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

Merge pull request #4291 from BerriAI/litellm_gemini_pricing_2

Browse source 
build(model_prices_and_context_window.json): fix gemini pricing
This commit is contained in:
Krish Dholakia 2024-06-19 17:15:02 -07:00 • committed by GitHub
commit d1f8af9e44
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 314 additions and 216 deletions
Download patch file Download diff file Expand all files Collapse all files

265
litellm/model_prices_and_context_window_backup.json
View file

@ -1149,19 +1149,27 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models" "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
}, },
"gemini-1.0-pro": { "gemini-1.0-pro": {
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
@ -1171,8 +1179,12 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
@ -1182,8 +1194,12 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
@ -1196,10 +1212,114 @@
"input_cost_per_image": 0.001315, "input_cost_per_image": 0.001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_video_per_second": 0.001315, "input_cost_per_video_per_second": 0.001315,
"input_cost_per_token": 0.0000003125, "input_cost_per_token": 0.000005,
"input_cost_per_token_above_128k_tokens": 0.000000625, "input_cost_per_character": 0.00000125,
"output_cost_per_token": 0.0000009375, "input_cost_per_token_above_128k_tokens": 0.00001,
"output_cost_per_token_above_128k_tokens": 0.000001875, "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,
"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,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0514": {
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0215": {
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0409": {
"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_image": 0.00263,
"output_cost_per_video_per_second": 0.00263, "output_cost_per_video_per_second": 0.00263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1222,10 +1342,14 @@
"input_cost_per_image": 0.0001315, "input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315, "input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.00000003125, "input_cost_per_token": 0.0000005,
"input_cost_per_token_above_128k_tokens": 0.0000000625, "input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.00000009375, "input_cost_per_token_above_128k_tokens": 0.000001,
"output_cost_per_token_above_128k_tokens": 0.0000001875, "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_image": 0.000263,
"output_cost_per_video_per_second": 0.000263, "output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1249,10 +1373,14 @@
"input_cost_per_image": 0.0001315, "input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315, "input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.00000003125, "input_cost_per_token": 0.0000005,
"input_cost_per_token_above_128k_tokens": 0.0000000625, "input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.00000009375, "input_cost_per_token_above_128k_tokens": 0.000001,
"output_cost_per_token_above_128k_tokens": 0.0000001875, "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_image": 0.000263,
"output_cost_per_video_per_second": 0.000263, "output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1276,10 +1404,14 @@
"input_cost_per_image": 0.0001315, "input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315, "input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.00000003125, "input_cost_per_token": 0.0000005,
"input_cost_per_token_above_128k_tokens": 0.0000000625, "input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.00000009375, "input_cost_per_token_above_128k_tokens": 0.000001,
"output_cost_per_token_above_128k_tokens": 0.0000001875, "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_image": 0.000263,
"output_cost_per_video_per_second": 0.000263, "output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1290,89 +1422,6 @@
"supports_vision": true, "supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" "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,
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0514": {
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0215": {
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0409": {
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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_function_calling": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-experimental": { "gemini-experimental": {
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 1000000, "max_input_tokens": 1000000,

265
model_prices_and_context_window.json
View file

@ -1149,19 +1149,27 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models" "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
}, },
"gemini-1.0-pro": { "gemini-1.0-pro": {
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
@ -1171,8 +1179,12 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
@ -1182,8 +1194,12 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 32760, "max_input_tokens": 32760,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000003125, "input_cost_per_image": 0.0025,
"output_cost_per_token": 0.00000009375, "input_cost_per_video_per_second": 0.002,
"input_cost_per_token": 0.0000005,
"input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.0000015,
"output_cost_per_character": 0.000000375,
"litellm_provider": "vertex_ai-language-models", "litellm_provider": "vertex_ai-language-models",
"mode": "chat", "mode": "chat",
"supports_function_calling": true, "supports_function_calling": true,
@ -1196,10 +1212,114 @@
"input_cost_per_image": 0.001315, "input_cost_per_image": 0.001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_video_per_second": 0.001315, "input_cost_per_video_per_second": 0.001315,
"input_cost_per_token": 0.0000003125, "input_cost_per_token": 0.000005,
"input_cost_per_token_above_128k_tokens": 0.000000625, "input_cost_per_character": 0.00000125,
"output_cost_per_token": 0.0000009375, "input_cost_per_token_above_128k_tokens": 0.00001,
"output_cost_per_token_above_128k_tokens": 0.000001875, "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,
"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,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0514": {
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0215": {
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0409": {
"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_image": 0.00263,
"output_cost_per_video_per_second": 0.00263, "output_cost_per_video_per_second": 0.00263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1222,10 +1342,14 @@
"input_cost_per_image": 0.0001315, "input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315, "input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.00000003125, "input_cost_per_token": 0.0000005,
"input_cost_per_token_above_128k_tokens": 0.0000000625, "input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.00000009375, "input_cost_per_token_above_128k_tokens": 0.000001,
"output_cost_per_token_above_128k_tokens": 0.0000001875, "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_image": 0.000263,
"output_cost_per_video_per_second": 0.000263, "output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1249,10 +1373,14 @@
"input_cost_per_image": 0.0001315, "input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315, "input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.00000003125, "input_cost_per_token": 0.0000005,
"input_cost_per_token_above_128k_tokens": 0.0000000625, "input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.00000009375, "input_cost_per_token_above_128k_tokens": 0.000001,
"output_cost_per_token_above_128k_tokens": 0.0000001875, "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_image": 0.000263,
"output_cost_per_video_per_second": 0.000263, "output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1276,10 +1404,14 @@
"input_cost_per_image": 0.0001315, "input_cost_per_image": 0.0001315,
"input_cost_per_video_per_second": 0.0001315, "input_cost_per_video_per_second": 0.0001315,
"input_cost_per_audio_per_second": 0.000125, "input_cost_per_audio_per_second": 0.000125,
"input_cost_per_token": 0.00000003125, "input_cost_per_token": 0.0000005,
"input_cost_per_token_above_128k_tokens": 0.0000000625, "input_cost_per_character": 0.000000125,
"output_cost_per_token": 0.00000009375, "input_cost_per_token_above_128k_tokens": 0.000001,
"output_cost_per_token_above_128k_tokens": 0.0000001875, "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_image": 0.000263,
"output_cost_per_video_per_second": 0.000263, "output_cost_per_video_per_second": 0.000263,
"output_cost_per_audio_per_second": 0.00025, "output_cost_per_audio_per_second": 0.00025,
@ -1290,89 +1422,6 @@
"supports_vision": true, "supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" "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,
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0514": {
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0215": {
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0409": {
"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": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000009375,
"output_cost_per_token_above_128k_tokens": 0.000001875,
"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_function_calling": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-experimental": { "gemini-experimental": {
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 1000000, "max_input_tokens": 1000000,