From cab057da4ade0c6cfce265bd0d29b3f7fa961329 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Wed, 19 Jun 2024 14:14:44 -0700 Subject: [PATCH] build(model_prices_and_context_window.json): fix gemini pricing Resolves https://github.com/BerriAI/litellm/issues/4165#issuecomment-2179310636 --- ...odel_prices_and_context_window_backup.json | 265 +++++++++++------- model_prices_and_context_window.json | 265 +++++++++++------- 2 files changed, 314 insertions(+), 216 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 473f3d3fe..2f91cede8 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1125,19 +1125,27 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "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": { "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "supports_function_calling": true, @@ -1147,8 +1155,12 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "supports_function_calling": true, @@ -1158,8 +1170,12 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "supports_function_calling": true, @@ -1172,10 +1188,114 @@ "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, + "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-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_video_per_second": 0.00263, "output_cost_per_audio_per_second": 0.00025, @@ -1198,10 +1318,14 @@ "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": 0.00000003125, - "input_cost_per_token_above_128k_tokens": 0.0000000625, - "output_cost_per_token": 0.00000009375, - "output_cost_per_token_above_128k_tokens": 0.0000001875, + "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, @@ -1225,10 +1349,14 @@ "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": 0.00000003125, - "input_cost_per_token_above_128k_tokens": 0.0000000625, - "output_cost_per_token": 0.00000009375, - "output_cost_per_token_above_128k_tokens": 0.0000001875, + "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, @@ -1252,10 +1380,14 @@ "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": 0.00000003125, - "input_cost_per_token_above_128k_tokens": 0.0000000625, - "output_cost_per_token": 0.00000009375, - "output_cost_per_token_above_128k_tokens": 0.0000001875, + "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, @@ -1266,89 +1398,6 @@ "supports_vision": 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": 0.0000003125, - "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": { "max_tokens": 8192, "max_input_tokens": 1000000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 473f3d3fe..2f91cede8 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1125,19 +1125,27 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "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": { "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "supports_function_calling": true, @@ -1147,8 +1155,12 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "supports_function_calling": true, @@ -1158,8 +1170,12 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000003125, - "output_cost_per_token": 0.00000009375, + "input_cost_per_image": 0.0025, + "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", "mode": "chat", "supports_function_calling": true, @@ -1172,10 +1188,114 @@ "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, + "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-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_video_per_second": 0.00263, "output_cost_per_audio_per_second": 0.00025, @@ -1198,10 +1318,14 @@ "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": 0.00000003125, - "input_cost_per_token_above_128k_tokens": 0.0000000625, - "output_cost_per_token": 0.00000009375, - "output_cost_per_token_above_128k_tokens": 0.0000001875, + "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, @@ -1225,10 +1349,14 @@ "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": 0.00000003125, - "input_cost_per_token_above_128k_tokens": 0.0000000625, - "output_cost_per_token": 0.00000009375, - "output_cost_per_token_above_128k_tokens": 0.0000001875, + "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, @@ -1252,10 +1380,14 @@ "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": 0.00000003125, - "input_cost_per_token_above_128k_tokens": 0.0000000625, - "output_cost_per_token": 0.00000009375, - "output_cost_per_token_above_128k_tokens": 0.0000001875, + "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, @@ -1266,89 +1398,6 @@ "supports_vision": 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": 0.0000003125, - "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": { "max_tokens": 8192, "max_input_tokens": 1000000,