phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

Add gemini-1.5-pro-002 and gemini-1.5-flash-002 (#5879)

Browse source
This commit is contained in:
John HU 2024-09-25 19:31:37 -07:00 • committed by GitHub
parent a8dd495eae
commit 8c7e357a23
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 58 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

58
model_prices_and_context_window.json
View file

@ -1975,6 +1975,32 @@
"supports_response_schema": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-002": {
"max_tokens": 8192,
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
"input_cost_per_image": 0.001315,
"input_cost_per_audio_per_second": 0.000125,
"input_cost_per_video_per_second": 0.001315,
"input_cost_per_token": 0.000005,
"input_cost_per_character": 0.00000125,
"input_cost_per_token_above_128k_tokens": 0.00001,
"input_cost_per_character_above_128k_tokens": 0.0000025,
"output_cost_per_token": 0.000015,
"output_cost_per_character": 0.00000375,
"output_cost_per_token_above_128k_tokens": 0.00003,
"output_cost_per_character_above_128k_tokens": 0.0000075,
"output_cost_per_image": 0.00263,
"output_cost_per_video_per_second": 0.00263,
"output_cost_per_audio_per_second": 0.00025,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_system_messages": true,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_response_schema": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-001": {
"max_tokens": 8192,
"max_input_tokens": 1000000,
@ -2142,6 +2168,38 @@
"supports_response_schema": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-flash-002": {
"max_tokens": 8192,
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
"max_images_per_prompt": 3000,
"max_videos_per_prompt": 10,
"max_video_length": 1,
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
"max_pdf_size_mb": 30,
"input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"input_cost_per_token_above_128k_tokens": 0.000001,
"input_cost_per_character_above_128k_tokens": 0.00000025,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"output_cost_per_token_above_128k_tokens": 0.000003,
"output_cost_per_character_above_128k_tokens": 0.00000075,
"output_cost_per_image": 0.000263,
"output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_system_messages": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_response_schema": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-flash-001": {
"max_tokens": 8192,
"max_input_tokens": 1000000,