Einstein Requests
Catalog row in Vendor License Metrics · Cited
- Unit
- Other
- Aliases
- Einstein Request
- Definition
- Some of Salesforce's generative AI Services and features consume Einstein Requests. Salesforce Services may have included a quantity of Einstein Requests, with the specific entitlement indicated in the Usage Details table on the Order Form for such Services. Each API call made through the LLM gateway to a Large Language Model (LLM) consumes Einstein Requests.
- Counting rules
- Each API call made through the LLM gateway to a Large Language Model (LLM) consumes Einstein Requests. The API call size factor is calculated by: adding the size of the prompt request plus the size of the LLM-generated response, in tokens dividing by 2,000 tokens, and rounding up to the next highest integer. Einstein Requests per LLM API Call = Round up (Total input and output tokens /2000) * (4-10 for Salesforce-managed models and 4 for BYO-LLM). Multipliers as of October 24, 2025: BYO LLM Starter Prompts 4; Salesforce-enabled Basic 4 / Standard 10 / Advanced 38. Salesforce publishes no conversion between E1E/E4X and A1E. Which SKUs consume Einstein Requests vs Flex Credits is SKU/order-form specific.
- Floors / minimums
- Size factor uses a 2,000-token band. Included quantity is Order Form only.
- Related metrics
- Related from