Both the OpenAI client and the Google genai clients have very similar interfaces for managing batches:
# Create file
uploaded_file = client.files.upload(
file='my-batch-requests.jsonl',
config=types.UploadFileConfig(display_name='my-batch-requests', mime_type='jsonl')
)
# Start batch
file_batch_job = client.batches.create(
model="gemini-2.5-flash",
src=uploaded_file.name,
config={
'display_name': "file-upload-job-1",
},
)
https://platform.openai.com/docs/guides/batch
# Create file
batch_input_file = client.files.create(
file=open("test_batch_subset.jsonl", "rb"),
purpose="batch"
)
# Start batch
client.batches.create(
input_file_id=batch_input_file.id,
endpoint="/v1/chat/completions",
completion_window="24h",
metadata={
"description": "RPMD Test Batch",
}
)
Extending Gemini’s OpenAI compatibility to the batch APIs would be great!