Krish DholakiaandGitHub 6bb1d77f45 Org level tpm/rpm limits + Team tpm/rpm validation when assigned to org (#15549) ...

* fix(support-model-specific-tpm/rpm-limits): Allows setting rate limits by tpm/rpm for models by team

* fix(key_management_endpoints.py): enforce guaranteed throughput with key-level model tpm/rpm limits, when team-level tpm/rpm limits are set

* test: add unit testing

* feat(schema.prisma): add metadata to litellm budget table

* feat(proxy/utils.py): add org limits to user api key auth

allows org level tpm/rpm limiting to work

* feat: add org level tpm/rpm limits + inherit org id in key from team

enables org level tpm/rpm limits

* feat: validated working org tpm/rpm limits

* feat: support updating org level, model specific tpm/rpm limits

* fix: working key validation for org level tpm/rpm limits

* fix: working validation for orgs when giving tpm/rpm to teams

* fix(key_management_endpoints.py): fix tpm/rpm limits on orgs

* fix(key_management_endpoints.py): support limits

* refactor: remove duplicate var

* fix: refactor to avoid ruff errors

* fix: fix typign

* fix: fix linting error

* fix: fix testing

* fix(key_management_endpoints.py): document params

2025-10-25 13:40:29 -07:00

..

__init__.py

…

internal_user_endpoints.py

[Feat] Proxy CLI: Create a python method to login using litellm proxy (#14782)

2025-09-22 21:28:38 -07:00

key_management_endpoints.py

Org level tpm/rpm limits + Team tpm/rpm validation when assigned to org (#15549)

2025-10-25 13:40:29 -07:00