BerriAI/litellm v1.78.2-nightly

on GitHub

What's Changed

• [Docs] v1.78.0-stable by @ishaan-jaff in #15452
• docs: cleanup docs + build ui by @krrishdholakia in #15454
• GPT-5 return reasoning content via /chat/completions + GPT-5-Codex working on Claude Code by @krrishdholakia in #15441
• [Docs] Key Rotations by @ishaan-jaff in #15455
• feat(scim_v2.py): if group.id doesn't exist, use external id + Passthrough - ensure updates and deletions persist across instances by @krrishdholakia in #15276
• Responses API - enable calling anthropic/gemini models in Responses API streaming in openai ruby sdk + DB - sanity check pending migrations before startup by @krrishdholakia in #15432
• (feat) Passthrough - allow admin to give access to specific passthrough endpoints by @krrishdholakia in #15401
• Litellm docs 10 11 2025 by @krrishdholakia in #15457
• Fix: Pricing for Claude Sonnet 4.5 in US regions is 10x too high by @jlan-nl in #15374
• [Add]: perf summary by @AlexsanderHamir in #15458
• Fix apply_guardrail endpoint returning raw string instead of ApplyGuardrailResponse by @Copilot in #15436
• Reduce claude-4-sonnet max_output_tokens to 64k by @hampusnasstrom in #15409
• Fixed a few typos by @ImadSaddik in #15267
• Litellm staging branch 10 11 2025 p1 by @krrishdholakia in #15456
• Add anthropic/claude-sonnet-4.5 to OpenRouter cost map by @huangyafei in #15472
• docs: add ecs deployment guide by @mubashir1osmani in #15468
• fix(ollama/chat): correctly map reasoning_effort to think in requests by @kowyo in #15465
• [Docs] - Update benchmark results by @AlexsanderHamir in #15461
• Get completion cost directly from OpenRouter by @dhruvyad in #15448
• [Fix] GEMINI - CLI - add google_routes to llm_api_routes by @ishaan-jaff in #15500
• [Feat] Allow Team Admins to export a report of the team spending by @ishaan-jaff in #15542
• small fix code snippet custom_prompt_management.md by @davizucon in #15544
• change gpt-5-codex support in model_price json by @FelipeRodriguesGare in #15540
• [Feat] Native /ocr endpoint support by @ishaan-jaff in #15573
• added claude-haiku-4.5 by @mubashir1osmani in #15579
• [Feat] Add anthropic.claude-haiku-4-5-20251001-v1:0 on Bedrock, VertexAI by @ishaan-jaff in #15581

New Contributors

• @hampusnasstrom made their first contribution in #15409
• @ImadSaddik made their first contribution in #15267
• @dhruvyad made their first contribution in #15448
• @davizucon made their first contribution in #15544

Full Changelog: v1.78.0-nightly...v1.78.2-nightly

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.78.2-nightly

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