curl --request POST \
  --url https://api.pramaan.dev/v1/capabilities/text.embed-contextual \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "documents": [
    {
      "chunks": [
        "Vector search compares points.",
        "Each point represents a document."
      ]
    }
  ]
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    documents: [
      {
        chunks: ['Vector search compares points.', 'Each point represents a document.']
      }
    ]
  })
};

fetch('https://api.pramaan.dev/v1/capabilities/text.embed-contextual', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.pramaan.dev/v1/capabilities/text.embed-contextual"

payload = { "documents": [{ "chunks": ["Vector search compares points.", "Each point represents a document."] }] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "model": "embed-17",
  "space": "<string>",
  "dimensions": 1537,
  "documents": [
    {
      "embeddings": [
        [
          123
        ]
      ]
    }
  ],
  "usage": {
    "inputTokens": 4503599627370495
  }
}

{
  "error": {
    "code": "addendum_required",
    "message": "<string>",
    "next": "<string>",
    "request_id": "<string>",
    "retryable": true,
    "effect": "none",
    "slot": "<string>",
    "required_micro": 123,
    "reason": "balance",
    "plan": "<string>",
    "needs": [
      {
        "kind": "approval",
        "detail": "<string>",
        "step": "<string>"
      }
    ]
  }
}