· Updated
gpt-image-1.5, chatgpt-image-latest, gpt-image-1, and gpt-image-1-mini. You submit up to 50,000 jobs in a JSONL file, and results come back within 24 hours through a separate rate limit pool - no competing with your sync traffic.Until now, generating images at scale meant hitting rate limits or paying full price per call. Batch processing at half the cost changes the economics for teams building visual pipelines - product catalogs, dataset augmentation, automated marketing. The dedicated rate pool is equally important: bulk work no longer degrades your production API.
Switch your bulk image pipelines to the Batch API via the /v1/images/generations or /v1/images/edits endpoints - the same models and parameters work as in sync mode.
🎨 Generating or editing images at scale? Batch API now supports GPT Image models: gpt-image-1.5, chatgpt-image-latest, gpt-image-1, gpt-image-1-mini. Submit up to 50,000 generations or edits as async jobs at 50% lower cost with separate rate limits. https://t.co/9W6TCeBGw3 https://t.co/KMcBIf8UxR
More like this
OpenAIMar 15
OpenRouterApr 24
GoogleApr 1
LumaMay 5