litellm/litellm-rust/docs/customer-proxy
Nate Armstrong b83353906b
feat(gateway): enforce key, team, user, member and end-user budgets on shared spend counters (#47044)
Adds a built-in budgets hook that runs the proxy's budget checks, in its
order and with its messages, on the proxy's Redis spend:* counters. Each
request reads and seeds the counters, checks them and reserves its
maximum cost in one Redis script, then settles the reservation to its
real cost off the request path, so replicas and Python proxies sharing
the Redis enforce one budget. Without Redis the counters are kept per
replica. The key store now reads user, team member and end-user budgets,
and auth no longer checks budgets against stored spend.


Claude-Session: https://claude.ai/code/session_0138knkqKpkoSr6PApenZan5

Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-19 09:58:44 -07:00
..
bedrock_messages-flow.svg feat(gateway): native Bedrock invoke for /v1/messages (#46814) 2026-10-16 12:43:01 -07:00
budgets.svg feat(gateway): enforce key, team, user, member and end-user budgets on shared spend counters (#47044) 2026-10-19 09:58:44 -07:00
hooks-pipeline.svg feat(gateway): hooks and observers around inference requests, with usage and cost (#47032) 2026-10-19 09:58:43 -07:00
loadtest-rig.svg feat(gateway): load-test kit, Docker build knobs and TCP_NODELAY for the customer proxy (#46806) 2026-10-16 12:42:59 -07:00
openai_chat-flow.svg feat(gateway): native OpenAI chat completions with SSE passthrough (#46813) 2026-10-16 12:43:00 -07:00
ops-drain.svg feat(gateway): health probes, Prometheus /metrics and graceful drain (#46808) 2026-10-16 12:43:00 -07:00
ops-metrics.svg feat(gateway): health probes, Prometheus /metrics and graceful drain (#46808) 2026-10-16 12:43:00 -07:00
routing-cooldown.svg feat(router): load balance, retry and cool down across deployments of a model group (#46817) 2026-10-16 12:43:01 -07:00
routing-request-flow.svg feat(router): load balance, retry and cool down across deployments of a model group (#46817) 2026-10-16 12:43:01 -07:00
shared_state-redis.svg feat(gateway): share router cooldowns and follow proxy key invalidations through Redis (#47017) 2026-10-17 16:34:03 -07:00
spend-writer.svg feat(gateway): write spend to the proxy's database from a native observer (#47041) 2026-10-19 09:58:43 -07:00
virtual_keys-auth-flow.svg feat(gateway): accept virtual keys from LiteLLM_VerificationToken (#46819) 2026-10-16 12:43:01 -07:00