These changes may affect Developer Edition (DE) Orgs, Trailhead Playgrounds, and more.
Org-level model request rate limits:
- 1,000 requests per hour
- 5,000,000 tokens per hour
- 1,000,000 tokens per minute
Model types:
- Models configured for Advanced Prompts are unavailable in Free and Trial orgs. See the Usage Type category in Large Language Model Support for details on each model.
- Features with dedicated rules, such as Agentforce Vibes and its allowlisted Opus models, retain their own limits.
Models API calls:
- 5 requests per minute
- 100 tokens per minute
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: These changes take effect starting the week of October 5, 2026.