Create batch
$ openai batches create
post /batches
Creates and executes a batch from an uploaded file of requests
Parameters
-
--completion-window: "24h"The time frame within which the batch should be processed. Currently only
24his supported. -
--endpoint: "/v1/responses" or "/v1/chat/completions" or "/v1/embeddings" or 5 moreThe endpoint to be used for all requests in the batch. Currently
/v1/responses,/v1/chat/completions,/v1/embeddings,/v1/completions,/v1/moderations,/v1/images/generations,/v1/images/edits, and/v1/videosare supported. Note that/v1/embeddingsbatches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch. -
--input-file-id: stringThe ID of an uploaded file that contains requests for the new batch.
See upload file for how to upload a file.
Your input file must be formatted as a JSONL file, and must be uploaded with the purpose
batch. The file can contain up to 50,000 requests, and can be up to 200 MB in size. -
--metadata: optional map[string]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
--output-expires-after: optional object { anchor, seconds }The expiration policy for the output and/or error file that are generated for a batch.
Returns
-
batch: object { id, completion_window, created_at, 19 more }-
id: string -
completion_window: stringThe time frame within which the batch should be processed.
-
created_at: numberThe Unix timestamp (in seconds) for when the batch was created.
-
endpoint: stringThe OpenAI API endpoint used by the batch.
-
input_file_id: stringThe ID of the input file for the batch.
-
object: "batch"The object type, which is always
batch. -
status: "validating" or "failed" or "in_progress" or 5 moreThe current status of the batch.
-
"validating" -
"failed" -
"in_progress" -
"finalizing" -
"completed" -
"expired" -
"cancelling" -
"cancelled"
-
-
cancelled_at: optional numberThe Unix timestamp (in seconds) for when the batch was cancelled.
-
cancelling_at: optional numberThe Unix timestamp (in seconds) for when the batch started cancelling.
-
completed_at: optional numberThe Unix timestamp (in seconds) for when the batch was completed.
-
error_file_id: optional stringThe ID of the file containing the outputs of requests with errors.
-
errors: optional object { data, object }-
data: optional array of BatchError-
code: optional stringAn error code identifying the error type.
-
line: optional numberThe line number of the input file where the error occurred, if applicable.
-
message: optional stringA human-readable message providing more details about the error.
-
param: optional stringThe name of the parameter that caused the error, if applicable.
-
-
object: optional stringThe object type, which is always
list.
-
-
expired_at: optional numberThe Unix timestamp (in seconds) for when the batch expired.
-
expires_at: optional numberThe Unix timestamp (in seconds) for when the batch will expire.
-
failed_at: optional numberThe Unix timestamp (in seconds) for when the batch failed.
-
finalizing_at: optional numberThe Unix timestamp (in seconds) for when the batch started finalizing.
-
in_progress_at: optional numberThe Unix timestamp (in seconds) for when the batch started processing.
-
metadata: optional map[string]Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
-
model: optional stringModel ID used to process the batch, like
gpt-5-2025-08-07. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models. -
output_file_id: optional stringThe ID of the file containing the outputs of successfully executed requests.
-
request_counts: optional object { completed, failed, total }The request counts for different statuses within the batch.
-
completed: numberNumber of requests that have been completed successfully.
-
failed: numberNumber of requests that have failed.
-
total: numberTotal number of requests in the batch.
-
-
usage: optional object { input_tokens, input_tokens_details, output_tokens, 2 more }Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used. Only populated on batches created after September 7, 2025.
-
input_tokens: numberThe number of input tokens.
-
input_tokens_details: object { cached_tokens }A detailed breakdown of the input tokens.
-
cached_tokens: numberThe number of tokens that were retrieved from the cache. More on prompt caching.
-
-
output_tokens: numberThe number of output tokens.
-
output_tokens_details: object { reasoning_tokens }A detailed breakdown of the output tokens.
-
reasoning_tokens: numberThe number of reasoning tokens.
-
-
total_tokens: numberThe total number of tokens used.
-
-
Example
openai batches create \
--api-key 'My API Key' \
--completion-window 24h \
--endpoint /v1/responses \
--input-file-id input_file_id
Response
{
"id": "id",
"completion_window": "completion_window",
"created_at": 0,
"endpoint": "endpoint",
"input_file_id": "input_file_id",
"object": "batch",
"status": "validating",
"cancelled_at": 0,
"cancelling_at": 0,
"completed_at": 0,
"error_file_id": "error_file_id",
"errors": {
"data": [
{
"code": "code",
"line": 0,
"message": "message",
"param": "param"
}
],
"object": "object"
},
"expired_at": 0,
"expires_at": 0,
"failed_at": 0,
"finalizing_at": 0,
"in_progress_at": 0,
"metadata": {
"foo": "string"
},
"model": "model",
"output_file_id": "output_file_id",
"request_counts": {
"completed": 0,
"failed": 0,
"total": 0
},
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
}
}