docs(proxy): clarify mcp_rpm_limit is enforced for keys and teams, not per user

This commit is contained in:
mateo-berri 2026-06-02 13:24:11 +00:00
parent a34126afae
commit 8c74ef7d37
No known key found for this signature in database

View file

@ -386,7 +386,7 @@ async def new_user(
- soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests.
- model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
- model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
- mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}
- mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}. Enforced for keys and teams only; values set on a user are stored but not enforced per user.
- model_tpm_limit: Optional[float] - Model-specific tpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
- spend: Optional[float] - Amount spent by user. Default is 0. Will be updated by proxy whenever user is used. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
- agent_id: Optional[str] - The agent id associated with the user.
@ -1428,7 +1428,7 @@ async def user_update(
- soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests.
- model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
- model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
- mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}
- mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}. Enforced for keys and teams only; values set on a user are stored but not enforced per user.
- model_tpm_limit: Optional[float] - Model-specific tpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
- spend: Optional[float] - Amount spent by user. Default is 0. Will be updated by proxy whenever user is used. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
- agent_id: Optional[str] - The agent id associated with the user.