI is fastest LLM implementation here, with good context is like 99% on point
- DeepL is like 70% on point

### Mapping Languages
{language}
{!language}
{_language}

### Engines

#### Engine type
- llm (Large Language Model)
- ml (Machine Learning) - traditional translate api like DeepL, Google Translate