From d8fc5c3a37fc77e5d88f5e15f4cbc1102d98aceb Mon Sep 17 00:00:00 2001
From: Emerson Gomes <emerson.gomes@thalesgroup.com>
Date: Sun, 14 Dec 2025 14:34:46 -0600
Subject: [PATCH] Add Azure Cohere 4 reranking models (#17961)

---
 ...odel_prices_and_context_window_backup.json | 22 +++++++++++++++++++
 model_prices_and_context_window.json          | 22 +++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index c584deb683..2af548ce07 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -5145,6 +5145,28 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "azure_ai/cohere-rerank-v4.0-pro": {
+        "input_cost_per_query": 0.0025,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_query_tokens": 4096,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
+    "azure_ai/cohere-rerank-v4.0-fast": {
+        "input_cost_per_query": 0.002,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_query_tokens": 4096,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
     "azure_ai/deepseek-r1": {
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "azure_ai",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index c584deb683..2af548ce07 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -5145,6 +5145,28 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "azure_ai/cohere-rerank-v4.0-pro": {
+        "input_cost_per_query": 0.0025,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_query_tokens": 4096,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
+    "azure_ai/cohere-rerank-v4.0-fast": {
+        "input_cost_per_query": 0.002,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_query_tokens": 4096,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
     "azure_ai/deepseek-r1": {
         "input_cost_per_token": 1.35e-06,
         "litellm_provider": "azure_ai",