scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

docs(fireworks): explain what get_model_cost_key is for

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-13 03:36:00 +00:00
parent a519d805bb
commit f1fe61af06
1 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
litellm/llms/base_llm/base_utils.py
View file

@ -52,7 +52,10 @@ class BaseLLMModelInfo(ABC):
def get_model_cost_key(self, model: str) -> str | None:
"""
Extra `litellm.model_cost` key to try for this provider's spelling of `model`, after the exact keys miss.
Maps the model name a user sends to the key `litellm.model_cost` stores it under, when the two differ.
`get_model_info` tries this key once the exact `model` and `provider/model` keys miss. The default None means
the provider's user-facing names already match the cost map, so there is nothing extra to try. Fireworks
overrides it: `deepseek-r1` -> `fireworks_ai/accounts/fireworks/models/deepseek-r1`.
"""
return None