Batch from $0.15 per million tokens.
Send a file, get results within your window: 24 hours standard, 72 hours Flex at the lowest price. Drop‑in for the OpenAI Batch API.
pip install openai−from openai import OpenAIclient = OpenAI(api_key=os.environ["MSERVE_API_KEY"],
)file = client.files.create(file=open("input.jsonl", "rb"),purpose="batch",)batch = client.batches.create(input_file_id=file.id,endpoint="/v1/chat/completions",completion_window="24h",)
Same files, same calls.
Upload JSONL, create a batch, download results. If you use the OpenAI Batch API today, you're done.
Pick your window.
A 24-hour window at the standard rate. Choose Flex for a 72-hour window and a deeper discount.
Pay for what ran.
Cancel any time and keep the results that finished. Requests that miss the window come back as expired and are not billed.
Pricing
Model
Qwen3.8 27B (Batch)Best forBatch jobsLicenseApache-2.0Price
24 h$0.22/ 1M tokens
Flex$0.15/ 1M tokens
FAQ
Is there a minimum?
No platform fee. Top up from $5.
How do I pick Flex?
Add metadata: {"tier": "flex"} to the batch. Your SDK types stay the same.
What can run in a batch?
/v1/chat/completions, /v1/completions, and /v1/embeddings.
Start building for less.
One email when your key is ready. Nothing else.