From b45ef7f6b9848f669c8bd177b8c047f1b67a9d8a Mon Sep 17 00:00:00 2001 From: Nicholas Gigliotti Date: Mon, 16 Mar 2026 21:03:08 -0400 Subject: [PATCH] Keep multimodal gemini-embedding-2-preview entry to align with #23599 Main has two duplicate keys for vertex_ai/gemini-embedding-2-preview. Our JSON round-trip collapsed them to the second (text-only) entry, but PR #23599 intentionally keeps the first (multimodal pricing) entry. Restore the multimodal entry to avoid conflicts. --- litellm/model_prices_and_context_window_backup.json | 7 +++++-- model_prices_and_context_window.json | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e18f00508c..f55b66cc7d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -14623,14 +14623,17 @@ "uses_embed_content": true }, "vertex_ai/gemini-embedding-2-preview": { - "input_cost_per_token": 1.5e-07, + "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, "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", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true }, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e18f00508c..f55b66cc7d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14623,14 +14623,17 @@ "uses_embed_content": true }, "vertex_ai/gemini-embedding-2-preview": { - "input_cost_per_token": 1.5e-07, + "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, "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", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true },