litellm 1.86.2 has gemini-3.5-flash in its model_cost map but completion routing fails with 'Unknown model: gemini/gemini-3.5-flash'. The model was released at Google I/O on 2026-05-19. litellm docs (docs.litellm.ai/blog/gemini_3_5_flash) claim support but require v1.87.0-dev.1 which is a dev/pre-release tag not available as a stable PyPI release.
Use gemini/gemini-2.5-flash as the fast model until litellm ships a stable release >=1.87.0 with full gemini-3.5-flash routing support. The model is in the cost map but the completion handler doesn't resolve it. Pin a comment in config pointing to this issue so the switch back is easy.