Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Upload file

files.create(FileCreateParams**kwargs) -> FileObject
POST/files

Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and each project can store up to 2.5 TB of files in total. There is no organization-wide storage limit. Uploads to this endpoint are rate-limited to 1,000 requests per minute per authenticated user.

  • The Assistants API supports files up to 2 million tokens and of specific file types. See the Assistants Tools guide for details.
  • The Fine-tuning API only supports .jsonl files. The input also has certain required formats for fine-tuning chat or completions models.
  • The Batch API only supports .jsonl files up to 200 MB in size. The input also has a specific required format.
  • For Retrieval or file_search ingestion, upload files here first. If you need to attach multiple uploaded files to the same vector store, use /vector_stores/{vector_store_id}/file_batches instead of attaching them one by one. Vector store attachment has separate limits from file upload, including 2,000 attached files per minute per organization.

Please contact us if you need to increase these storage limits.

ParametersExpand Collapse
file: FileTypes

The File object (not file name) to be uploaded.

purpose: FilePurpose

The intended purpose of the uploaded file. One of:

  • assistants: Used in the Assistants API
  • batch: Used in the Batch API
  • fine-tune: Used for fine-tuning
  • vision: Images used for vision fine-tuning
  • user_data: Flexible file type for any purpose
  • evals: Used for eval data sets
expires_after: Optional[ExpiresAfter]

The expiration policy for a file. By default, files with purpose=batch expire after 30 days and all other files are persisted until they are manually deleted.

ReturnsExpand Collapse
class FileObject: …

The File object represents a document that has been uploaded to OpenAI.

id: str

The file identifier, which can be referenced in the API endpoints.

bytes: int

The size of the file, in bytes.

created_at: int

The Unix timestamp (in seconds) for when the file was created.

formatunixtime
filename: str

The name of the file.

object: Literal["file"]

The object type, which is always file.

purpose: Literal["assistants", "assistants_output", "batch", 5 more]

The intended purpose of the file. Supported values are assistants, assistants_output, batch, batch_output, fine-tune, fine-tune-results, vision, and user_data.

Deprecatedstatus: Literal["uploaded", "processed", "error"]

Deprecated. The current status of the file, which can be either uploaded, processed, or error.

expires_at: Optional[int]

The Unix timestamp (in seconds) for when the file will expire.

formatunixtime
Deprecatedstatus_details: Optional[str]

Deprecated. For details on why a fine-tuning training file failed validation, see the error field on fine_tuning.job.

Upload file

from openai import OpenAI
client = OpenAI()

client.files.create(
  file=open("mydata.jsonl", "rb"),
  purpose="fine-tune",
  expires_after={
    "anchor": "created_at",
    "seconds": 2592000
  }
)
{
  "id": "file-abc123",
  "object": "file",
  "bytes": 120000,
  "created_at": 1677610602,
  "expires_at": 1677614202,
  "filename": "mydata.jsonl",
  "purpose": "fine-tune",
}
Returns Examples
{
  "id": "file-abc123",
  "object": "file",
  "bytes": 120000,
  "created_at": 1677610602,
  "expires_at": 1677614202,
  "filename": "mydata.jsonl",
  "purpose": "fine-tune",
}