fix: update gemini-live model to use realtime mode instead of chat#18009
fix: update gemini-live model to use realtime mode instead of chat#18009Chesars wants to merge 3 commits intoBerriAI:mainfrom
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
ishaan-jaff
left a comment
There was a problem hiding this comment.
Please leave it on the catalog, we support it through pass through live API requests
I suggest fixing the supported endpoints to not include /chat, /completions
The gemini-live-2.5-flash-preview-native-audio-09-2025 model only works with WebSocket (Live API), not REST endpoints. Changed supported_endpoints from /v1/chat/completions to /vertex_ai/live to reflect the actual passthrough endpoint available in LiteLLM proxy.
The gemini/ prefix indicates Google AI Studio, which uses /v1/realtime endpoint (OpenAI-compatible), not /vertex_ai/live.
56cb9c2 to
c8160fd
Compare
Thanks for the feedback! You're right - Updated the PR to fix supported_endpoints:
|
|
shouldn't you also fix the |
The mode field is used by health checks to determine the correct check method (WebSocket for realtime vs REST for chat).
Exactly, updated in 763b00a |
|
Closing as superseded by #22814. |
Title
fix: update gemini-live model to use realtime mode instead of chat
Relevant issues
N/A
Pre-Submission checklist
tests/litellm/directory, Adding at least 1 test is a hard requirement - N/A (JSON config only)make test-unitType
🐛 Bug Fix
Summary
The
gemini-live-2.5-flash-preview-native-audio-09-2025model was incorrectly configured withmode: "chat"and REST API endpoints, but this model only works with WebSockets (Realtime API).Changes
modefrom"chat"to"realtime"supported_endpointsfrom["/v1/chat/completions", "/v1/completions"]to the correct realtime endpoints:gemini/prefix:/v1/realtimevertex_ai/prefix:/vertex_ai/liveFiles changed:
model_prices_and_context_window.jsonlitellm/model_prices_and_context_window_backup.json