feat(azure_ai): add pricing for azure_ai/kimi-k2.7-code

litellm/model_prices_and_context_window_backup.json

@@ -8496,6 +8496,20 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure_ai/kimi-k2.7-code": {
+        "cache_read_input_token_cost": 1.9e-07,
+        "input_cost_per_token": 9.5e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-7-code-in-microsoft-foundry/4532286",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "azure_ai/ministral-3b": {
         "input_cost_per_token": 4e-08,
         "litellm_provider": "azure_ai",

model_prices_and_context_window.json

@@ -8496,6 +8496,20 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure_ai/kimi-k2.7-code": {
+        "cache_read_input_token_cost": 1.9e-07,
+        "input_cost_per_token": 9.5e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 4e-06,
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-7-code-in-microsoft-foundry/4532286",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "azure_ai/ministral-3b": {
         "input_cost_per_token": 4e-08,
         "litellm_provider": "azure_ai",

tests/test_litellm/llms/azure_ai/test_azure_ai_kimi_k27_code_metadata.py

@@ -0,0 +1,85 @@
+"""
+Test Azure AI Kimi K2.7 Code model metadata.
+"""
+
+import json
+from importlib.resources import files
+
+import pytest
+
+
+@pytest.fixture(scope="module")
+def use_local_model_cost_map():
+    monkeypatch = pytest.MonkeyPatch()
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+
+    import litellm
+    from litellm.utils import _invalidate_model_cost_lowercase_map
+
+    original_model_cost = litellm.model_cost
+    litellm.model_cost = json.loads(
+        files("litellm")
+        .joinpath("model_prices_and_context_window_backup.json")
+        .read_text(encoding="utf-8")
+    )
+    litellm.get_model_info.cache_clear()
+    _invalidate_model_cost_lowercase_map()
+    try:
+        yield litellm
+    finally:
+        litellm.model_cost = original_model_cost
+        litellm.get_model_info.cache_clear()
+        _invalidate_model_cost_lowercase_map()
+        monkeypatch.undo()
+
+
+def test_azure_ai_kimi_k27_code_model_info(use_local_model_cost_map):
+    model_info = use_local_model_cost_map.get_model_info(model="azure_ai/kimi-k2.7-code")
+
+    assert model_info["litellm_provider"] == "azure_ai"
+    assert model_info["mode"] == "chat"
+    assert model_info["max_input_tokens"] == 262144
+    assert model_info["max_output_tokens"] == 262144
+    assert model_info["max_tokens"] == 262144
+    assert model_info["input_cost_per_token"] == pytest.approx(9.5e-07)
+    assert model_info["output_cost_per_token"] == pytest.approx(4e-06)
+    assert model_info["cache_read_input_token_cost"] == pytest.approx(1.9e-07)
+    assert model_info["supports_function_calling"] is True
+    assert model_info["supports_reasoning"] is True
+    assert model_info["supports_tool_choice"] is True
+
+
+def test_azure_ai_kimi_k27_code_cost_per_token(use_local_model_cost_map):
+    from litellm.llms.azure_ai.cost_calculator import cost_per_token
+    from litellm.types.utils import Usage
+
+    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="kimi-k2.7-code", usage=usage)
+
+    assert prompt_cost == pytest.approx(0.95)
+    assert completion_cost == pytest.approx(4.0)
+
+
+def test_azure_ai_kimi_k27_code_cached_prompt_cost(use_local_model_cost_map):
+    from litellm.llms.azure_ai.cost_calculator import cost_per_token
+    from litellm.types.utils import (
+        PromptTokensDetailsWrapper,
+        Usage,
+    )
+
+    usage = Usage(
+        prompt_tokens=1_000_000,
+        completion_tokens=0,
+        total_tokens=1_000_000,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=1_000_000),
+    )
+
+    prompt_cost, completion_cost = cost_per_token(model="kimi-k2.7-code", usage=usage)
+
+    assert prompt_cost == pytest.approx(0.19)
+    assert completion_cost == pytest.approx(0.0)