From f453f20290cee51132fad9a824fb0609e0633e02 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Thu, 9 Jul 2026 16:07:58 +0000
Subject: [PATCH] feat(azure_ai): add Cohere Command A (03-2025) model pricing
 and metadata

---
 ...odel_prices_and_context_window_backup.json | 12 ++++
 model_prices_and_context_window.json          | 12 ++++
 .../test_azure_ai_command_a_metadata.py       | 63 +++++++++++++++++++
 3 files changed, 87 insertions(+)
 create mode 100644 tests/test_litellm/llms/azure_ai/test_azure_ai_command_a_metadata.py

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index db534b52df9..f2f6ef7ca0b 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -8125,6 +8125,18 @@
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
+    "azure_ai/cohere-command-a-03-2025": {
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-command-a-in-foundry/4530376",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
     "azure_ai/cohere-rerank-v3-english": {
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 363ba9842b0..26aa391b6b6 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -8125,6 +8125,18 @@
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
+    "azure_ai/cohere-command-a-03-2025": {
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-command-a-in-foundry/4530376",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
     "azure_ai/cohere-rerank-v3-english": {
         "input_cost_per_query": 0.002,
         "input_cost_per_token": 0.0,
diff --git a/tests/test_litellm/llms/azure_ai/test_azure_ai_command_a_metadata.py b/tests/test_litellm/llms/azure_ai/test_azure_ai_command_a_metadata.py
new file mode 100644
index 00000000000..ab0d563f55a
--- /dev/null
+++ b/tests/test_litellm/llms/azure_ai/test_azure_ai_command_a_metadata.py
@@ -0,0 +1,63 @@
+"""
+Test Azure AI Cohere Command A 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_command_a_model_info(use_local_model_cost_map):
+    model_info = use_local_model_cost_map.get_model_info(model="azure_ai/cohere-command-a-03-2025")
+
+    assert model_info["litellm_provider"] == "azure_ai"
+    assert model_info["mode"] == "chat"
+    assert model_info["max_input_tokens"] == 256000
+    assert model_info["max_output_tokens"] == 8000
+    assert model_info["max_tokens"] == 8000
+    assert model_info["input_cost_per_token"] == pytest.approx(2.5e-06)
+    assert model_info["output_cost_per_token"] == pytest.approx(1e-05)
+    assert model_info["supports_function_calling"] is True
+    assert model_info["supports_tool_choice"] is True
+
+
+def test_azure_ai_command_a_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="cohere-command-a-03-2025", usage=usage)
+
+    assert prompt_cost == pytest.approx(2.5)
+    assert completion_cost == pytest.approx(10.0)