scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109

chore: keep base field ordering for service tier cache write costs

Browse source
This commit is contained in:
mateo-berri 2026-08-05 02:11:05 -07:00
parent e8a80b9883
commit 69a8043667
2 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
litellm/types/utils.py
View file

@ -201,13 +201,13 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_flex: Optional[float] # OpenAI flex service tier pricing
input_cost_per_token_priority: Optional[float] # OpenAI priority service tier pricing
cache_creation_input_token_cost: Optional[float]
cache_creation_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing
cache_creation_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing
cache_creation_input_token_cost_above_200k_tokens: Optional[float]
cache_creation_input_token_cost_above_272k_tokens: Optional[float]
cache_creation_input_token_cost_above_272k_tokens_priority: Optional[float]
cache_creation_input_token_cost_above_272k_tokens_flex: Optional[float]
cache_creation_input_token_cost_above_1hr: Optional[float]
cache_creation_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing
cache_creation_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing
cache_read_input_token_cost: Optional[float]
cache_read_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing
cache_read_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing
@ -3258,13 +3258,13 @@ class CustomPricingLiteLLMParams(BaseModel):
input_cost_per_token_flex: Optional[float] = None
input_cost_per_token_priority: Optional[float] = None
cache_creation_input_token_cost: Optional[float] = None
cache_creation_input_token_cost_flex: Optional[float] = None
cache_creation_input_token_cost_priority: Optional[float] = None
cache_creation_input_token_cost_above_1hr: Optional[float] = None
cache_creation_input_token_cost_above_200k_tokens: Optional[float] = None
cache_creation_input_token_cost_above_272k_tokens: Optional[float] = None
cache_creation_input_token_cost_above_272k_tokens_priority: Optional[float] = None
cache_creation_input_token_cost_above_272k_tokens_flex: Optional[float] = None
cache_creation_input_token_cost_flex: Optional[float] = None
cache_creation_input_token_cost_priority: Optional[float] = None
cache_creation_input_audio_token_cost: Optional[float] = None
cache_read_input_token_cost: Optional[float] = None
cache_read_input_token_cost_flex: Optional[float] = None

8
litellm/utils.py
View file

@ -5405,10 +5405,6 @@ def _get_model_info_helper(
input_cost_per_token_flex=_model_info.get("input_cost_per_token_flex", None),
input_cost_per_token_priority=_model_info.get("input_cost_per_token_priority", None),
cache_creation_input_token_cost=_model_info.get("cache_creation_input_token_cost", None),
cache_creation_input_token_cost_flex=_model_info.get("cache_creation_input_token_cost_flex", None),
cache_creation_input_token_cost_priority=_model_info.get(
"cache_creation_input_token_cost_priority", None
),
cache_creation_input_token_cost_above_200k_tokens=_model_info.get(
"cache_creation_input_token_cost_above_200k_tokens", None
),
@ -5421,6 +5417,10 @@ def _get_model_info_helper(
cache_creation_input_token_cost_above_272k_tokens_flex=_model_info.get(
"cache_creation_input_token_cost_above_272k_tokens_flex", None
),
cache_creation_input_token_cost_flex=_model_info.get("cache_creation_input_token_cost_flex", None),
cache_creation_input_token_cost_priority=_model_info.get(
"cache_creation_input_token_cost_priority", None
),
cache_read_input_token_cost=_model_info.get("cache_read_input_token_cost", None),
prompt_cache_min_tokens=_model_info.get("prompt_cache_min_tokens", None),
cache_read_input_token_cost_above_200k_tokens=_model_info.get(