Some model providers now support batch processing natively, increasing the maximum number of requests per job. When using models that support native batch processing in Flow, there is a limit of 50,000 items per day.
These models support native batch processing:
- GPT 4.1
- GPT 4.1 Mini
- GPT 4 Omni
- GPT 4 Omni Mini
- GPT 5
- GPT 5 Mini
- OpenAI GPT 4 Omni Mini
- Bedrock Claude Haiku 4.5
- Bedrock Claude Sonnet 4.5
Where: This change applies to Lightning Experience in Enterprise, Performance, and Unlimited editions with an Einstein for Sales, Einstein for Platform, or Einstein for Service add-on.
When: This feature is available starting the week of 2/2.