What's Changed
- fix(utils.py): support dynamic params for openai-compatible providers by @krrishdholakia in #4801
- fix(factory.py): refactor factory to use httpx client by @krrishdholakia in #4796
- docs - show to do spend tracking with OpenAI Js + Proxy by @ishaan-jaff in #4805
- fix(user_api_key_auth.py): update valid token cache with updated team object cache by @krrishdholakia in #4799
- feat - add mistral
open-codestral-mamba
open-mistral-nemo
by @ishaan-jaff in #4808 - fix(openai.py): drop invalid params if
drop_params: true
for azure ai by @krrishdholakia in #4806 - [Ui] add together AI, Mistral, PerplexityAI, OpenRouter models on Admin UI by @ishaan-jaff in #4802
- router - use verbose logger when using litellm.Router by @ishaan-jaff in #4809
- Revert "[Ui] add together AI, Mistral, PerplexityAI, OpenRouter models on Admin UI " by @ishaan-jaff in #4811
- [Feat] Return response headers on
litellm.completion
,litellm.embedding
by @ishaan-jaff in #4807 - Fix: use Bedrock region from environment variables before other region definitions by @petermuller in #4613
- Revert "Fix: use Bedrock region from environment variables before other region definitions" by @krrishdholakia in #4819
Full Changelog: v1.41.25...v1.41.26
Docker Run LiteLLM Proxy
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.41.26
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 ✅ | 100.0 | 122.89826346409966 | 6.42178976324838 | 0.0 | 1922 | 0 | 84.74049599999489 | 2107.5484990000177 |
Aggregated | Passed ✅ | 100.0 | 122.89826346409966 | 6.42178976324838 | 0.0 | 1922 | 0 | 84.74049599999489 | 2107.5484990000177 |