From a74e269f7d180b9c31185ed83894ef4840249ba3 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Thu, 14 May 2026 00:35:53 +0530 Subject: [PATCH] fix(cost): align vertex_ai/gemini-embedding-2-preview with Vertex multimodal pricing (#27848) * fix(cost): align vertex_ai/gemini-embedding-2-preview with Vertex multimodal pricing Co-authored-by: Cursor * fix(cost): align vertex_ai/gemini-embedding-2 GA source URL with preview Per Greptile review on #27848: GA entry referenced ai.google.dev while the preview entry was updated to the canonical Vertex AI pricing page. Both share identical pricing values; sync the source URL for consistency. https://claude.ai/code/session_01W8jRwstnmduadGw8Z8egxe --------- Co-authored-by: Cursor Co-authored-by: Claude --- litellm/model_prices_and_context_window_backup.json | 9 ++++++--- model_prices_and_context_window.json | 9 ++++++--- tests/test_litellm/test_utils.py | 3 ++- 3 files changed, 14 insertions(+), 7 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 8df25d2c9b5..61e0dd07968 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -15551,14 +15551,17 @@ "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 }, @@ -15573,7 +15576,7 @@ "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 70b065aa918..e62f8686e9d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -15556,14 +15556,17 @@ "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 }, @@ -15578,7 +15581,7 @@ "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/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index d07af922ea6..bc60375f906 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -3002,7 +3002,7 @@ def test_model_info_for_openrouter_kimi_k2_5(): def test_gemini_embedding_2_ga_in_cost_map(): - """GA gemini-embedding-2 entries align with preview multimodal unit pricing.""" + """GA and Vertex preview gemini-embedding-2 entries align with multimodal unit pricing.""" import json from pathlib import Path @@ -3013,6 +3013,7 @@ def test_gemini_embedding_2_ga_in_cost_map(): for key, provider in ( ("gemini/gemini-embedding-2", "gemini"), ("vertex_ai/gemini-embedding-2", "vertex_ai"), + ("vertex_ai/gemini-embedding-2-preview", "vertex_ai"), ("gemini-embedding-2", "vertex_ai-embedding-models"), ): info = model_cost.get(key)