Forge LLM tokens per minute rate limit increased to 500,000
- Announced
- Tags
- forge-core-platform
- Severity
- notable, set by
reef/atlassian-rule-v2 - Source
- https://developer.atlassian.com/changelog/#CHANGE-3497
What’s changing
The tokens per minute (TPM) rate limit for Forge LLMs has been increased from 50,000 to 500,000.
This 10x increase allows you to build more complex agentic solutions and handle larger volumes of data within Forge's hosted app platform. The limit applies per installation of your app for each model.
What you need to do
No action is required to benefit from this increase; the new limit is already active for all Forge apps using the LLM API.
If your app previously encountered rate limiting errors (429 Too Many Requests) due to token usage, you may now be able to increase the frequency or size of your LLM requests. For more details on all Forge LLM constraints, including requests per minute and context window sizes, see the Forge LLM limits documentation.
More details
See https://developer.atlassian.com/platform/forge/limits-llm/ for more information.
The text above is the source's. reef added the severity, the dates it could read from the text, and the endpoints and scopes named in code.