What's Changed
- Add azure/gpt-4o-2024-08-06 pricing. by @Manouchehri in #5510
- [Fix] get_llm_provider, return provider as
cohere_chatfor cohere chat models by @ishaan-jaff in #5511 - fix proxy server - always read redis for rate limiting logic by @ishaan-jaff in #5484
- Helicone stream response logging by @maamalama in #5516
- security - Prevent sql injection in
/team/updatequery by @krrishdholakia in #5513 - [Fix-Refactor] support presidio on new guardrails config by @ishaan-jaff in #5514
- [Fix - Proxy] show error from /spend/tags and /spend/logs on client side by @ishaan-jaff in #5520
- [Feat] log request / response on pass through endpoints by @ishaan-jaff in #5518
- [Fix-Proxy] show more descriptive error messages on /health checks by @ishaan-jaff in #5521
Full Changelog: v1.44.16...v1.44.17
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.17
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 ✅ | 110.0 | 144.75345275454978 | 6.424739460241986 | 0.0 | 1923 | 0 | 86.76964199997883 | 3621.227346000012 |
| Aggregated | Passed ✅ | 110.0 | 144.75345275454978 | 6.424739460241986 | 0.0 | 1923 | 0 | 86.76964199997883 | 3621.227346000012 |