diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index c246700dc0e..957ce7ea197 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -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
diff --git a/litellm/utils.py b/litellm/utils.py
index 58d2f4b9ef7..b5240c89c4c 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -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
                 ),
diff --git a/tests/test_litellm/llms/openai_like/test_sail_provider.py b/tests/test_litellm/llms/openai_like/test_sail_provider.py
index 7cafab12262..69b7f9cdf6f 100644
--- a/tests/test_litellm/llms/openai_like/test_sail_provider.py
+++ b/tests/test_litellm/llms/openai_like/test_sail_provider.py
@@ -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]