ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(cost): align vertex_ai/gemini-embedding-2-preview with Vertex multimodal pricing (#27848)

Browse Source 
* fix(cost): align vertex_ai/gemini-embedding-2-preview with Vertex multimodal pricing

Co-authored-by: Cursor <cursoragent@cursor.com>

* 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 <cursoragent@cursor.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Sameer Kankute 2026-05-14 00:35:53 +05:30 committed by GitHub
parent 466f06df6d
commit a74e269f7d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
litellm/model_prices_and_context_window_backup.json
View File

@ -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
},

9
model_prices_and_context_window.json
View File

@ -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
},

3
tests/test_litellm/test_utils.py
View File

@ -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)