scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

fix(model_prices): bill muse spark web search grounding per query

Browse source
This commit is contained in:
mateo-berri 2026-08-12 19:44:20 -07:00
parent 1369b3e6f3
commit 39a5ede2d9
3 changed files with 45 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
litellm/model_prices_and_context_window_backup.json
View file

@ -27473,6 +27473,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.25e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
@ -27509,6 +27514,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.25e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
@ -27545,6 +27555,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",

15
model_prices_and_context_window.json
View file

@ -27473,6 +27473,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.25e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
@ -27509,6 +27514,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.25e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",
@ -27545,6 +27555,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.0025,
"search_context_size_low": 0.0025,
"search_context_size_medium": 0.0025
},
"source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits",
"supported_endpoints": [
"/v1/chat/completions",

15
tests/test_litellm/test_muse_spark_1_2_model_metadata.py
View file

@ -6,9 +6,11 @@ import pytest
import litellm
from litellm.cost_calculator import cost_per_token
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
from litellm.litellm_core_utils.llm_cost_calc.tool_call_cost_tracking import StandardBuiltInToolCostTracking
MUSE_SPARK_STANDARD = "meta/muse-spark-1.2"
MUSE_SPARK_CONTRIBUTOR = "meta/muse-spark-1.2-contributor"
WEB_SEARCH_COST_PER_QUERY = 0.0025
PRICING = (
(MUSE_SPARK_STANDARD, 1.25e-06, 1.5e-07, 4.25e-06),
@ -68,6 +70,12 @@ def test_muse_spark_1_2_model_info(model: str, input_cost: float, cached_cost: f
assert info["supported_modalities"] == ["text", "image", "video"]
assert info["supported_output_modalities"] == ["text"]
assert info["search_context_cost_per_query"] == {
"search_context_size_high": WEB_SEARCH_COST_PER_QUERY,
"search_context_size_low": WEB_SEARCH_COST_PER_QUERY,
"search_context_size_medium": WEB_SEARCH_COST_PER_QUERY,
}
@pytest.mark.parametrize("model, input_cost, cached_cost, output_cost", PRICING)
def test_muse_spark_1_2_cost_per_token(
@ -88,6 +96,13 @@ def test_muse_spark_1_2_routes_to_meta_model_api(model: str):
assert api_base == "https://api.meta.ai/v1"
@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR))
def test_muse_spark_1_2_web_search_cost_per_query(local_model_cost_map, model: str):
info = litellm.get_model_info(model=model)
assert StandardBuiltInToolCostTracking.get_cost_for_web_search(model_info=info) == WEB_SEARCH_COST_PER_QUERY
@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR))
def test_muse_spark_1_2_backup_matches_main(model: str):
"""Ensure the bundled model cost map stays in sync with the canonical file."""