Skip to main content
For the following example to work, save your API key to the NEBIUS_API_KEY environment variable.

​
Create a batch: POST

Request: 
client.batches.create(
    input_file_id=batch_requests.id,
    endpoint="/v1/chat/completions",
    completion_window="24h",
    metadata={
        "description": "Asynchronous job"
    }
)

{
  "id": "batch_123",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "errors": null,
  "input_file_id": "file-123",
  "completion_window": "24h",
  "status": "validating",
  "output_file_id": null,
  "error_file_id": null,
  "created_at": 1730723835,
  "in_progress_at": null,
  "expires_at": 1730810235,
  "completed_at": null,
  "failed_at": null,
  "expired_at": null,
  "request_counts": {
    "total": 0,
    "completed": 0,
    "failed": 0
  },
  "metadata": {
    "customer_id": "user_123",
    "batch_description": "Asynchronous job"
  }
}

​
Get batch info: GET

Request: 
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.studio.nebius.com/v1/",
    api_key=os.environ.get("NEBIUS_API_KEY"),
)

client.batches.retrieve("batch_123")

{
  "id": "batch_123",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "errors": null,
  "input_file_id": "file-123",
  "completion_window": "24h",
  "status": "validating",
  "output_file_id": null,
  "error_file_id": null,
  "created_at": 1730723835,
  "in_progress_at": null,
  "expires_at": 1730810235,
  "completed_at": null,
  "failed_at": null,
  "expired_at": null,
  "request_counts": {
    "total": 0,
    "completed": 0,
    "failed": 0
  },
  "metadata": {
    "customer_id": "user_123",
    "batch_description": "Asynchronous job"
  }
}

​
List batches: GET

Request: 
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.studio.nebius.com/v1/",
    api_key=os.environ.get("NEBIUS_API_KEY"),
)

client.batches.list()

{
  "object": "list",
  "data": [
    {
      "id": "batch_123",
      "object": "batch",
      "endpoint": "/v1/chat/completions",
      "errors": null,
      "input_file_id": "file-123",
      "completion_window": "24h",
      "status": "completed",
      "output_file_id": "file-re45SV",
      "error_file_id": "file-TrOWL1",
      "created_at": 1730723835,
      "in_progress_at": 1730723839,
      "expires_at": 1730810235,
      "finalizing_at": 1730797684,
      "completed_at": 1730797702,
      "failed_at": null,
      "expired_at": null,
      "cancelling_at": null,
      "cancelled_at": null,
      "request_counts": {
        "total": 120,
        "completed": 117,
        "failed": 3
      },
      "metadata": {
        "customer_id": "user_123456789",
        "batch_description": "Asyncronous job"
      }
    },
    { ... },
  ],
  "first_id": "batch_123",
  "last_id": "batch_987",
  "has_more": true
}

​
Cancel a batch: POST

Request: 
client.batches.cancel("batch_123")

{
  "id": "batch_123",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "errors": null,
  "input_file_id": "file-123",
  "completion_window": "24h",
  "status": "cancelling",
  "output_file_id": null,
  "error_file_id": null,
  "created_at": 1730723835,
  "in_progress_at": null,
  "expires_at": 1730810235,
  "finalizing_at": null,
  "completed_at": null,
  "failed_at": null,
  "expired_at": null,
  "cancelling_at": 1730735840,
  "cancelled_at": null,
  "request_counts": {
    "total": 100,
    "completed": 20,
    "failed": 0
  },
  "metadata": {
    "customer_id": "user_123",
    "batch_description": "Asynchronous job"
  }
}
To learn more about batch inference, see Batch inference. For detailed field descriptions, see the API reference.