BerriAI/litellm v1.77.7.dev.3

on GitHub

What's Changed

• [Update] doc: perf update by @AlexsanderHamir in #15211
• Added prettier to autoformat frontend by @ARajan1084 in #15215
• feat(snowflake): add function calling support for Snowflake Cortex REST API by @jatorre in #15221
• [Fix] - Router: add model_name index for O(1) deployment lookups by @AlexsanderHamir in #15113
• Add Watson X foundation model definitions to model_prices_and_context… by @Gal-bloch in #15219
• (BUG) Fix passing headers for gemini by @Sameerlite in #15231
• [MCP Gateway] UI - Select allowed tools for Key, Teams by @ishaan-jaff in #15241
• [Refactor] Utils: extract inner function from client by @AlexsanderHamir in #15234
• [MCP Gateway] Backend - Allow storing allowed tools by team/key by @ishaan-jaff in #15243
• [MCP Gateway] Fine-grained Database Object Storage Control by @ishaan-jaff in #15255
• Add GPT-5 Pro model configuration and documentation by @TeddyAmkie in #15258
• Adds turbopack to the npm run dev command in UI to build faster during development by @ARajan1084 in #15250
• (perf) fix: Replaces bloated key list calls with lean key aliases endpoint by @ARajan1084 in #15252
• fix: Router settings do not update despite success message by @ARajan1084 in #15249
• Removed stop param from unsupported azure models by @Sameerlite in #15229
• feat: add stop parameter to non-supported params for GPT-5 by @TeddyAmkie in #15244
• [Feat]: Day 0 Support, Add gpt-image-1-mini by @ishaan-jaff in #15259
• fix(azure/responses): remove invalid status param from azure call + MCP - support setting CA_BUNDLE_PATH by @krrishdholakia in #15253
• Chore/vertex ai context caching by @otaviofbrito in #15226
• Azure - passthrough support with router models by @krrishdholakia in #15240
• feat: add Global Cross-Region Inference by @uc4w6c in #15210
• Added streaming support for response api streaming image generation by @Sameerlite in #15269
• feature: adds Infinity as a provider in the UI by @ARajan1084 in #15285

New Contributors

• @Gal-bloch made their first contribution in #15219

Full Changelog: v1.77.7-nightly...v1.77.7.dev.3

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.77.7.dev.3

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