scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

fix(cost): move gemini-embedding-2-preview to per-token rates

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 01:34:22 +00:00
parent 27a486e4d3
commit a28ea22ec1
3 changed files with 13 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
litellm/model_prices_and_context_window_backup.json
View file

@ -25604,6 +25604,7 @@
"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_token_batches": 1e-07,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 8192,
@ -25634,6 +25635,7 @@
"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_token_batches": 1e-07,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
@ -25692,6 +25694,7 @@
"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_token_batches": 1e-07,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "gemini",
"max_input_tokens": 8192,

3
model_prices_and_context_window.json
View file

@ -25604,6 +25604,7 @@
"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_token_batches": 1e-07,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai-embedding-models",
"max_input_tokens": 8192,
@ -25634,6 +25635,7 @@
"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_token_batches": 1e-07,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
@ -25692,6 +25694,7 @@
"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_token_batches": 1e-07,
"input_cost_per_video_token": 1.2e-05,
"litellm_provider": "gemini",
"max_input_tokens": 8192,

11
tests/test_litellm/test_utils.py
View file

@ -2946,7 +2946,7 @@ def test_model_info_for_openrouter_kimi_k2_5():
def test_gemini_embedding_2_ga_in_cost_map():
"""GA and Vertex preview gemini-embedding-2 entries align with multimodal unit pricing."""
"""GA and Vertex preview gemini-embedding-2 entries align with multimodal token pricing."""
import json
from pathlib import Path
@ -2968,9 +2968,12 @@ def test_gemini_embedding_2_ga_in_cost_map():
assert info.get("mode") == "embedding"
assert info.get("supports_multimodal") is True
assert info.get("input_cost_per_token") == 2e-07
assert info.get("input_cost_per_image") == 0.00012
assert info.get("input_cost_per_audio_per_second") == 0.00016
assert info.get("input_cost_per_video_per_second") == 0.00079
assert info.get("input_cost_per_audio_token") == 6.5e-06
assert info.get("input_cost_per_image_token") == 4.5e-07
assert info.get("input_cost_per_video_token") == 1.2e-05
assert "input_cost_per_image" not in info
assert "input_cost_per_audio_per_second" not in info
assert "input_cost_per_video_per_second" not in info
if provider in ("vertex_ai-embedding-models", "vertex_ai"):
assert (
info.get("uses_embed_content") is True