From 5424ccae2953d38c0776e4b12750c235e73912ac Mon Sep 17 00:00:00 2001
From: Ewerton Silva <ewertoncom297@gmail.com>
Date: Thu, 18 Jun 2026 21:05:49 -0300
Subject: [PATCH] fix(utils): preserve arbitrary above-threshold tiered pricing
 keys in get_model_info

get_model_info rebuilt ModelInfo by copying a fixed allow-list of
input/output_cost_per_token_above_<N>_tokens keys (128k/200k/272k/512k), so any other
threshold a user registered was dropped before reaching _get_token_base_cost, which already
reads an arbitrary threshold out of the key name. Custom tiers such as above_500k_tokens were
silently ignored and billing fell back to the base per-token rate. Carry over any
_above_<N>_tokens cost key present on the source cost-map entry that the fixed fields miss

Fixes #30344
---
 litellm/utils.py                              | 12 ++++++-
 .../llm_cost_calc/test_llm_cost_calc_utils.py | 35 +++++++++++++++++++
 2 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/litellm/utils.py b/litellm/utils.py
index c9001e7d906..7686707ce19 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -5842,6 +5842,9 @@ def _is_potential_model_name_in_model_cost(
     )
 
 
+_ABOVE_THRESHOLD_COST_KEY = re.compile(r"_above_\d+k?_tokens$")
+
+
 def _get_model_info_helper(
     model: str,
     custom_llm_provider: Optional[str] = None,
@@ -6019,7 +6022,7 @@ def _get_model_info_helper(
                 )
                 _output_cost_per_token = 0
 
-            return ModelInfoBase(
+            returned_model_info = ModelInfoBase(
                 key=key,
                 max_tokens=_model_info.get("max_tokens", None),
                 max_input_tokens=_model_info.get("max_input_tokens", None),
@@ -6236,6 +6239,13 @@ def _get_model_info_helper(
                 uses_embed_content=_model_info.get("uses_embed_content", None),
                 supports_image_size=_model_info.get("supports_image_size", None),
             )
+            for cost_key, cost_value in _model_info.items():
+                if (
+                    cost_key not in returned_model_info
+                    and _ABOVE_THRESHOLD_COST_KEY.search(cost_key) is not None
+                ):
+                    returned_model_info[cost_key] = cost_value  # type: ignore[literal-required]
+            return returned_model_info
     except Exception as e:
         verbose_logger.debug(f"Error getting model info: {e}")
         raise Exception(
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index 9b3152fae07..29fe3484497 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -384,6 +384,41 @@ def test_generic_cost_per_token_minimax_m3_above_512k_tokens():
     assert round(completion_cost, 10) == round(expected_completion, 10)
 
 
+def test_generic_cost_per_token_honors_non_standard_above_threshold():
+    """Regression for #30344: get_model_info must keep arbitrary
+    input/output_cost_per_token_above_<N>_tokens thresholds, not only the hard-coded
+    128k/200k/272k/512k set, so a custom tier boundary is applied past its limit."""
+    model = "litellm-test-non-standard-tier"
+    custom_llm_provider = "openai"
+    litellm.register_model(
+        {
+            model: {
+                "litellm_provider": custom_llm_provider,
+                "mode": "chat",
+                "input_cost_per_token": 1e-6,
+                "output_cost_per_token": 2e-6,
+                "input_cost_per_token_above_500k_tokens": 9e-6,
+                "output_cost_per_token_above_500k_tokens": 18e-6,
+            }
+        }
+    )
+
+    prompt_tokens = 600000
+    completion_tokens = 1000
+    usage = Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+    )
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model=model,
+        usage=usage,
+        custom_llm_provider=custom_llm_provider,
+    )
+    assert round(prompt_cost, 10) == round(9e-6 * prompt_tokens, 10)
+    assert round(completion_cost, 10) == round(18e-6 * completion_tokens, 10)
+
+
 def test_generic_cost_per_token_gpt55():
     """gpt-5.5: base pricing — $5/1M input, $30/1M output, $0.50/1M cached input."""
     model = "gpt-5.5"