diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 4e1869a83a8..23ce80f9968 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -9713,6 +9713,30 @@
             "/v1/images/generations"
         ]
     },
+    "azure_ai/MAI-Thinking-1": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 8e-06,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "azure_ai/Llama-3.2-11B-Vision-Instruct": {
         "deprecation_date": "2026-06-13",
         "input_cost_per_token": 3.7e-07,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 4e1869a83a8..23ce80f9968 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -9713,6 +9713,30 @@
             "/v1/images/generations"
         ]
     },
+    "azure_ai/MAI-Thinking-1": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 8e-06,
+        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "azure_ai/Llama-3.2-11B-Vision-Instruct": {
         "deprecation_date": "2026-06-13",
         "input_cost_per_token": 3.7e-07,
diff --git a/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py b/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py
index fd6fab6a521..9612d97d946 100644
--- a/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py
+++ b/tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py
@@ -501,7 +501,7 @@ class TestAzureAIServiceTierCostCalculation:
         assert flex_completion < standard_completion
 
 
-def test_codestral_2501_model_info_and_cost():
+def test_codestral_2501_model_info_and_cost(local_model_cost_map):
     model_info = get_model_info(model="Codestral-2501", custom_llm_provider="azure_ai")
     usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000)
 
@@ -512,3 +512,19 @@ def test_codestral_2501_model_info_and_cost():
     assert model_info["max_output_tokens"] == 4096
     assert prompt_cost == pytest.approx(0.3)
     assert completion_cost == pytest.approx(0.9)
+
+
+def test_mai_thinking_1_model_info_and_cost(local_model_cost_map):
+    model_info = get_model_info(model="MAI-Thinking-1", custom_llm_provider="azure_ai")
+    usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000)
+
+    prompt_cost, completion_cost = cost_per_token(model="MAI-Thinking-1", usage=usage)
+
+    assert model_info["mode"] == "chat"
+    assert model_info["max_input_tokens"] == 256000
+    assert model_info["max_output_tokens"] == 64000
+    assert model_info["cache_read_input_token_cost"] == pytest.approx(2e-07)
+    assert model_info["supports_reasoning"] is True
+    assert model_info["supports_function_calling"] is True
+    assert prompt_cost == pytest.approx(2.0)
+    assert completion_cost == pytest.approx(8.0)