What's Changed
- Add key & team level budget metric for prometheus by @yujonglee in #7831
- fix(key_management_endpoints.py): fix default allowed team member roles by @krrishdholakia in #7843
- (UI - View SpendLogs Table) by @ishaan-jaff in #7842
- [fix dd llm obs] - use env vars for setting dd tags, service name by @ishaan-jaff in #7835
- [Hashicorp - secret manager] - use vault namespace for tls auth by @ishaan-jaff in #7834
- QA: ensure all bedrock regional models have same
supported_as base + Anthropic nested pydantic object support by @krrishdholakia in #7844 - 10x Bedrock perf improvement - refactor: make bedrock image transformation requests async by @krrishdholakia in #7840
/key/delete- allow team admin to delete team keys by @krrishdholakia in #7846- Improve Proxy Resiliency: Cooldown single-deployment model groups if 100% calls failed in high traffic by @krrishdholakia in #7823
- LiteLLM Minor Fixes & Improvements (2024/16/01) by @krrishdholakia in #7826
- Remove UI build output by @yujonglee in #7849
- Fix invalid base URL error by @yujonglee in #7852
- Refactor logs UI by @yujonglee in #7851
Full Changelog: v1.58.4...v1.59.0
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.59.0
Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat
Load Test LiteLLM Proxy Results
| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
|---|---|---|---|---|---|---|---|---|---|
| /chat/completions | Passed ✅ | 250.0 | 285.129348931583 | 6.106818187164813 | 0.0 | 1827 | 0 | 224.69302100000732 | 2869.612018000055 |
| Aggregated | Passed ✅ | 250.0 | 285.129348931583 | 6.106818187164813 | 0.0 | 1827 | 0 | 224.69302100000732 | 2869.612018000055 |