scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-29 01:42:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 79

refactor(cost): drop speculative above-272k balanced cost keys

Browse source
This commit is contained in:
shrey kharbanda 2026-09-24 04:59:43 +00:00
parent a978d5e03b
commit a8c8fdc64e
3 changed files with 2 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
litellm/types/utils.py
View file

@ -276,7 +276,6 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
cache_creation_input_token_cost_above_272k_tokens: float | None
cache_creation_input_token_cost_above_272k_tokens_priority: float | None
cache_creation_input_token_cost_above_272k_tokens_flex: float | None
cache_creation_input_token_cost_above_272k_tokens_balanced: float | None
cache_creation_input_token_cost_above_1hr: float | None
cache_creation_input_token_cost_flex: float | None # OpenAI flex service tier pricing
cache_creation_input_token_cost_balanced: float | None # balanced service tier pricing
@ -294,7 +293,6 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
cache_read_input_token_cost_above_272k_tokens: float | None
cache_read_input_token_cost_above_272k_tokens_priority: float | None
cache_read_input_token_cost_above_272k_tokens_flex: float | None
cache_read_input_token_cost_above_272k_tokens_balanced: float | None
cache_read_input_token_cost_above_512k_tokens: float | None
cache_read_input_token_cost_batches: ReadOnly[float | None]
cache_read_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
@ -312,7 +310,6 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
input_cost_per_token_above_272k_tokens_priority: float | None
input_cost_per_token_above_272k_tokens_flex: float | None
input_cost_per_token_above_272k_tokens_balanced: float | None
input_cost_per_token_above_512k_tokens: float | None # MiniMax-M3: prompts >512K priced at 2x input
input_cost_per_character_above_128k_tokens: float | None # only for vertex ai models
input_cost_per_query: float | None # per-request pricing: rerank, search, and Bedrock Marengo embeddings
@ -351,7 +348,6 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
output_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
output_cost_per_token_above_272k_tokens_priority: float | None
output_cost_per_token_above_272k_tokens_flex: float | None
output_cost_per_token_above_272k_tokens_balanced: float | None
output_cost_per_token_above_512k_tokens: float | None # MiniMax-M3: prompts >512K priced at 2x output
output_cost_per_character_above_128k_tokens: float | None # only for vertex ai models
output_cost_per_image: float | None
@ -3724,7 +3720,6 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
cache_creation_input_token_cost_above_272k_tokens: float | None = None
cache_creation_input_token_cost_above_272k_tokens_priority: float | None = None
cache_creation_input_token_cost_above_272k_tokens_flex: float | None = None
cache_creation_input_token_cost_above_272k_tokens_balanced: float | None = None
cache_creation_input_token_cost_flex: float | None = None
cache_creation_input_token_cost_balanced: float | None = None
cache_creation_input_token_cost_priority: float | None = None
@ -3738,7 +3733,6 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
cache_read_input_token_cost_above_200k_tokens_priority: float | None = None
cache_read_input_token_cost_above_272k_tokens_priority: float | None = None
cache_read_input_token_cost_above_272k_tokens_flex: float | None = None
cache_read_input_token_cost_above_272k_tokens_balanced: float | None = None
cache_read_input_token_cost_batches: float | None = None
cache_read_input_token_cost_above_272k_tokens_batches: float | None = None
cache_creation_input_token_cost_batches: float | None = None
@ -3753,7 +3747,6 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
input_cost_per_token_above_200k_tokens_priority: float | None = None
input_cost_per_token_above_272k_tokens_priority: float | None = None
input_cost_per_token_above_272k_tokens_flex: float | None = None
input_cost_per_token_above_272k_tokens_balanced: float | None = None
input_cost_per_token_above_272k_tokens_batches: float | None = None
input_cost_per_query: float | None = None
input_cost_per_image: float | None = None
@ -3779,7 +3772,6 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
output_cost_per_token_above_200k_tokens_priority: float | None = None
output_cost_per_token_above_272k_tokens_priority: float | None = None
output_cost_per_token_above_272k_tokens_flex: float | None = None
output_cost_per_token_above_272k_tokens_balanced: float | None = None
output_cost_per_token_above_272k_tokens_batches: float | None = None
output_cost_per_character_above_128k_tokens: float | None = None
output_cost_per_image: float | None = None

12
litellm/utils.py
View file

@ -6075,9 +6075,6 @@ 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_above_272k_tokens_balanced=_model_info.get(
"cache_creation_input_token_cost_above_272k_tokens_balanced", None
),
cache_creation_input_token_cost_flex=_model_info.get("cache_creation_input_token_cost_flex", None),
cache_creation_input_token_cost_balanced=_model_info.get(
"cache_creation_input_token_cost_balanced", None
@ -6106,9 +6103,6 @@ def _get_model_info_helper(
cache_read_input_token_cost_above_272k_tokens_flex=_model_info.get(
"cache_read_input_token_cost_above_272k_tokens_flex", None
),
cache_read_input_token_cost_above_272k_tokens_balanced=_model_info.get(
"cache_read_input_token_cost_above_272k_tokens_balanced", None
),
cache_read_input_token_cost_above_512k_tokens=_model_info.get(
"cache_read_input_token_cost_above_512k_tokens", None
),
@ -6141,9 +6135,6 @@ def _get_model_info_helper(
input_cost_per_token_above_272k_tokens_flex=_model_info.get(
"input_cost_per_token_above_272k_tokens_flex", None
),
input_cost_per_token_above_272k_tokens_balanced=_model_info.get(
"input_cost_per_token_above_272k_tokens_balanced", None
),
input_cost_per_token_above_512k_tokens=_model_info.get("input_cost_per_token_above_512k_tokens", None),
input_cost_per_query=_model_info.get("input_cost_per_query", None),
input_cost_per_second=_model_info.get("input_cost_per_second", None),
@ -6207,9 +6198,6 @@ def _get_model_info_helper(
output_cost_per_token_above_272k_tokens_flex=_model_info.get(
"output_cost_per_token_above_272k_tokens_flex", None
),
output_cost_per_token_above_272k_tokens_balanced=_model_info.get(
"output_cost_per_token_above_272k_tokens_balanced", None
),
output_cost_per_token_above_512k_tokens=_model_info.get(
"output_cost_per_token_above_512k_tokens", None
),

3
tests/test_litellm/llms/openai_like/test_sail_provider.py
View file

@ -517,8 +517,9 @@ class TestSailTierPricing:
{"extra_body": {"metadata": {"completion_window": "balanced"}}},
{"extra_body": {"metadata": {"completion_window": "flex"}}},
{"metadata": {"completion_window": "balanced"}},
{"service_tier": "auto", "extra_body": {"metadata": {"completion_window": "flex"}}},
],
ids=["extra_body_balanced", "extra_body_flex", "metadata_balanced"],
ids=["extra_body_balanced", "extra_body_flex", "metadata_balanced", "auto_tier_flex_window"],
)
def test_completion_window_in_optional_params_bills_at_tier_rates(self, optional_params: dict):
rates = litellm.model_cost[MODEL]