Batch Generate

Batch Generate processes up to 100 AI generation requests in a single API call. You submit an array of generation specifications -- each with its own model, prompt, and parameters -- and the system distributes them across GPU infrastructure in parallel. Results are delivered via webhook callback or polling endpoint, with each item tracked by its own generation ID. Developers building content pipelines, e-commerce product image generators, and automated marketing systems use batch generation to process large volumes efficiently. A product catalog team can generate lifestyle images for 100 SKUs in one call. A content platform can produce thumbnails, social cards, and preview images in a single batch. Any workflow that needs more than a handful of generations benefits from the reduced overhead of batch submission. Structure your batch requests with consistent parameters where possible -- this helps the system optimize GPU allocation. Include a unique client reference ID per item for easy reconciliation with your database. Use the webhook callback option rather than polling for high-volume workflows to reduce API calls. Each item in the batch is billed at its individual generation cost with no batch surcharge.