From 69a80436673d634fad78e48d811157f6b8a09578 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Wed, 5 Aug 2026 02:11:05 -0700
Subject: [PATCH] chore: keep base field ordering for service tier cache write
 costs

---
 litellm/types/utils.py | 8 ++++----
 litellm/utils.py       | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index 70b7beefcce..77f83c5b6f8 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -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
diff --git a/litellm/utils.py b/litellm/utils.py
index f3e90298306..d24a4dc928f 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -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(