curl --request POST \
  --url http://localhost:8080/openai/v1/batches/{batch_id}/cancel

{
  "id": "<string>",
  "object": "<string>",
  "status": "validating",
  "request_counts": {
    "total": 123,
    "completed": 123,
    "failed": 123,
    "succeeded": 123,
    "expired": 123,
    "canceled": 123,
    "pending": 123
  },
  "cancelling_at": 123,
  "cancelled_at": 123,
  "extra_fields": {
    "request_type": "<string>",
    "provider": "openai",
    "model_requested": "<string>",
    "model_deployment": "<string>",
    "latency": 123,
    "chunk_index": 123,
    "raw_request": {},
    "raw_response": {},
    "cache_debug": {
      "cache_hit": true,
      "cache_id": "<string>",
      "hit_type": "<string>",
      "provider_used": "<string>",
      "model_used": "<string>",
      "input_tokens": 123,
      "threshold": 123,
      "similarity": 123
    }
  }
}