phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Squashed commit of the following: (#9709)

Browse source 
commit b12a9892b7
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Wed Apr 2 08:09:56 2025 -0700

    fix(utils.py): don't modify openai_token_counter

commit 294de31803
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 21:22:40 2025 -0700

    fix: fix linting error

commit cb6e9fbe40
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:52:45 2025 -0700

    refactor: complete migration

commit bfc159172d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:09:59 2025 -0700

    refactor: refactor more constants

commit 43ffb6a558
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:45:24 2025 -0700

    fix: test

commit 04dbe4310c
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:28:58 2025 -0700

    refactor: refactor: move more constants into constants.py

commit 3c26284aff
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:14:46 2025 -0700

    refactor: migrate hardcoded constants out of __init__.py

commit c11e0de69d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:11:21 2025 -0700

    build: migrate all constants into constants.py

commit 7882bdc787
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:07:37 2025 -0700

    build: initial test banning hardcoded numbers in repo
This commit is contained in:
Krish Dholakia 2025-04-02 21:24:54 -07:00 • committed by GitHub
parent 5a722ef18f
commit 8ee32291e0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
51 changed files with 509 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/cost_calculator.py
View file

@ -9,6 +9,10 @@ from pydantic import BaseModel
import litellm
import litellm._logging
from litellm import verbose_logger
from litellm.constants import (
DEFAULT_MAX_LRU_CACHE_SIZE,
DEFAULT_REPLICATE_GPU_PRICE_PER_SECOND,
)
from litellm.litellm_core_utils.llm_cost_calc.tool_call_cost_tracking import (
StandardBuiltInToolCostTracking,
)
@ -355,9 +359,7 @@ def cost_per_token( # noqa: PLR0915
def get_replicate_completion_pricing(completion_response: dict, total_time=0.0):
# see https://replicate.com/pricing
# for all litellm currently supported LLMs, almost all requests go to a100_80gb
a100_80gb_price_per_second_public = (
0.001400 # assume all calls sent to A100 80GB for now
)
a100_80gb_price_per_second_public = DEFAULT_REPLICATE_GPU_PRICE_PER_SECOND # assume all calls sent to A100 80GB for now
if total_time == 0.0: # total time is in ms
start_time = completion_response.get("created", time.time())
end_time = getattr(completion_response, "ended", time.time())
@ -450,7 +452,7 @@ def _select_model_name_for_cost_calc(
return return_model
@lru_cache(maxsize=16)
@lru_cache(maxsize=DEFAULT_MAX_LRU_CACHE_SIZE)
def _model_contains_known_llm_provider(model: str) -> bool:
"""
Check if the model contains a known llm provider