From 18c3118eb63b3c0cbf94183789565c6ef9c53ef1 Mon Sep 17 00:00:00 2001
From: "berriai-litellm-provider-info-sync[bot]"
 <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
Date: Tue, 6 Oct 2026 01:49:46 -0700
Subject: [PATCH] fix(azure): add gpt-6-sol priority processing prices (#44829)

Price-Sync: litellm-providers

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 42 ++++++++++++-------
 model_prices_and_context_window.json          | 42 ++++++++++++-------
 2 files changed, 54 insertions(+), 30 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 5f4b42bc923..64a9aaf8576 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -8480,11 +8480,17 @@
     "azure/gpt-6-sol": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8492,11 +8498,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8529,11 +8533,17 @@
     "azure/gpt-6-sol-2026-09-22": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8541,11 +8551,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -9071,10 +9079,16 @@
         "deprecation_date": "2028-03-11",
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -9082,11 +9096,9 @@
         "mode": "chat",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3.3e-05,
+        "output_cost_per_token_priority": 2.2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 5f4b42bc923..64a9aaf8576 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -8480,11 +8480,17 @@
     "azure/gpt-6-sol": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8492,11 +8498,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -8529,11 +8533,17 @@
     "azure/gpt-6-sol-2026-09-22": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost_priority": 5e-06,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
         "deprecation_date": "2028-03-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
+        "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -8541,11 +8551,9 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -9071,10 +9079,16 @@
         "deprecation_date": "2028-03-11",
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -9082,11 +9096,9 @@
         "mode": "chat",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
-        "search_context_cost_per_query": {
-            "search_context_size_high": 0.01,
-            "search_context_size_low": 0.01,
-            "search_context_size_medium": 0.01
-        },
+        "output_cost_per_token_above_272k_tokens_priority": 3.3e-05,
+        "output_cost_per_token_priority": 2.2e-05,
+        "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01},
         "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
         "supported_endpoints": [
             "/v1/chat/completions",