From 243c1cdb04e4b6f6904626f9ff1725d2d4da3baa Mon Sep 17 00:00:00 2001
From: shivam <shivam@berri.ai>
Date: Fri, 15 May 2026 17:15:27 -0700
Subject: [PATCH] fix(model_catalog): tighten Azure AI GPT-5.4 cost and
 capability metadata

Add supports_web_search for base GPT-5.4 aliases, priority-tier Pro rates,
and mini/nano above-272k plus priority pricing for correct spend math.

Co-authored-by: Cursor <cursoragent@cursor.com>
---
 ...odel_prices_and_context_window_backup.json | 49 ++++++++++++++++++
 model_prices_and_context_window.json          | 50 +++++++++++++++++++
 2 files changed, 99 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index b3c20f11372..5e81fd8e442 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -2093,6 +2093,7 @@
         "supports_tool_choice": true,
         "supports_service_tier": true,
         "supports_vision": true,
+        "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": true
@@ -2146,8 +2147,12 @@
     "azure_ai/gpt-5.4-pro": {
         "cache_read_input_token_cost": 3e-06,
         "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
         "input_cost_per_token": 3e-05,
         "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -2155,6 +2160,8 @@
         "mode": "responses",
         "output_cost_per_token": 0.00018,
         "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
         "supported_endpoints": [
             "/v1/batch",
@@ -2186,8 +2193,12 @@
     "azure_ai/gpt-5.4-pro-2026-03-05": {
         "cache_read_input_token_cost": 3e-06,
         "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
         "input_cost_per_token": 3e-05,
         "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -2195,6 +2206,8 @@
         "mode": "responses",
         "output_cost_per_token": 0.00018,
         "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
         "supported_endpoints": [
             "/v1/batch",
@@ -2225,13 +2238,22 @@
     },
     "azure_ai/gpt-5.4-mini": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
         "input_cost_per_token": 7.5e-07,
+        "input_cost_per_token_above_272k_tokens": 1.5e-06,
+        "input_cost_per_token_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
+        "output_cost_per_token_above_272k_tokens": 6.75e-06,
+        "output_cost_per_token_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -2263,13 +2285,22 @@
     },
     "azure_ai/gpt-5.4-mini-2026-03-17": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
         "input_cost_per_token": 7.5e-07,
+        "input_cost_per_token_above_272k_tokens": 1.5e-06,
+        "input_cost_per_token_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
+        "output_cost_per_token_above_272k_tokens": 6.75e-06,
+        "output_cost_per_token_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -2301,13 +2332,22 @@
     },
     "azure_ai/gpt-5.4-nano": {
         "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
+        "cache_read_input_token_cost_priority": 4e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-07,
+        "input_cost_per_token_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -2339,13 +2379,22 @@
     },
     "azure_ai/gpt-5.4-nano-2026-03-17": {
         "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
+        "cache_read_input_token_cost_priority": 4e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-07,
+        "input_cost_per_token_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
         "supported_endpoints": [
             "/v1/chat/completions",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 6fb5c2d089c..af7e15b4f3e 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -2107,6 +2107,7 @@
         "supports_tool_choice": true,
         "supports_service_tier": true,
         "supports_vision": true,
+        "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": true
@@ -2153,6 +2154,7 @@
         "supports_tool_choice": true,
         "supports_service_tier": true,
         "supports_vision": true,
+        "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": true
@@ -2160,8 +2162,12 @@
     "azure_ai/gpt-5.4-pro": {
         "cache_read_input_token_cost": 3e-06,
         "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
         "input_cost_per_token": 3e-05,
         "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -2169,6 +2175,8 @@
         "mode": "responses",
         "output_cost_per_token": 0.00018,
         "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
         "supported_endpoints": [
             "/v1/batch",
@@ -2200,8 +2208,12 @@
     "azure_ai/gpt-5.4-pro-2026-03-05": {
         "cache_read_input_token_cost": 3e-06,
         "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
         "input_cost_per_token": 3e-05,
         "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -2209,6 +2221,8 @@
         "mode": "responses",
         "output_cost_per_token": 0.00018,
         "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
         "supported_endpoints": [
             "/v1/batch",
@@ -2239,13 +2253,22 @@
     },
     "azure_ai/gpt-5.4-mini": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
         "input_cost_per_token": 7.5e-07,
+        "input_cost_per_token_above_272k_tokens": 1.5e-06,
+        "input_cost_per_token_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
+        "output_cost_per_token_above_272k_tokens": 6.75e-06,
+        "output_cost_per_token_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -2277,13 +2300,22 @@
     },
     "azure_ai/gpt-5.4-mini-2026-03-17": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
         "input_cost_per_token": 7.5e-07,
+        "input_cost_per_token_above_272k_tokens": 1.5e-06,
+        "input_cost_per_token_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
+        "output_cost_per_token_above_272k_tokens": 6.75e-06,
+        "output_cost_per_token_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -2315,13 +2347,22 @@
     },
     "azure_ai/gpt-5.4-nano": {
         "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
+        "cache_read_input_token_cost_priority": 4e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-07,
+        "input_cost_per_token_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -2353,13 +2394,22 @@
     },
     "azure_ai/gpt-5.4-nano-2026-03-17": {
         "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
+        "cache_read_input_token_cost_priority": 4e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-07,
+        "input_cost_per_token_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
         "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
         "supported_endpoints": [
             "/v1/chat/completions",