scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49

fix(cost): bill gemini-embedding-2-preview per token like the GA entries

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-09-15 01:18:50 +00:00
parent 6a18105275
commit 4a8ec7b9d8
3 changed files with 40 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
litellm/model_prices_and_context_window_backup.json
View file

@ -25601,10 +25601,10 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
},
"gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_audio_token": 6.5e-06,
"input_cost_per_image_token": 4.5e-07,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 8192,
"max_tokens": 8192,
@ -25631,10 +25631,10 @@
"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_audio_token": 6.5e-06,
"input_cost_per_image_token": 4.5e-07,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
@ -25689,10 +25689,10 @@
},
"gemini/gemini-embedding-2-preview": {
"deprecation_date": "2026-08-10",
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_audio_token": 6.5e-06,
"input_cost_per_image_token": 4.5e-07,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_tokens": 8192,

18
model_prices_and_context_window.json
View file

@ -25601,10 +25601,10 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
},
"gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_audio_token": 6.5e-06,
"input_cost_per_image_token": 4.5e-07,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 8192,
"max_tokens": 8192,
@ -25631,10 +25631,10 @@
"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_audio_token": 6.5e-06,
"input_cost_per_image_token": 4.5e-07,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
@ -25689,10 +25689,10 @@
},
"gemini/gemini-embedding-2-preview": {
"deprecation_date": "2026-08-10",
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_audio_token": 6.5e-06,
"input_cost_per_image_token": 4.5e-07,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_tokens": 8192,

22
tests/test_litellm/llms/vertex_ai/gemini_embeddings/test_batch_embed_content_transformation.py
View file

@ -500,6 +500,28 @@ class TestProcessEmbedContentResponseUsage:
)
assert prompt_cost == pytest.approx(516 * 1.2e-5 + 64 * 6.5e-6)
def test_preview_alias_bills_audio_per_token(self):
response_json = {
"embedding": {"values": [0.1]},
"usageMetadata": {
"promptTokenCount": 64,
"totalTokenCount": 64,
"promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 64}],
},
}
result = process_embed_content_response(
input="audio",
model_response=EmbeddingResponse(),
model="gemini-embedding-2-preview",
response_json=response_json,
)
prompt_cost, _ = generic_cost_per_token(
model="gemini-embedding-2-preview",
usage=result.usage,
custom_llm_provider="vertex_ai",
)
assert prompt_cost == pytest.approx(64 * 6.5e-6)
def test_image_without_modality_details_uses_image_rate(self):
response_json = {
"embedding": {"values": [0.1]},