Merge pull request #4760 from skucherlapati/bug_4757_add_medlm_to_cost_calc

Add Medlm cost calc

litellm/model_prices_and_context_window_backup.json

@@ -1820,6 +1820,26 @@
         "supports_vision": true,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
     },
+    "medlm-medium": {
+        "max_tokens": 8192,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 8192,
+        "input_cost_per_character": 0.0000005,
+        "output_cost_per_character": 0.000001,
+        "litellm_provider": "vertex_ai-language-models",
+        "mode": "chat",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+    },
+    "medlm-large": {
+        "max_tokens": 1024,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 1024,
+        "input_cost_per_character": 0.000005,
+        "output_cost_per_character": 0.000015,
+        "litellm_provider": "vertex_ai-language-models",
+        "mode": "chat",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+    },
     "vertex_ai/claude-3-sonnet@20240229": {
         "max_tokens": 4096,
         "max_input_tokens": 200000,

litellm/tests/test_completion_cost.py

@@ -706,6 +706,18 @@ def test_vertex_ai_completion_cost():
     print("calculated_input_cost: {}".format(calculated_input_cost))
 
 
+def test_vertex_ai_medlm_completion_cost():
+    model="medlm-medium"
+    messages = [{"role": "user", "content": "Test MedLM completion cost."}]
+    predictive_cost = completion_cost(model=model, messages=messages)
+    assert predictive_cost > 0
+
+    model="medlm-large"
+    messages = [{"role": "user", "content": "Test MedLM completion cost."}]
+    predictive_cost = completion_cost(model=model, messages=messages)
+    assert predictive_cost > 0
+
+
 def test_vertex_ai_claude_completion_cost():
     from litellm import Choices, Message, ModelResponse
     from litellm.utils import Usage