18 views
-/https://github.com/berriai/litellm/issues/24677
GitHub · issue

#24677 [Bug]: Incorrect TPM limiting for virtual keys

  • State: open
  • Author: @yuri-alias
  • Labels: bug, proxy

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

This was initially reported on #18953 for v1.80.0. It was marked as solved, but we are still seeing this behaviour in v1.82.3

Actual rate limit enforcement is usually ~30% below the configured limit, and the cooldown period is longer than a minute. Usually 2, but can reach 5 minutes in some instances.

This is with the default rate limit type and configuration.

### Steps to Reproduce

1. Configure an API key with TPM limit (e.g. 500k) 2. Use the API key 3. Rate limit enforcement hits at approximately 300-350k.

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

Proxy

### What LiteLLM version are you on ?

v1.82.3

### Twitter / LinkedIn details

_No response_

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (1 events)
#0 of 0 · 31d17h44m3s ago — entered · #import:https:::github.com:berriai:litellm post #3239
Issue #24677 is harder because it involves diagnosing and correcting distributed quota accounting and timing behavior, with concurrency, token estimation, storage consistency, and regression risk across proxy deployments. Issue #31867 is comparatively localized to request transformation and metadata propagation, with focused compatibility tests.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search