diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
index 78a555940c8..153b8457e38 100644
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@@ -77,7 +77,7 @@ from litellm.llms.tencent.cost_calculator import (
 )
 from litellm.llms.together_ai.cost_calculator import (
     get_model_params_and_category,
-    has_together_registry_entry,
+    has_together_registry_pricing,
 )
 from litellm.llms.vertex_ai.cost_calculator import (
     cost_per_character as google_cost_per_character,
@@ -1556,7 +1556,7 @@ def completion_cost(
                 # Calculate cost based on prompt_tokens, completion_tokens
                 if (
                     "togethercomputer" in model or "together_ai" in model or custom_llm_provider == "together_ai"
-                ) and not has_together_registry_entry(model, litellm.model_cost):
+                ) and not has_together_registry_pricing(model, litellm.model_cost):
                     model = get_model_params_and_category(model, call_type=CallTypes(call_type))
 
                 # replicate llms are calculate based on time for request running
diff --git a/litellm/llms/together_ai/cost_calculator.py b/litellm/llms/together_ai/cost_calculator.py
index 2f492496e7b..6fc2c949fa6 100644
--- a/litellm/llms/together_ai/cost_calculator.py
+++ b/litellm/llms/together_ai/cost_calculator.py
@@ -19,9 +19,10 @@ from litellm.constants import (
 from litellm.types.utils import CallTypes
 
 
-def has_together_registry_entry(model: str, cost_map: Mapping[str, object]) -> bool:
+def has_together_registry_pricing(model: str, cost_map: Mapping[str, object]) -> bool:
     stripped: Final = model.removeprefix("together_ai/")
-    return f"together_ai/{stripped}" in cost_map
+    entry: Final = cost_map.get(f"together_ai/{stripped}")
+    return isinstance(entry, Mapping) and "input_cost_per_token" in entry
 
 
 # Extract the number of billion parameters from the model name
diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py
index bf230bf794c..edc0635a741 100644
--- a/tests/test_litellm/test_cost_calculator.py
+++ b/tests/test_litellm/test_cost_calculator.py
@@ -3838,3 +3838,16 @@ def test_completion_cost_together_unmapped_model_still_uses_size_bucket(_local_m
     )
 
     assert cost == pytest.approx((23 + 15) * 9e-07, rel=1e-9)
+
+
+def test_completion_cost_together_metadata_only_model_still_uses_size_bucket(_local_model_cost_map):
+    assert "input_cost_per_token" not in litellm.model_cost["together_ai/togethercomputer/CodeLlama-34b-Instruct"]
+
+    cost = completion_cost(
+        completion_response=_together_chat_response(
+            model="togethercomputer/CodeLlama-34b-Instruct", prompt_tokens=23, completion_tokens=15, cached_tokens=0
+        ),
+        custom_llm_provider="together_ai",
+    )
+
+    assert cost == pytest.approx((23 + 15) * 8e-07, rel=1e-9)