curl -i -X POST \
  https://marcie.redocly.app/_mock/openapi/text/translate/accuracy \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_API_KEY_HERE' \
  -d '{
    "text1": "You owe me 200 dollars, and I am here till today.",
    "text2": "Vous me devez 200 dollars, et je suis là jusqu'\''à aujourd'\''hui.",
    "explain": true
  }'

curl -i -X POST \
  https://marcie.redocly.app/_mock/openapi/text/enrichment/plainlang/rewrite \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_API_KEY_HERE' \
  -d '{
    "text": "Quantum mechanics is a basic theory in physics that explains how things work at the tiny scale of atoms and subatomic particles. It is the basis for all quantum physics, like quantum chemistry, quantum field theory, quantum technology, and quantum information science."
  }'

curl -i -X POST \
  https://marcie.redocly.app/_mock/openapi/text/enrichment/readability/rewrite \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_API_KEY_HERE' \
  -d '{
    "text": "These methods still require supervised training in order to perform a task. When only minimal or no supervised data is available, another line of work has demonstrated the promise of language models to perform specific tasks, such as common sense reasoning (Schwartz et al., 2017) and sentiment analysis (Radford et al., 2017). In this paper, we connect these two lines of work and continue the trend of more general methods of transfer. We demonstrate language models can perform down-stream tasks in a zero-shot setting – without any parameter or architecture modification. We demonstrate this approach shows potential by highlighting the ability of language models to perform a wide range of tasks in a zero-shot setting. We achieve promising, competitive, and state of the art results depending on the task.",
    "target": "5"
  }'