From c3b202ba0bc9536a057cb4aca380961b55744cc6 Mon Sep 17 00:00:00 2001 From: anzzyspeaksgit Date: Sun, 15 Mar 2026 12:03:46 +0000 Subject: [PATCH] fix(pricing): correct inverted preview cache pricing multipliers per reviewer feedback --- model_prices_and_context_window.json | 81 ++++++++++++++-------------- 1 file changed, 42 insertions(+), 39 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d28a53d1abb..22a70583900 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -13771,7 +13771,7 @@ "input_cost_per_token_priority": 1.8e-07, "input_cost_per_audio_token_priority": 5.4e-07, "output_cost_per_token_priority": 7.2e-07, - "cache_read_input_token_cost_priority": 2e-08, + "cache_read_input_token_cost_priority": 1.8000000000000002e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_audio_token_flex": 1.5e-07, "output_cost_per_token_flex": 2e-07, @@ -13824,11 +13824,11 @@ "input_cost_per_token_priority": 5.4e-07, "input_cost_per_audio_token_priority": 1.8e-06, "output_cost_per_token_priority": 4.5e-06, - "cache_read_input_token_cost_priority": 5e-08, + "cache_read_input_token_cost_priority": 1.35e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_audio_token_flex": 5e-07, "output_cost_per_token_flex": 1.25e-06, - "cache_read_input_token_cost_flex": 1.5e-08 + "cache_read_input_token_cost_flex": 3.75e-08 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "cache_read_input_token_cost": 7.5e-08, @@ -13966,13 +13966,13 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_priority": 1.8e-07, - "input_cost_per_audio_token_priority": 5.4e-07, + "input_cost_per_audio_token_priority": 9e-07, "output_cost_per_token_priority": 7.2e-07, - "cache_read_input_token_cost_priority": 2e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token_flex": 5e-08, - "input_cost_per_audio_token_flex": 1.5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, "output_cost_per_token_flex": 2e-07, - "cache_read_input_token_cost_flex": 5e-09 + "cache_read_input_token_cost_flex": 1.25e-08 }, "gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, @@ -14440,7 +14440,11 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "cache_read_input_token_cost_priority": 2.25e-07, + "cache_read_input_token_cost_flex": 6.25e-08, + "input_cost_per_audio_token_priority": 1.26e-06, + "input_cost_per_audio_token_flex": 3.5e-07 }, "gemini-robotics-er-1.5-preview": { "cache_read_input_token_cost": 0, @@ -14567,17 +14571,14 @@ "uses_embed_content": true }, "vertex_ai/gemini-embedding-2-preview": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, - "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, + "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", "supports_multimodal": true, "uses_embed_content": true }, @@ -14594,18 +14595,6 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "uses_embed_content": true }, - "vertex_ai/gemini-embedding-2-preview": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", - "supports_multimodal": true, - "uses_embed_content": true - }, "gemini/gemini-embedding-001": { "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", @@ -15083,7 +15072,7 @@ "input_cost_per_token_priority": 1.8e-07, "input_cost_per_audio_token_priority": 5.4e-07, "output_cost_per_token_priority": 7.2e-07, - "cache_read_input_token_cost_priority": 2e-08, + "cache_read_input_token_cost_priority": 1.8000000000000002e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_audio_token_flex": 1.5e-07, "output_cost_per_token_flex": 2e-07, @@ -15138,11 +15127,11 @@ "input_cost_per_token_priority": 5.4e-07, "input_cost_per_audio_token_priority": 1.8e-06, "output_cost_per_token_priority": 4.5e-06, - "cache_read_input_token_cost_priority": 5e-08, + "cache_read_input_token_cost_priority": 1.35e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_audio_token_flex": 5e-07, "output_cost_per_token_flex": 1.25e-06, - "cache_read_input_token_cost_flex": 1.5e-08 + "cache_read_input_token_cost_flex": 3.75e-08 }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, @@ -15286,13 +15275,13 @@ "supports_web_search": true, "tpm": 250000, "input_cost_per_token_priority": 1.8e-07, - "input_cost_per_audio_token_priority": 5.4e-07, + "input_cost_per_audio_token_priority": 9e-07, "output_cost_per_token_priority": 7.2e-07, - "cache_read_input_token_cost_priority": 2e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token_flex": 5e-08, - "input_cost_per_audio_token_flex": 1.5e-07, + "input_cost_per_audio_token_flex": 2.5e-07, "output_cost_per_token_flex": 2e-07, - "cache_read_input_token_cost_flex": 5e-09 + "cache_read_input_token_cost_flex": 1.25e-08 }, "gemini/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 3e-07, @@ -15753,7 +15742,11 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "tpm": 10000000 + "tpm": 10000000, + "cache_read_input_token_cost_priority": 2.25e-07, + "cache_read_input_token_cost_flex": 6.25e-08, + "input_cost_per_audio_token_priority": 1.26e-06, + "input_cost_per_audio_token_flex": 3.5e-07 }, "gemini/gemini-exp-1114": { "input_cost_per_token": 0, @@ -31018,7 +31011,9 @@ "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", - "supported_regions": ["global"], + "supported_regions": [ + "global" + ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -36624,7 +36619,9 @@ "audio" ], "supports_audio_input": true, - "supports_audio_output": true + "supports_audio_output": true, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_flex": 5e-07 }, "gemini-2.5-flash-native-audio-preview-12-2025": { "input_cost_per_audio_token": 1e-06, @@ -36648,7 +36645,9 @@ "audio" ], "supports_audio_input": true, - "supports_audio_output": true + "supports_audio_output": true, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_flex": 5e-07 }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 1e-06, @@ -36700,7 +36699,9 @@ "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, - "rpm": 10 + "rpm": 10, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_flex": 5e-07 }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { "input_cost_per_audio_token": 1e-06, @@ -36726,7 +36727,9 @@ "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, - "rpm": 10 + "rpm": 10, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_flex": 5e-07 }, "gemini-2.5-flash-preview-tts": { "input_cost_per_token": 3e-07, @@ -37063,4 +37066,4 @@ "supports_response_schema": true, "supports_tool_choice": true } -} +} \ No newline at end of file