v1.70.2.dev5

What's Changed

• [Feature] Add supports_computer_use to the model list by @slytechnical in #10881
• [Feat] - Add Support for Showing Passthrough endpoint Error Logs on LiteLLM UI by @ishaan-jaff in #10990
• added support to credential delete to support slashes in the curl by @jugaldb in #10987
• Add new gemini preview models + Fix cohere v2 embedding 'embedding_types' param mapping by @krrishdholakia in #10991
• Litellm add new gemini models by @krrishdholakia in #10998
• [Feat] Prometheus - Track route on proxy_* metrics by @ishaan-jaff in #10992
• fix: default role for JWT authentication by @ishaan-jaff in #10995
• fix(internal_user_endpoints.py): allow resetting spend/max budget on /user/update + Fix updating user budget across multiple instances by @krrishdholakia in #10993
• Improve response_id propagation logic and add tests for valid/empty I… by @daarko10 in #11006
• Support vertex_ai global endpoints for chat by @sorenmat in #10658
• Ollama wildcard support by @matthid in #10982
• Spend rounded to 4 decimal points on Teams page by @NANDINI-star in #11013
• Place organization and team create buttons at the top by @NANDINI-star in #10948
• Feat: add xai/grok-3 pricing by @ishaan-jaff in #11028
• [Feat] Add Image Edits Support to LiteLLM by @ishaan-jaff in #11020
• Updating the available VoyageAI models in the docs by @fzowl in #11003
• Fix UI - Call tool renders correctly when no arguments required by @wagnerjt in #11012
• Verbose error on admin add by @jugaldb in #10978
• Spend rounded to 4 for Organizations and Users page by @NANDINI-star in #11023
• Fix: Handle dict objects in Anthropic streaming response by @jgowdy-godaddy in #11032
• feat: add Databricks Llama 4 Maverick model cost by @bepotp in #11008
• Add LiteLLM Managed Files support for finetuning api create endpoint by @krrishdholakia in #11039
• Fixes the InvitationLink Prisma find_many query by @jmorenoc-o in #11031
• Support passing prompt_label to langfuse + Log consistent modelParams to langfuse by @krrishdholakia in #11018
• Fix CI | Added closing tags for + indentation changes by @NANDINI-star in #11046
• Feat: add MCP to Responses API and bump openai python sdk by @ishaan-jaff in #11029
• Model filter on logs by @NANDINI-star in #11048
• [Feat] Add claude-4 model family by @ishaan-jaff in #11060

New Contributors

• @slytechnical made their first contribution in #10881
• @daarko10 made their first contribution in #11006
• @sorenmat made their first contribution in #10658
• @matthid made their first contribution in #10982
• @jgowdy-godaddy made their first contribution in #11032
• @bepotp made their first contribution in #11008
• @jmorenoc-o made their first contribution in #11031

Full Changelog: v1.70.2-nightly...v1.70.2.dev5

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.70.2.dev5

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	Failed ❌	490.0	556.7359308349169	5.626256137716844	0.0	1684	0	437.79858300001706	2137.070654000013
Aggregated	Failed ❌	490.0	556.7359308349169	5.626256137716844	0.0	1684	0	437.79858300001706	2137.070654000013