scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 86

Merge pull request #36717 from BerriAI/litellm_add_muse_spark_1_2

Browse source 
feat(model_prices): add meta/muse-spark-1.2 and its contributor tier
This commit is contained in:
Mateo Wang 2026-08-13 16:19:06 -07:00 • committed by GitHub
commit 373a0fc506
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 295 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

87
litellm/model_prices_and_context_window_backup.json
View file

@ -27711,6 +27711,93 @@
"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",
"/v1/responses",
"/v1/messages"
],
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_minimal_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"meta/muse-spark-1.2": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "meta",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"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",
"/v1/responses",
"/v1/messages"
],
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_minimal_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"meta/muse-spark-1.2-contributor": {
"cache_read_input_token_cost": 2e-09,
"input_cost_per_token": 1e-07,
"litellm_provider": "meta",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"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",

87
model_prices_and_context_window.json
View file

@ -27711,6 +27711,93 @@
"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",
"/v1/responses",
"/v1/messages"
],
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_minimal_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"meta/muse-spark-1.2": {
"cache_read_input_token_cost": 1.5e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "meta",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"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",
"/v1/responses",
"/v1/messages"
],
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_minimal_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"meta/muse-spark-1.2-contributor": {
"cache_read_input_token_cost": 2e-09,
"input_cost_per_token": 1e-07,
"litellm_provider": "meta",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"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",

121
tests/test_litellm/test_muse_spark_1_2_model_metadata.py Normal file
View file

@ -0,0 +1,121 @@
import json
from pathlib import Path
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),
(MUSE_SPARK_CONTRIBUTOR, 1e-07, 2e-09, 2e-07),
)
def _load_cost_map(filename: str = "model_prices_and_context_window.json") -> dict:
with open(Path(__file__).parents[2] / filename) as f:
return json.load(f)
@pytest.fixture
def local_model_cost_map(monkeypatch):
"""Force the bundled backup cost map so assertions don't depend on the
network-fetched ``main`` copy (which lags this branch until merge)."""
original_model_cost = litellm.model_cost
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
litellm.model_cost = litellm.get_model_cost_map(url="")
litellm.get_model_info.cache_clear()
try:
yield
finally:
litellm.model_cost = original_model_cost
litellm.get_model_info.cache_clear()
@pytest.mark.parametrize("model, input_cost, cached_cost, output_cost", PRICING)
def test_muse_spark_1_2_model_info(model: str, input_cost: float, cached_cost: float, output_cost: float):
info = _load_cost_map().get(model)
assert info is not None, f"{model} not found in model_prices_and_context_window.json"
assert info["litellm_provider"] == "meta"
assert info["mode"] == "chat"
assert info["input_cost_per_token"] == input_cost
assert info["output_cost_per_token"] == output_cost
assert info["cache_read_input_token_cost"] == cached_cost
assert info["max_input_tokens"] == 1048576
assert info["max_output_tokens"] == 131072
assert info["max_tokens"] == 131072
assert info["supports_function_calling"] is True
assert info["supports_parallel_function_calling"] is True
assert info["supports_prompt_caching"] is True
assert info["supports_reasoning"] is True
assert info["supports_response_schema"] is True
assert info["supports_tool_choice"] is True
assert info["supports_vision"] is True
assert info["supports_pdf_input"] is True
assert info["supports_web_search"] is True
assert info["supports_minimal_reasoning_effort"] is True
assert info["supports_xhigh_reasoning_effort"] is True
assert info["supported_endpoints"] == ["/v1/chat/completions", "/v1/responses", "/v1/messages"]
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(
local_model_cost_map, model: str, input_cost: float, cached_cost: float, output_cost: float
):
prompt_cost, completion_cost = cost_per_token(model=model, prompt_tokens=1000, completion_tokens=500)
assert prompt_cost == pytest.approx(1000 * input_cost)
assert completion_cost == pytest.approx(500 * output_cost)
@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR))
def test_muse_spark_1_2_routes_to_meta_model_api(model: str):
routed_model, provider, _, api_base = get_llm_provider(model=model, api_key="sk-test")
assert routed_model == model.split("/", 1)[1]
assert provider == "meta"
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."""
main_cost = _load_cost_map()
backup_cost = _load_cost_map("litellm/model_prices_and_context_window_backup.json")
assert backup_cost.get(model) == main_cost.get(model), f"{model} differs between main and backup model cost maps"
def test_muse_spark_contributor_tier_is_cheaper_than_standard():
cost_map = _load_cost_map()
standard = cost_map[MUSE_SPARK_STANDARD]
contributor = cost_map[MUSE_SPARK_CONTRIBUTOR]
for field in ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost"):
assert contributor[field] < standard[field], f"contributor {field} should undercut the standard tier"