scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-15 09:12:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 311

fix(vertex-ai): add gemini-omni-flash-preview deprecation date and correct omni flash token limits

Browse source
This commit is contained in:
devin-ai-integration[bot] 2026-11-03 10:13:12 +00:00
parent 35379b1e7c
commit 812a89da71
2 changed files with 12 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
litellm/model_prices_and_context_window_backup.json
View file

@ -32513,16 +32513,17 @@
"web_search_billing_unit": "per_query"
},
"gemini-omni-flash-preview": {
"deprecation_date": "2026-11-06",
"input_cost_per_audio_token": 1.5e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_input_tokens": 131072,
"max_output_tokens": 57920,
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"output_cost_per_video_token": 1.75e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview",
"supported_endpoints": [
"/v1/chat/completions"
],
@ -69882,12 +69883,12 @@
"input_cost_per_token": 1.5e-06,
"litellm_provider": "vertex_ai",
"max_output_tokens": 57920,
"max_input_tokens": 57920,
"max_input_tokens": 131072,
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"output_cost_per_video_token": 1.75e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-1-1-flash",
"supported_endpoints": [
"/v1beta/interactions"
],

11
model_prices_and_context_window.json
View file

@ -32513,16 +32513,17 @@
"web_search_billing_unit": "per_query"
},
"gemini-omni-flash-preview": {
"deprecation_date": "2026-11-06",
"input_cost_per_audio_token": 1.5e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_input_tokens": 131072,
"max_output_tokens": 57920,
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"output_cost_per_video_token": 1.75e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview",
"supported_endpoints": [
"/v1/chat/completions"
],
@ -69882,12 +69883,12 @@
"input_cost_per_token": 1.5e-06,
"litellm_provider": "vertex_ai",
"max_output_tokens": 57920,
"max_input_tokens": 57920,
"max_input_tokens": 131072,
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
"output_cost_per_video_token": 1.75e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-1-1-flash",
"supported_endpoints": [
"/v1beta/interactions"
],