phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Realtime API: Support 'base_model' cost tracking + show response in spend logs (if enabled) (#9897)

Browse source 
* refactor(litellm_logging.py): refactor realtime cost tracking to use common code as rest

Ensures basic features like base model just work

* feat(realtime/): support 'base_model' cost tracking on realtime api

Fixes issue where base model was not working on realtime

* fix: fix ruff linting error

* test: fix test
This commit is contained in:
Krish Dholakia 2025-04-10 21:24:45 -07:00 • committed by GitHub
parent 78879c68a9
commit 9f27e8363f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 102 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

16
litellm/realtime_api/main.py
View file

@ -7,6 +7,7 @@ from litellm import get_llm_provider
from litellm.secret_managers.main import get_secret_str
from litellm.types.router import GenericLiteLLMParams
from ..litellm_core_utils.get_litellm_params import get_litellm_params
from ..litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
from ..llms.azure.realtime.handler import AzureOpenAIRealtime
from ..llms.openai.realtime.handler import OpenAIRealtime
@ -34,13 +35,11 @@ async def _arealtime(
For PROXY use only.
"""
litellm_logging_obj: LiteLLMLogging = kwargs.get("litellm_logging_obj") # type: ignore
litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None)
proxy_server_request = kwargs.get("proxy_server_request", None)
model_info = kwargs.get("model_info", None)
metadata = kwargs.get("metadata", {})
user = kwargs.get("user", None)
litellm_params = GenericLiteLLMParams(**kwargs)
litellm_params_dict = get_litellm_params(**kwargs)
model, _custom_llm_provider, dynamic_api_key, dynamic_api_base = get_llm_provider(
model=model,
api_base=api_base,
@ -51,14 +50,7 @@ async def _arealtime(
model=model,
user=user,
optional_params={},
litellm_params={
"litellm_call_id": litellm_call_id,
"proxy_server_request": proxy_server_request,
"model_info": model_info,
"metadata": metadata,
"preset_cache_key": None,
"stream_response": {},
},
litellm_params=litellm_params_dict,
custom_llm_provider=_custom_llm_provider,
)