From 292a466253c9493ef3bb6623e933a3c525ca6ace Mon Sep 17 00:00:00 2001 From: F1bos Date: Sun, 8 Sep 2024 23:49:36 +0300 Subject: [PATCH 1/4] Fixed gemini-1.5-flash pricing --- ...odel_prices_and_context_window_backup.json | 20 +++++++++---------- model_prices_and_context_window.json | 20 +++++++++---------- 2 files changed, 20 insertions(+), 20 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 487e187a3c06..912c968311cc 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2512,16 +2512,16 @@ "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_pdf_size_mb": 30, - "input_cost_per_token": 0.00000035, - "input_cost_per_token_above_128k_tokens": 0.0000007, - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.0000021, + "input_cost_per_token": 0.000000075, + "input_cost_per_token_above_128k_tokens": 0.00000015, + "output_cost_per_token": 0.0000003, + "output_cost_per_token_above_128k_tokens": 0.0000006, "litellm_provider": "gemini", "mode": "chat", "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-latest": { "max_tokens": 8192, @@ -2533,16 +2533,16 @@ "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_pdf_size_mb": 30, - "input_cost_per_token": 0.00000035, - "input_cost_per_token_above_128k_tokens": 0.0000007, - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.0000021, + "input_cost_per_token": 0.000000075, + "input_cost_per_token_above_128k_tokens": 0.00000015, + "output_cost_per_token": 0.0000003, + "output_cost_per_token_above_128k_tokens": 0.0000006, "litellm_provider": "gemini", "mode": "chat", "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "source": "https://ai.google.dev/pricing" }, "gemini/gemini-pro": { "max_tokens": 8192, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 487e187a3c06..912c968311cc 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2512,16 +2512,16 @@ "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_pdf_size_mb": 30, - "input_cost_per_token": 0.00000035, - "input_cost_per_token_above_128k_tokens": 0.0000007, - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.0000021, + "input_cost_per_token": 0.000000075, + "input_cost_per_token_above_128k_tokens": 0.00000015, + "output_cost_per_token": 0.0000003, + "output_cost_per_token_above_128k_tokens": 0.0000006, "litellm_provider": "gemini", "mode": "chat", "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-latest": { "max_tokens": 8192, @@ -2533,16 +2533,16 @@ "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_pdf_size_mb": 30, - "input_cost_per_token": 0.00000035, - "input_cost_per_token_above_128k_tokens": 0.0000007, - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.0000021, + "input_cost_per_token": 0.000000075, + "input_cost_per_token_above_128k_tokens": 0.00000015, + "output_cost_per_token": 0.0000003, + "output_cost_per_token_above_128k_tokens": 0.0000006, "litellm_provider": "gemini", "mode": "chat", "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "source": "https://ai.google.dev/pricing" }, "gemini/gemini-pro": { "max_tokens": 8192, From 0f10ca0fae19417fdf9653d731f87bf256e17a66 Mon Sep 17 00:00:00 2001 From: F1bos Date: Sat, 14 Sep 2024 05:18:22 +0300 Subject: [PATCH 2/4] (models): Added missing gemini experimental models + fixed pricing for gemini-1.5-pro-exp-0827 --- ...odel_prices_and_context_window_backup.json | 50 +++++++++++++++++-- model_prices_and_context_window.json | 50 +++++++++++++++++-- 2 files changed, 92 insertions(+), 8 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 09d39fb43b29..1fb2997c0165 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2623,6 +2623,48 @@ "supports_vision": true, "source": "https://ai.google.dev/pricing" }, + "gemini/gemini-1.5-flash-exp-0827": { + "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_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://ai.google.dev/pricing" + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "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_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://ai.google.dev/pricing" + }, "gemini/gemini-pro": { "max_tokens": 8192, "max_input_tokens": 32760, @@ -2674,10 +2716,10 @@ "max_tokens": 8192, "max_input_tokens": 2097152, "max_output_tokens": 8192, - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "output_cost_per_token": 0.0000105, - "output_cost_per_token_above_128k_tokens": 0.000021, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", "mode": "chat", "supports_system_messages": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 09d39fb43b29..1fb2997c0165 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2623,6 +2623,48 @@ "supports_vision": true, "source": "https://ai.google.dev/pricing" }, + "gemini/gemini-1.5-flash-exp-0827": { + "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_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://ai.google.dev/pricing" + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "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_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://ai.google.dev/pricing" + }, "gemini/gemini-pro": { "max_tokens": 8192, "max_input_tokens": 32760, @@ -2674,10 +2716,10 @@ "max_tokens": 8192, "max_input_tokens": 2097152, "max_output_tokens": 8192, - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "output_cost_per_token": 0.0000105, - "output_cost_per_token_above_128k_tokens": 0.000021, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", "mode": "chat", "supports_system_messages": true, From 362b1b198c4e1744171e5c6e402cdefafd140308 Mon Sep 17 00:00:00 2001 From: F1bos Date: Sun, 15 Sep 2024 05:52:22 +0300 Subject: [PATCH 3/4] Added gemini/gemini-1.5-flash-001 model --- ...odel_prices_and_context_window_backup.json | 21 +++++++++++++++++++ model_prices_and_context_window.json | 21 +++++++++++++++++++ 2 files changed, 42 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d501d85726f7..687ab6f42fb9 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2581,6 +2581,27 @@ "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, + "gemini/gemini-1.5-flash-001": { + "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_token": 0.000000075, + "input_cost_per_token_above_128k_tokens": 0.00000015, + "output_cost_per_token": 0.0000003, + "output_cost_per_token_above_128k_tokens": 0.0000006, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://ai.google.dev/pricing" + }, "gemini/gemini-1.5-flash": { "max_tokens": 8192, "max_input_tokens": 1000000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d501d85726f7..687ab6f42fb9 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2581,6 +2581,27 @@ "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, + "gemini/gemini-1.5-flash-001": { + "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_token": 0.000000075, + "input_cost_per_token_above_128k_tokens": 0.00000015, + "output_cost_per_token": 0.0000003, + "output_cost_per_token_above_128k_tokens": 0.0000006, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://ai.google.dev/pricing" + }, "gemini/gemini-1.5-flash": { "max_tokens": 8192, "max_input_tokens": 1000000, From c57bcf8373cada99e959e33cb99f25e17ba38a0c Mon Sep 17 00:00:00 2001 From: F1bos Date: Sun, 15 Sep 2024 06:06:37 +0300 Subject: [PATCH 4/4] Updated supports_response_schema to true for gemini flash 1.5 models --- litellm/model_prices_and_context_window_backup.json | 7 +++++++ model_prices_and_context_window.json | 7 +++++++ 2 files changed, 14 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 687ab6f42fb9..d597b8bd0ee3 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2061,6 +2061,7 @@ "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-exp-0827": { @@ -2092,6 +2093,7 @@ "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": { @@ -2123,6 +2125,7 @@ "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-preview-0514": { @@ -2600,6 +2603,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash": { @@ -2621,6 +2625,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-latest": { @@ -2642,6 +2647,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-exp-0827": { @@ -2663,6 +2669,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-8b-exp-0827": { diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 687ab6f42fb9..d597b8bd0ee3 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2061,6 +2061,7 @@ "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-exp-0827": { @@ -2092,6 +2093,7 @@ "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": { @@ -2123,6 +2125,7 @@ "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-preview-0514": { @@ -2600,6 +2603,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash": { @@ -2621,6 +2625,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-latest": { @@ -2642,6 +2647,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-exp-0827": { @@ -2663,6 +2669,7 @@ "supports_system_messages": true, "supports_function_calling": true, "supports_vision": true, + "supports_response_schema": true, "source": "https://ai.google.dev/pricing" }, "gemini/gemini-1.5-flash-8b-exp-0827": {