fix: sort tiered token-cost thresholds numerically (#30375)

* fix: sort tiered token-cost thresholds numerically

_get_token_base_cost iterated input_cost_per_token_above_<N>_tokens keys with a
lexicographic sort, so for tiers whose thresholds have different digit lengths
(e.g. 90k vs 128k) a request crossing both was billed at the lower tier that
sorted first. Sort by the parsed numeric threshold instead, so the highest tier
the request actually crosses is applied.

* refactor: reuse _parse_above_token_threshold for inline threshold parse

---------

Co-authored-by: Eric (GabiDevFamily) <271972409+santino18727-debug@users.noreply.github.com>

litellm/litellm_core_utils/llm_cost_calc/utils.py

@@ -191,6 +191,11 @@ def _get_service_tier_cost_key(base_key: str, service_tier: Optional[str]) -> st
     return base_key
 
 
+def _parse_above_token_threshold(key: str) -> float:
+    threshold_str = key.split("_above_")[1].split("_tokens")[0]
+    return float(threshold_str.replace("k", "")) * (1000 if "k" in threshold_str else 1)
+
+
 def _get_token_base_cost(
     model_info: ModelInfo, usage: Usage, service_tier: Optional[str] = None
 ) -> Tuple[float, float, float, float, float]:
@@ -256,15 +261,13 @@ def _get_token_base_cost(
 
     # Only sort the threshold keys (typically 1-2 keys instead of 66+)
     threshold: Optional[float] = None
-    for key in sorted(threshold_keys, reverse=True):
+    for key in sorted(threshold_keys, key=_parse_above_token_threshold, reverse=True):
         value = model_info.get(key)
         if value is not None:
             try:
                 # Handle both formats: _above_128k_tokens and _above_128_tokens
                 threshold_str = key.split("_above_")[1].split("_tokens")[0]
-                threshold = float(threshold_str.replace("k", "")) * (
-                    1000 if "k" in threshold_str else 1
-                )
+                threshold = _parse_above_token_threshold(key)
                 if usage.prompt_tokens > threshold:
                     # Prefer a service_tier-specific above-threshold key when available,
                     # e.g. input_cost_per_token_priority_above_200k_tokens for Gemini

tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py

@@ -35,6 +35,7 @@ sys.path.insert(
 from litellm.litellm_core_utils.llm_cost_calc.utils import (
     PromptTokensDetailsResult,
     _calculate_input_cost,
+    _get_token_base_cost,
     calculate_cache_writing_cost,
     generic_cost_per_token,
 )
@@ -298,6 +299,26 @@ def test_generic_cost_per_token_above_200k_tokens():
     )
 
 
+def test_get_token_base_cost_picks_highest_crossed_tier():
+    """Regression test for #30345.
+
+    With graduated tiers at 90k and 128k whose keys have different digit lengths, a request
+    crossing both must be billed at the highest tier it crosses (128k), not the lower one that
+    happens to sort first lexicographically.
+    """
+    model_info = {
+        "input_cost_per_token": 1e-6,
+        "output_cost_per_token": 2e-6,
+        "input_cost_per_token_above_90k_tokens": 5e-6,
+        "input_cost_per_token_above_128k_tokens": 9e-6,
+    }
+    usage = Usage(prompt_tokens=150_000, completion_tokens=10, total_tokens=150_010)
+
+    prompt_base_cost = _get_token_base_cost(model_info, usage)[0]
+
+    assert prompt_base_cost == 9e-6
+
+
 def test_generic_cost_per_token_gpt54_above_272k_tokens():
     """GPT-5.4/5.4-pro: prompts >272K input tokens priced at 2x input, 1.5x output."""
     model = "gpt-5.4"