From 91b965732e871cca03cc287b794e35ab0e7c1083 Mon Sep 17 00:00:00 2001
From: Shivam Rawat <shivam@berri.ai>
Date: Tue, 4 Aug 2026 15:29:10 -0700
Subject: [PATCH] fix(pricing): apply Azure GPT-5.6 Luna and Terra price cuts

Azure matched OpenAI's 7/30 price decreases for GPT-5.6 Luna (-80%) and
Terra (-20%), confirmed by the Microsoft Foundry GA blog. Scale all cost
fields for azure global and us/eu data zone entries accordingly and add
the now-published cache write prices to the global entries.
---
 ...odel_prices_and_context_window_backup.json | 122 +++++++++---------
 model_prices_and_context_window.json          | 122 +++++++++---------
 2 files changed, 124 insertions(+), 120 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 2b8abe9dc3f..45022b379cb 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -6431,23 +6431,24 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-terra": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
-        "cache_read_input_token_cost_priority": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
-        "input_cost_per_token": 2.5e-06,
-        "input_cost_per_token_above_272k_tokens": 5e-06,
-        "input_cost_per_token_priority": 5e-06,
-        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_priority": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_above_272k_tokens": 2.25e-05,
-        "output_cost_per_token_priority": 3e-05,
-        "output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "output_cost_per_token_priority": 2.4e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6476,23 +6477,24 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-luna": {
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "cache_read_input_token_cost_priority": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "input_cost_per_token_priority": 2e-06,
-        "input_cost_per_token_above_272k_tokens_priority": 4e-06,
+        "cache_creation_input_token_cost": 2.5e-07,
+        "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",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_272k_tokens": 9e-06,
-        "output_cost_per_token_priority": 1.2e-05,
-        "output_cost_per_token_above_272k_tokens_priority": 1.8e-05,
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_above_272k_tokens": 1.8e-06,
+        "output_cost_per_token_priority": 2.4e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6605,20 +6607,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-terra": {
-        "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
-        "cache_read_input_token_cost_priority": 6.875e-07,
-        "input_cost_per_token": 2.75e-06,
-        "input_cost_per_token_above_272k_tokens": 5.5e-06,
-        "input_cost_per_token_priority": 6.875e-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_priority": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_priority": 5.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.65e-05,
-        "output_cost_per_token_above_272k_tokens": 2.475e-05,
-        "output_cost_per_token_priority": 4.125e-05,
+        "output_cost_per_token": 1.32e-05,
+        "output_cost_per_token_above_272k_tokens": 1.98e-05,
+        "output_cost_per_token_priority": 3.3e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6647,20 +6649,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-luna": {
-        "cache_read_input_token_cost": 1.1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
-        "cache_read_input_token_cost_priority": 2.75e-07,
-        "input_cost_per_token": 1.1e-06,
-        "input_cost_per_token_above_272k_tokens": 2.2e-06,
-        "input_cost_per_token_priority": 2.75e-06,
+        "cache_read_input_token_cost": 2.2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
+        "cache_read_input_token_cost_priority": 5.5e-08,
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_above_272k_tokens": 4.4e-07,
+        "input_cost_per_token_priority": 5.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-06,
-        "output_cost_per_token_above_272k_tokens": 9.9e-06,
-        "output_cost_per_token_priority": 1.65e-05,
+        "output_cost_per_token": 1.32e-06,
+        "output_cost_per_token_above_272k_tokens": 1.98e-06,
+        "output_cost_per_token_priority": 3.3e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6773,20 +6775,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-terra": {
-        "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
-        "cache_read_input_token_cost_priority": 6.875e-07,
-        "input_cost_per_token": 2.75e-06,
-        "input_cost_per_token_above_272k_tokens": 5.5e-06,
-        "input_cost_per_token_priority": 6.875e-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_priority": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_priority": 5.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.65e-05,
-        "output_cost_per_token_above_272k_tokens": 2.475e-05,
-        "output_cost_per_token_priority": 4.125e-05,
+        "output_cost_per_token": 1.32e-05,
+        "output_cost_per_token_above_272k_tokens": 1.98e-05,
+        "output_cost_per_token_priority": 3.3e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6815,20 +6817,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-luna": {
-        "cache_read_input_token_cost": 1.1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
-        "cache_read_input_token_cost_priority": 2.75e-07,
-        "input_cost_per_token": 1.1e-06,
-        "input_cost_per_token_above_272k_tokens": 2.2e-06,
-        "input_cost_per_token_priority": 2.75e-06,
+        "cache_read_input_token_cost": 2.2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
+        "cache_read_input_token_cost_priority": 5.5e-08,
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_above_272k_tokens": 4.4e-07,
+        "input_cost_per_token_priority": 5.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-06,
-        "output_cost_per_token_above_272k_tokens": 9.9e-06,
-        "output_cost_per_token_priority": 1.65e-05,
+        "output_cost_per_token": 1.32e-06,
+        "output_cost_per_token_above_272k_tokens": 1.98e-06,
+        "output_cost_per_token_priority": 3.3e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 4cfc4206f85..aabb8ac05c9 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -6431,23 +6431,24 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-terra": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
-        "cache_read_input_token_cost_priority": 5e-07,
-        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
-        "input_cost_per_token": 2.5e-06,
-        "input_cost_per_token_above_272k_tokens": 5e-06,
-        "input_cost_per_token_priority": 5e-06,
-        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-07,
+        "cache_read_input_token_cost_priority": 4e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_priority": 4e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_above_272k_tokens": 2.25e-05,
-        "output_cost_per_token_priority": 3e-05,
-        "output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_272k_tokens": 1.8e-05,
+        "output_cost_per_token_priority": 2.4e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6476,23 +6477,24 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-luna": {
-        "cache_read_input_token_cost": 1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2e-07,
-        "cache_read_input_token_cost_priority": 2e-07,
-        "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07,
-        "input_cost_per_token": 1e-06,
-        "input_cost_per_token_above_272k_tokens": 2e-06,
-        "input_cost_per_token_priority": 2e-06,
-        "input_cost_per_token_above_272k_tokens_priority": 4e-06,
+        "cache_creation_input_token_cost": 2.5e-07,
+        "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",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "output_cost_per_token_above_272k_tokens": 9e-06,
-        "output_cost_per_token_priority": 1.2e-05,
-        "output_cost_per_token_above_272k_tokens_priority": 1.8e-05,
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_above_272k_tokens": 1.8e-06,
+        "output_cost_per_token_priority": 2.4e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6605,20 +6607,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-terra": {
-        "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
-        "cache_read_input_token_cost_priority": 6.875e-07,
-        "input_cost_per_token": 2.75e-06,
-        "input_cost_per_token_above_272k_tokens": 5.5e-06,
-        "input_cost_per_token_priority": 6.875e-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_priority": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_priority": 5.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.65e-05,
-        "output_cost_per_token_above_272k_tokens": 2.475e-05,
-        "output_cost_per_token_priority": 4.125e-05,
+        "output_cost_per_token": 1.32e-05,
+        "output_cost_per_token_above_272k_tokens": 1.98e-05,
+        "output_cost_per_token_priority": 3.3e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6647,20 +6649,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-luna": {
-        "cache_read_input_token_cost": 1.1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
-        "cache_read_input_token_cost_priority": 2.75e-07,
-        "input_cost_per_token": 1.1e-06,
-        "input_cost_per_token_above_272k_tokens": 2.2e-06,
-        "input_cost_per_token_priority": 2.75e-06,
+        "cache_read_input_token_cost": 2.2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
+        "cache_read_input_token_cost_priority": 5.5e-08,
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_above_272k_tokens": 4.4e-07,
+        "input_cost_per_token_priority": 5.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-06,
-        "output_cost_per_token_above_272k_tokens": 9.9e-06,
-        "output_cost_per_token_priority": 1.65e-05,
+        "output_cost_per_token": 1.32e-06,
+        "output_cost_per_token_above_272k_tokens": 1.98e-06,
+        "output_cost_per_token_priority": 3.3e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6773,20 +6775,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-terra": {
-        "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
-        "cache_read_input_token_cost_priority": 6.875e-07,
-        "input_cost_per_token": 2.75e-06,
-        "input_cost_per_token_above_272k_tokens": 5.5e-06,
-        "input_cost_per_token_priority": 6.875e-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_priority": 5.5e-07,
+        "input_cost_per_token": 2.2e-06,
+        "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_priority": 5.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.65e-05,
-        "output_cost_per_token_above_272k_tokens": 2.475e-05,
-        "output_cost_per_token_priority": 4.125e-05,
+        "output_cost_per_token": 1.32e-05,
+        "output_cost_per_token_above_272k_tokens": 1.98e-05,
+        "output_cost_per_token_priority": 3.3e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -6815,20 +6817,20 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-luna": {
-        "cache_read_input_token_cost": 1.1e-07,
-        "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
-        "cache_read_input_token_cost_priority": 2.75e-07,
-        "input_cost_per_token": 1.1e-06,
-        "input_cost_per_token_above_272k_tokens": 2.2e-06,
-        "input_cost_per_token_priority": 2.75e-06,
+        "cache_read_input_token_cost": 2.2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
+        "cache_read_input_token_cost_priority": 5.5e-08,
+        "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_above_272k_tokens": 4.4e-07,
+        "input_cost_per_token_priority": 5.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 6.6e-06,
-        "output_cost_per_token_above_272k_tokens": 9.9e-06,
-        "output_cost_per_token_priority": 1.65e-05,
+        "output_cost_per_token": 1.32e-06,
+        "output_cost_per_token_above_272k_tokens": 1.98e-06,
+        "output_cost_per_token_priority": 3.3e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",