What's Changed
- [Feat-Proxy] allow turning off message logging for OTEL (callback specific) by @ishaan-jaff in #5603
- fix #5614: Fixed the template error null pointer evaluation by @Pit-Storm in #5615
- [Fix-Proxy] Regenerate keys when no duration is passed by @ishaan-jaff in #5616
- [Fix-Perf] Vertex AI cache httpx clients by @ishaan-jaff in #5619
- [Feat-Perf] Use common helper to get async httpx clients for all providers by @ishaan-jaff in #5620
- [Feat-Perf Improvement Vertex] Only Refresh credentials when token is expired by @ishaan-jaff in #5622
- Add Cohere refresh models and update pricing by @jalammar in #5571
- [Feat-Vertex Perf] Use async func to get auth credentials by @ishaan-jaff in #5623
New Contributors
Full Changelog: v1.44.23...v1.44.24
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.24
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 ✅ | 120.0 | 144.67113647299365 | 6.373192750121196 | 0.0 | 1907 | 0 | 99.51562199995578 | 2800.6129780000037 |
| Aggregated | Passed ✅ | 120.0 | 144.67113647299365 | 6.373192750121196 | 0.0 | 1907 | 0 | 99.51562199995578 | 2800.6129780000037 |