scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

gemini-3.1-flash-lite pricing (#27933)

Browse source 
* feat(model_prices): add gemini-3.1-flash-lite pricing with standard/batch/flex/priority tiers

* fix pricing

* add service tier

---------

Co-authored-by: shin-berri <shin-laptop@berri.ai>
This commit is contained in:
mubashir1osmani 2026-05-18 23:27:52 -04:00 • committed by Sameer Kankute
parent 1c80fa9c3b
commit b9b715157b
No known key found for this signature in database
1 changed files with 47 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

67
model_prices_and_context_window.json
View file

@ -15006,10 +15006,16 @@
"supports_service_tier": true
},
"gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 4.5e-08,
"cache_read_input_token_cost_per_audio_token": 9e-08,
"input_cost_per_audio_token": 9e-07,
"input_cost_per_token": 4.5e-07,
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
"cache_read_input_token_cost_per_audio_token": 5e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"input_cost_per_audio_token": 5e-07,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
@ -15021,9 +15027,12 @@
"max_video_length": 1,
"max_videos_per_prompt": 10,
"mode": "chat",
"output_cost_per_reasoning_token": 2.7e-06,
"output_cost_per_token": 2.7e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token_flex": 7.5e-07,
"output_cost_per_token_priority": 2.7e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -17128,10 +17137,16 @@
"supports_service_tier": true
},
"gemini/gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 4.5e-08,
"cache_read_input_token_cost_per_audio_token": 9e-08,
"input_cost_per_audio_token": 9e-07,
"input_cost_per_token": 4.5e-07,
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
"cache_read_input_token_cost_per_audio_token": 5e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"input_cost_per_audio_token": 5e-07,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "gemini",
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
@ -17143,10 +17158,13 @@
"max_video_length": 1,
"max_videos_per_prompt": 10,
"mode": "chat",
"output_cost_per_reasoning_token": 2.7e-06,
"output_cost_per_token": 2.7e-06,
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token_flex": 7.5e-07,
"output_cost_per_token_priority": 2.7e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -33932,10 +33950,16 @@
"web_search_billing_unit": "per_query"
},
"vertex_ai/gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 4.5e-08,
"cache_read_input_token_cost_per_audio_token": 9e-08,
"input_cost_per_audio_token": 9e-07,
"input_cost_per_token": 4.5e-07,
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
"cache_read_input_token_cost_per_audio_token": 5e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"input_cost_per_audio_token": 5e-07,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
@ -33947,8 +33971,11 @@
"max_video_length": 1,
"max_videos_per_prompt": 10,
"mode": "chat",
"output_cost_per_reasoning_token": 2.7e-06,
"output_cost_per_token": 2.7e-06,
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token_flex": 7.5e-07,
"output_cost_per_token_priority": 2.7e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"supported_endpoints": [
"/v1/chat/completions",