From 9456564b3cca8ad0fa3245f297d08fb515128cc5 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Mon, 10 Aug 2026 13:11:55 +0000
Subject: [PATCH 1/7] fix(model_prices): refresh deprecation dates and xAI
 pricing from provider docs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 608 ++++++++++++++----
 model_prices_and_context_window.json          | 390 +++++++++--
 .../llms/xai/test_xai_cost_calculator.py      |  24 +-
 3 files changed, 834 insertions(+), 188 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index d954e33da9c..83185949841 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -2808,6 +2808,7 @@
     },
     "azure/codex-mini": {
         "cache_read_input_token_cost": 3.75e-07,
+        "deprecation_date": "2026-11-15",
         "input_cost_per_token": 1.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -3627,7 +3628,7 @@
         "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/<deployment-name> where deployment-name is your Azure deployment (e.g., azure-model-router)"
     },
     "azure/eu/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.375e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -3644,7 +3645,7 @@
         "supports_vision": true
     },
     "azure/eu/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -3661,6 +3662,7 @@
     },
     "azure/eu/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 1.65e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -3742,6 +3744,7 @@
     },
     "azure/eu/gpt-5-2025-08-07": {
         "cache_read_input_token_cost": 1.375e-07,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -3774,6 +3777,7 @@
     },
     "azure/eu/gpt-5-mini-2025-08-07": {
         "cache_read_input_token_cost": 2.75e-08,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 2.75e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -3840,6 +3844,7 @@
     },
     "azure/eu/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.4e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.38e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -3934,6 +3939,7 @@
     },
     "azure/eu/gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5.5e-09,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 5.5e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -3966,6 +3972,7 @@
     },
     "azure/eu/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-10-21",
         "input_cost_per_token": 1.65e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -4011,6 +4018,7 @@
     },
     "azure/eu/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 1.21e-06,
         "input_cost_per_token_batches": 6.05e-07,
         "litellm_provider": "azure",
@@ -4027,7 +4035,7 @@
     },
     "azure/global-standard/gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.25e-06,
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4044,7 +4052,7 @@
     },
     "azure/global-standard/gpt-4o-2024-11-20": {
         "cache_read_input_token_cost": 1.25e-06,
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4073,7 +4081,7 @@
         "supports_vision": true
     },
     "azure/global/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4090,7 +4098,7 @@
         "supports_vision": true
     },
     "azure/global/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4142,6 +4150,7 @@
     },
     "azure/global/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4476,7 +4485,7 @@
         "supports_web_search": false
     },
     "azure/gpt-4.1-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -4543,7 +4552,7 @@
         "supports_web_search": false
     },
     "azure/gpt-4.1-mini-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1e-07,
         "input_cost_per_token": 4e-07,
         "input_cost_per_token_batches": 2e-07,
@@ -4609,7 +4618,7 @@
         "supports_vision": true
     },
     "azure/gpt-4.1-nano-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2026-10-14",
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -4677,6 +4686,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-05-13": {
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4691,7 +4701,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4708,7 +4718,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -4725,6 +4735,7 @@
         "supports_vision": true
     },
     "azure/gpt-audio-2025-08-28": {
+        "deprecation_date": "2027-03-02",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4756,6 +4767,7 @@
         "supports_vision": false
     },
     "azure/gpt-audio-1.5-2026-02-23": {
+        "deprecation_date": "2027-08-24",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4787,6 +4799,7 @@
         "supports_vision": false
     },
     "azure/gpt-audio-mini-2025-10-06": {
+        "deprecation_date": "2027-04-06",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "azure",
@@ -4866,6 +4879,7 @@
     },
     "azure/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 1.65e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4933,6 +4947,7 @@
     "azure/gpt-realtime-2025-08-28": {
         "cache_creation_input_audio_token_cost": 4e-06,
         "cache_read_input_token_cost": 4e-06,
+        "deprecation_date": "2027-03-02",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -4965,6 +4980,7 @@
     "azure/gpt-realtime-1.5-2026-02-23": {
         "cache_creation_input_audio_token_cost": 4e-06,
         "cache_read_input_token_cost": 4e-06,
+        "deprecation_date": "2027-08-24",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -5102,6 +5118,7 @@
         "supports_tool_choice": true
     },
     "azure/gpt-4o-transcribe": {
+        "deprecation_date": "2026-10-15",
         "input_cost_per_audio_token": 2.5e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -5114,6 +5131,7 @@
         ]
     },
     "azure/gpt-4o-transcribe-diarize": {
+        "deprecation_date": "2027-04-15",
         "input_cost_per_audio_token": 2.5e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -5145,6 +5163,7 @@
     "azure/gpt-5.1-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2027-05-15",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
@@ -5182,6 +5201,7 @@
     "azure/gpt-5.1-chat-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
@@ -5218,6 +5238,7 @@
     "azure/gpt-5.1-codex-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2027-05-15",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
@@ -5251,6 +5272,7 @@
     "azure/gpt-5.1-codex-mini-2025-11-13": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-05-15",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "azure",
@@ -5315,6 +5337,7 @@
     },
     "azure/gpt-5-2025-08-07": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5347,6 +5370,7 @@
     },
     "azure/gpt-5-chat": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -5380,6 +5404,7 @@
     },
     "azure/gpt-5-chat-latest": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -5412,6 +5437,7 @@
     },
     "azure/gpt-5-codex": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2027-03-17",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5474,6 +5500,7 @@
     },
     "azure/gpt-5-mini-2025-08-07": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5538,6 +5565,7 @@
     },
     "azure/gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5e-09,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 5e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5569,6 +5597,7 @@
         "supports_vision": true
     },
     "azure/gpt-5-pro": {
+        "deprecation_date": "2027-04-07",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5633,6 +5662,7 @@
     },
     "azure/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -5697,6 +5727,7 @@
     },
     "azure/gpt-5.1-codex-max": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5791,6 +5822,7 @@
     "azure/gpt-5.2-2025-12-11": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2027-06-08",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5827,6 +5859,7 @@
     "azure/gpt-5.2-chat": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5861,6 +5894,7 @@
     "azure/gpt-5.2-chat-2025-12-11": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-05-13",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5894,6 +5928,7 @@
     },
     "azure/gpt-5.2-codex": {
         "cache_read_input_token_cost": 1.75e-07,
+        "deprecation_date": "2027-07-13",
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5925,6 +5960,7 @@
     "azure/gpt-5.3-chat": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5958,6 +5994,7 @@
     },
     "azure/gpt-5.3-codex": {
         "cache_read_input_token_cost": 1.75e-07,
+        "deprecation_date": "2027-08-24",
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -6164,6 +6201,7 @@
         "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,
+        "deprecation_date": "2027-09-02",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_above_272k_tokens": 5e-06,
         "input_cost_per_token_priority": 5e-06,
@@ -6203,6 +6241,7 @@
     "azure/us/gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.8e-07,
         "cache_read_input_token_cost_priority": 5.5e-07,
+        "deprecation_date": "2027-09-02",
         "input_cost_per_token": 2.75e-06,
         "input_cost_per_token_priority": 5.5e-06,
         "output_cost_per_token": 1.65e-05,
@@ -6238,6 +6277,7 @@
     "azure/eu/gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.8e-07,
         "cache_read_input_token_cost_priority": 5.5e-07,
+        "deprecation_date": "2027-09-02",
         "input_cost_per_token": 2.75e-06,
         "input_cost_per_token_priority": 5.5e-06,
         "output_cost_per_token": 1.65e-05,
@@ -6308,6 +6348,7 @@
     "azure/gpt-5.4-pro-2026-03-05": {
         "cache_read_input_token_cost": 3e-06,
         "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "deprecation_date": "2027-09-07",
         "input_cost_per_token": 3e-05,
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "litellm_provider": "azure",
@@ -6390,6 +6431,7 @@
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
         "cache_read_input_token_cost_priority": 1e-06,
         "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_above_272k_tokens": 1e-05,
         "input_cost_per_token_priority": 1e-05,
@@ -6435,6 +6477,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
         "input_cost_per_token_priority": 4e-06,
@@ -6480,6 +6523,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2e-07,
         "input_cost_per_token_above_272k_tokens": 4e-07,
         "input_cost_per_token_priority": 4e-07,
@@ -6566,6 +6610,7 @@
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
         "cache_read_input_token_cost_priority": 1.375e-06,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
         "input_cost_per_token_priority": 1.375e-05,
@@ -6608,6 +6653,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -6650,6 +6696,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -6734,6 +6781,7 @@
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
         "cache_read_input_token_cost_priority": 1.375e-06,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
         "input_cost_per_token_priority": 1.375e-05,
@@ -6776,6 +6824,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -6818,6 +6867,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -7216,6 +7266,7 @@
     },
     "azure/gpt-5.4-mini-2026-03-17": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2027-09-21",
         "input_cost_per_token": 7.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -7286,6 +7337,7 @@
     },
     "azure/gpt-5.4-nano-2026-03-17": {
         "cache_read_input_token_cost": 2e-08,
+        "deprecation_date": "2027-09-21",
         "input_cost_per_token": 2e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -7321,6 +7373,7 @@
     },
     "azure/gpt-image-1": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
@@ -7432,6 +7485,7 @@
     },
     "azure/gpt-image-1-mini": {
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2027-04-07",
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "azure",
@@ -7456,6 +7510,7 @@
     },
     "azure/gpt-image-1.5-2025-12-16": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2027-06-16",
         "input_cost_per_token": 5e-06,
         "input_cost_per_image_token": 8e-06,
         "litellm_provider": "azure",
@@ -7483,6 +7538,7 @@
     },
     "azure/gpt-image-2-2026-04-21": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2027-10-21",
         "input_cost_per_token": 5e-06,
         "input_cost_per_image_token": 8e-06,
         "litellm_provider": "azure",
@@ -7613,6 +7669,7 @@
     },
     "azure/o1-2024-12-17": {
         "cache_read_input_token_cost": 7.5e-06,
+        "deprecation_date": "2026-10-21",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7718,7 +7775,7 @@
         "supports_vision": true
     },
     "azure/o3-2025-04-16": {
-        "deprecation_date": "2026-04-16",
+        "deprecation_date": "2026-10-21",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "azure",
@@ -7749,6 +7806,7 @@
     },
     "azure/o3-deep-research": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2026-12-26",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7796,6 +7854,7 @@
     },
     "azure/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 5.5e-07,
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7839,6 +7898,7 @@
         "supports_vision": true
     },
     "azure/o3-pro-2025-06-10": {
+        "deprecation_date": "2026-12-17",
         "input_cost_per_token": 2e-05,
         "input_cost_per_token_batches": 1e-05,
         "litellm_provider": "azure",
@@ -7899,6 +7959,7 @@
     },
     "azure/o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 2.75e-07,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7939,6 +8000,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-3-large": {
+        "deprecation_date": "2028-02-09",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -7947,7 +8009,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-3-small": {
-        "deprecation_date": "2026-04-30",
+        "deprecation_date": "2028-02-09",
         "input_cost_per_token": 2e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -7956,6 +8018,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-ada-002": {
+        "deprecation_date": "2028-02-09",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -7987,17 +8050,19 @@
         ]
     },
     "azure/tts-1": {
+        "deprecation_date": "2026-12-15",
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "azure",
         "mode": "audio_speech"
     },
     "azure/tts-1-hd": {
+        "deprecation_date": "2026-12-15",
         "input_cost_per_character": 3e-05,
         "litellm_provider": "azure",
         "mode": "audio_speech"
     },
     "azure/us/gpt-4.1-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 5.5e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_batches": 1.1e-06,
@@ -8031,7 +8096,7 @@
         "supports_web_search": false
     },
     "azure/us/gpt-4.1-mini-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.1e-07,
         "input_cost_per_token": 4.4e-07,
         "input_cost_per_token_batches": 2.2e-07,
@@ -8065,7 +8130,7 @@
         "supports_web_search": false
     },
     "azure/us/gpt-4.1-nano-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2026-10-14",
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 1.1e-07,
         "input_cost_per_token_batches": 6e-08,
@@ -8098,7 +8163,7 @@
         "supports_vision": true
     },
     "azure/us/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.375e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -8115,7 +8180,7 @@
         "supports_vision": true
     },
     "azure/us/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -8132,6 +8197,7 @@
     },
     "azure/us/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 1.65e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -8213,6 +8279,7 @@
     },
     "azure/us/gpt-5-2025-08-07": {
         "cache_read_input_token_cost": 1.375e-07,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8245,6 +8312,7 @@
     },
     "azure/us/gpt-5-mini-2025-08-07": {
         "cache_read_input_token_cost": 2.75e-08,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 2.75e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8277,6 +8345,7 @@
     },
     "azure/us/gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5.5e-09,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 5.5e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8343,6 +8412,7 @@
     },
     "azure/us/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.4e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.38e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -8437,6 +8507,7 @@
     },
     "azure/us/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-10-21",
         "input_cost_per_token": 1.65e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -8481,7 +8552,7 @@
         "supports_vision": false
     },
     "azure/us/o3-2025-04-16": {
-        "deprecation_date": "2026-04-16",
+        "deprecation_date": "2026-10-21",
         "cache_read_input_token_cost": 5.5e-07,
         "input_cost_per_token": 2.2e-06,
         "litellm_provider": "azure",
@@ -8512,6 +8583,7 @@
     },
     "azure/us/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 1.21e-06,
         "input_cost_per_token_batches": 6.05e-07,
         "litellm_provider": "azure",
@@ -8528,6 +8600,7 @@
     },
     "azure/us/o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 3.1e-07,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.21e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -8544,6 +8617,7 @@
         "supports_vision": true
     },
     "azure/whisper-1": {
+        "deprecation_date": "2026-12-15",
         "input_cost_per_second": 0.0001,
         "litellm_provider": "azure",
         "mode": "audio_transcription",
@@ -11396,6 +11470,7 @@
         "output_cost_per_token": 5e-07
     },
     "chatgpt-4o-latest": {
+        "deprecation_date": "2026-02-17",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -11427,6 +11502,7 @@
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_read_input_token_cost": 1e-07,
+        "deprecation_date": "2026-10-15",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11499,6 +11575,7 @@
         "cache_creation_input_token_cost": 3e-07,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-08,
+        "deprecation_date": "2026-04-20",
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11517,7 +11594,7 @@
         "cache_creation_input_token_cost": 1.875e-05,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 1.5e-06,
-        "deprecation_date": "2026-05-01",
+        "deprecation_date": "2026-01-05",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11535,6 +11612,7 @@
     "claude-4-opus-20250514": {
         "cache_creation_input_token_cost": 1.875e-05,
         "cache_read_input_token_cost": 1.5e-06,
+        "deprecation_date": "2026-06-15",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11563,6 +11641,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost": 3e-07,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "deprecation_date": "2026-06-15",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "litellm_provider": "anthropic",
@@ -11627,6 +11706,7 @@
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2026-09-29",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
@@ -11812,7 +11892,7 @@
         "cache_creation_input_token_cost_above_1hr": 3e-05,
         "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
-        "deprecation_date": "2026-05-14",
+        "deprecation_date": "2026-06-15",
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
@@ -11839,6 +11919,7 @@
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-11-24",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -12153,7 +12234,7 @@
         "prompt_cache_min_tokens": 1024
     },
     "claude-sonnet-4-20250514": {
-        "deprecation_date": "2026-05-14",
+        "deprecation_date": "2026-06-15",
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
@@ -12508,6 +12589,7 @@
     },
     "codex-mini-latest": {
         "cache_read_input_token_cost": 3.75e-07,
+        "deprecation_date": "2026-02-12",
         "input_cost_per_token": 1.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -12719,6 +12801,7 @@
         "supports_tool_choice": true
     },
     "computer-use-preview": {
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 8192,
@@ -12746,6 +12829,7 @@
         "supports_vision": true
     },
     "dall-e-2": {
+        "deprecation_date": "2026-05-12",
         "input_cost_per_image": 0.02,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -12756,6 +12840,7 @@
         ]
     },
     "dall-e-3": {
+        "deprecation_date": "2026-05-12",
         "input_cost_per_image": 0.04,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -17281,6 +17366,7 @@
         "output_cost_per_token_batches": 1e-06
     },
     "ft:gpt-3.5-turbo": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "openai",
@@ -17294,6 +17380,7 @@
         "supports_tool_choice": true
     },
     "ft:gpt-3.5-turbo-0125": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -17327,6 +17414,7 @@
         "supports_tool_choice": true
     },
     "ft:gpt-4-0613": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
@@ -17433,6 +17521,7 @@
     },
     "ft:gpt-4.1-nano-2025-04-14": {
         "cache_read_input_token_cost": 5e-08,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 2e-07,
         "input_cost_per_token_batches": 1e-07,
         "litellm_provider": "openai",
@@ -17451,6 +17540,7 @@
     },
     "ft:o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 1e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 4e-06,
         "input_cost_per_token_batches": 2e-06,
         "litellm_provider": "openai",
@@ -17702,6 +17792,46 @@
         "tpm": 8000000,
         "supports_image_size": false
     },
+    "gemini-3-pro-image": {
+        "input_cost_per_image": 0.0011,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.134,
+        "output_cost_per_image_token": 0.00012,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query"
+    },
     "gemini-3-pro-image-preview": {
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
@@ -17742,6 +17872,44 @@
         },
         "web_search_billing_unit": "per_query"
     },
+    "gemini-3.1-flash-image": {
+        "input_cost_per_image": 0.00056,
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0672,
+        "output_cost_per_image_token": 6e-05,
+        "output_cost_per_token": 3e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query"
+    },
     "gemini-3.1-flash-image-preview": {
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
@@ -18847,6 +19015,7 @@
     },
     "gemini/gemini-robotics-er-1.5-preview": {
         "cache_read_input_token_cost": 0,
+        "deprecation_date": "2026-04-30",
         "input_cost_per_token": 3e-07,
         "input_cost_per_audio_token": 1e-06,
         "litellm_provider": "gemini",
@@ -19089,6 +19258,7 @@
         "uses_embed_content": true
     },
     "gemini/gemini-embedding-001": {
+        "deprecation_date": "2026-07-14",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "gemini",
         "max_input_tokens": 2048,
@@ -19101,6 +19271,7 @@
         "tpm": 10000000
     },
     "gemini/gemini-embedding-2-preview": {
+        "deprecation_date": "2026-08-10",
         "input_cost_per_audio_per_second": 0.00016,
         "input_cost_per_image": 0.00012,
         "input_cost_per_token": 2e-07,
@@ -19263,6 +19434,7 @@
     },
     "gemini/gemini-2.5-flash": {
         "cache_read_input_token_cost": 3e-08,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "gemini",
@@ -19310,6 +19482,7 @@
     },
     "gemini/gemini-2.5-flash-image": {
         "cache_read_input_token_cost": 3e-08,
+        "deprecation_date": "2026-10-02",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "gemini",
@@ -19389,7 +19562,6 @@
         ],
         "supports_function_calling": false,
         "supports_prompt_caching": true,
-        "supports_reasoning": false,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_vision": true,
@@ -19399,9 +19571,11 @@
             "search_context_size_medium": 0.014,
             "search_context_size_high": 0.014
         },
-        "web_search_billing_unit": "per_query"
+        "web_search_billing_unit": "per_query",
+        "supports_reasoning": false
     },
     "gemini/gemini-3-pro-image-preview": {
+        "deprecation_date": "2026-06-25",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -19487,6 +19661,7 @@
         "web_search_billing_unit": "per_query"
     },
     "gemini/gemini-3.1-flash-image-preview": {
+        "deprecation_date": "2026-06-25",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
         "litellm_provider": "gemini",
@@ -19571,6 +19746,7 @@
     },
     "gemini/gemini-2.5-flash-lite": {
         "cache_read_input_token_cost": 1e-08,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -19618,6 +19794,7 @@
     },
     "gemini/gemini-2.5-flash-lite-preview-09-2025": {
         "cache_read_input_token_cost": 1e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -19865,6 +20042,7 @@
     "gemini/gemini-2.5-pro": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "input_cost_per_token_priority": 1.25e-06,
@@ -19999,6 +20177,7 @@
     },
     "gemini/gemini-3.1-flash-lite-preview": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-05-25",
         "input_cost_per_audio_token": 5e-07,
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "gemini",
@@ -20051,6 +20230,7 @@
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-05-07",
         "input_cost_per_audio_token": 5e-07,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
@@ -20818,18 +20998,21 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini/imagen-4.0-fast-generate-001": {
+        "deprecation_date": "2026-08-17",
         "litellm_provider": "gemini",
         "mode": "image_generation",
         "output_cost_per_image": 0.02,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini/imagen-4.0-generate-001": {
+        "deprecation_date": "2026-08-17",
         "litellm_provider": "gemini",
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini/imagen-4.0-ultra-generate-001": {
+        "deprecation_date": "2026-08-17",
         "litellm_provider": "gemini",
         "mode": "image_generation",
         "output_cost_per_image": 0.06,
@@ -20913,6 +21096,7 @@
         "supports_web_search": false
     },
     "gemini/veo-2.0-generate-001": {
+        "deprecation_date": "2026-06-30",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -21004,8 +21188,7 @@
         "max_tokens": 16000,
         "mode": "chat",
         "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/messages"
+            "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -21018,8 +21201,7 @@
         "max_tokens": 16000,
         "mode": "chat",
         "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/messages"
+            "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -21071,8 +21253,7 @@
         "max_tokens": 16000,
         "mode": "chat",
         "supported_endpoints": [
-            "/v1/chat/completions",
-            "/v1/messages"
+            "/v1/chat/completions"
         ],
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -21950,6 +22131,7 @@
         "supports_vision": true
     },
     "gpt-3.5-turbo": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -21963,6 +22145,7 @@
         "supports_tool_choice": true
     },
     "gpt-3.5-turbo-0125": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -22022,6 +22205,7 @@
         "output_cost_per_token": 2e-06
     },
     "gpt-4": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
@@ -22062,7 +22246,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-0613": {
-        "deprecation_date": "2025-06-06",
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
@@ -22076,7 +22260,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-1106-preview": {
-        "deprecation_date": "2026-03-26",
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -22091,6 +22275,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-turbo": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -22107,6 +22292,7 @@
         "supports_vision": true
     },
     "gpt-4-turbo-2024-04-09": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -22288,6 +22474,7 @@
     "gpt-4.1-nano": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 5e-08,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_batches": 5e-08,
         "input_cost_per_token_priority": 2e-07,
@@ -22324,6 +22511,7 @@
     "gpt-4.1-nano-2025-04-14": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 5e-08,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_priority": 2e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -22381,6 +22569,7 @@
         "supports_vision": true
     },
     "gpt-4o-2024-05-13": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_batches": 2.5e-06,
         "input_cost_per_token_priority": 8.75e-06,
@@ -22447,6 +22636,7 @@
         "supports_vision": true
     },
     "gpt-4o-audio-preview": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22464,6 +22654,7 @@
         "supports_tool_choice": true
     },
     "gpt-4o-audio-preview-2024-12-17": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22481,6 +22672,7 @@
         "supports_tool_choice": true
     },
     "gpt-4o-audio-preview-2025-06-03": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22498,6 +22690,7 @@
         "supports_tool_choice": true
     },
     "gpt-audio": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22567,6 +22760,7 @@
         "supports_vision": false
     },
     "gpt-audio-2025-08-28": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22603,6 +22797,7 @@
         "supports_vision": false
     },
     "gpt-audio-mini": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22639,6 +22834,7 @@
         "supports_vision": false
     },
     "gpt-audio-mini-2025-10-06": {
+        "deprecation_date": "2026-07-23",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22762,6 +22958,7 @@
         "supports_vision": true
     },
     "gpt-4o-mini-audio-preview": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "openai",
@@ -22779,6 +22976,7 @@
         "supports_tool_choice": true
     },
     "gpt-4o-mini-audio-preview-2024-12-17": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "openai",
@@ -22798,6 +22996,7 @@
     "gpt-4o-mini-realtime-preview": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22817,6 +23016,7 @@
     "gpt-4o-mini-realtime-preview-2024-12-17": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22861,6 +23061,7 @@
     },
     "gpt-4o-mini-search-preview-2025-03-11": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_batches": 7.5e-08,
         "litellm_provider": "openai",
@@ -22911,6 +23112,7 @@
     },
     "gpt-4o-realtime-preview": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -22929,6 +23131,7 @@
     },
     "gpt-4o-realtime-preview-2024-12-17": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -22947,6 +23150,7 @@
     },
     "gpt-4o-realtime-preview-2025-06-03": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -22991,6 +23195,7 @@
     },
     "gpt-4o-search-preview-2025-03-11": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_batches": 1.25e-06,
         "litellm_provider": "openai",
@@ -23023,6 +23228,7 @@
     },
     "gpt-image-1.5": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -23037,6 +23243,7 @@
     },
     "gpt-image-1.5-2025-12-16": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -23532,6 +23739,7 @@
     "gpt-5.1-chat-latest": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -23651,6 +23859,7 @@
     "gpt-5.2-chat-latest": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-08-10",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -23689,6 +23898,7 @@
     "gpt-5.3-chat-latest": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-08-10",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -24571,9 +24781,9 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 272000,
-        "max_tokens": 272000,
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -24604,12 +24814,13 @@
         "supports_minimal_reasoning_effort": true
     },
     "gpt-5-pro-2025-10-06": {
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 272000,
-        "max_tokens": 272000,
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -24643,6 +24854,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
@@ -24718,6 +24930,7 @@
     },
     "gpt-5-chat-latest": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -24753,6 +24966,7 @@
     },
     "gpt-5-codex": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
@@ -24788,6 +25002,7 @@
     "gpt-5.1-codex": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -24824,6 +25039,7 @@
     },
     "gpt-5.1-codex-max": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
@@ -24859,6 +25075,7 @@
     "gpt-5.1-codex-mini": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
@@ -24896,6 +25113,7 @@
     "gpt-5.2-codex": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -25013,6 +25231,7 @@
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
@@ -25094,6 +25313,7 @@
     "gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5e-09,
         "cache_read_input_token_cost_flex": 2.5e-09,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "input_cost_per_token_flex": 2.5e-08,
@@ -25133,6 +25353,7 @@
     },
     "gpt-image-1": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -25145,6 +25366,7 @@
     },
     "gpt-image-1-mini": {
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "openai",
@@ -25158,6 +25380,7 @@
     "gpt-realtime": {
         "cache_creation_input_audio_token_cost": 4e-07,
         "cache_read_input_token_cost": 4e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -25324,6 +25547,7 @@
     "gpt-realtime-mini": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -25355,6 +25579,7 @@
     "gpt-realtime-2025-08-28": {
         "cache_creation_input_audio_token_cost": 4e-07,
         "cache_read_input_token_cost": 4e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -29183,6 +29408,7 @@
     },
     "o1": {
         "cache_read_input_token_cost": 7.5e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29202,6 +29428,7 @@
     },
     "o1-2024-12-17": {
         "cache_read_input_token_cost": 7.5e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29220,6 +29447,7 @@
         "supports_vision": true
     },
     "o1-pro": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 0.00015,
         "input_cost_per_token_batches": 7.5e-05,
         "litellm_provider": "openai",
@@ -29252,6 +29480,7 @@
         "supports_vision": true
     },
     "o1-pro-2025-03-19": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 0.00015,
         "input_cost_per_token_batches": 7.5e-05,
         "litellm_provider": "openai",
@@ -29325,6 +29554,7 @@
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 8.75e-07,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 3.5e-06,
@@ -29361,6 +29591,7 @@
     },
     "o3-deep-research": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_batches": 5e-06,
         "litellm_provider": "openai",
@@ -29395,6 +29626,7 @@
     },
     "o3-deep-research-2025-06-26": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_batches": 5e-06,
         "litellm_provider": "openai",
@@ -29429,6 +29661,7 @@
     },
     "o3-mini": {
         "cache_read_input_token_cost": 5.5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29446,6 +29679,7 @@
     },
     "o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 5.5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29493,6 +29727,7 @@
         "supports_web_search": true
     },
     "o3-pro-2025-06-10": {
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2e-05,
         "input_cost_per_token_batches": 1e-05,
         "litellm_provider": "openai",
@@ -29527,6 +29762,7 @@
         "cache_read_input_token_cost": 2.75e-07,
         "cache_read_input_token_cost_flex": 1.375e-07,
         "cache_read_input_token_cost_priority": 5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
@@ -29552,6 +29788,7 @@
         "cache_read_input_token_cost": 2.75e-07,
         "cache_read_input_token_cost_flex": 1.375e-07,
         "cache_read_input_token_cost_priority": 5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
@@ -29575,6 +29812,7 @@
     },
     "o4-mini-deep-research": {
         "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
@@ -29609,6 +29847,7 @@
     },
     "o4-mini-deep-research-2025-06-26": {
         "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
@@ -32000,6 +32239,22 @@
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
+    "openrouter/z-ai/glm-5.1": {
+        "input_cost_per_token": 1.05e-06,
+        "output_cost_per_token": 3.5e-06,
+        "cache_read_input_token_cost": 5.25e-07,
+        "cache_creation_input_token_cost": 0.0,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 202752,
+        "max_output_tokens": 65535,
+        "max_tokens": 65535,
+        "mode": "chat",
+        "source": "https://openrouter.ai/z-ai/glm-5.1",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "openrouter/minimax/minimax-m2.1": {
         "input_cost_per_token": 2.7e-07,
         "output_cost_per_token": 1.2e-06,
@@ -39994,69 +40249,86 @@
     },
     "xai/grok-4.20-multi-agent-beta-0309": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
     },
     "xai/grok-4.20-beta-0309-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
     },
     "xai/grok-4.20-0309-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
     },
     "xai/grok-4.20-beta-0309-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
     },
     "xai/grok-4.3": {
         "cache_read_input_token_cost": 2e-07,
@@ -40101,8 +40373,8 @@
         "supports_web_search": true
     },
     "xai/grok-4.5": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
         "litellm_provider": "xai",
@@ -40122,8 +40394,8 @@
         "supports_web_search": true
     },
     "xai/grok-4.5-latest": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
         "litellm_provider": "xai",
@@ -40156,51 +40428,64 @@
         "supports_web_search": true
     },
     "xai/grok-code-fast": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 2e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     },
     "xai/grok-code-fast-1": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 2e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "deprecation_date": "2026-05-15"
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     },
     "xai/grok-code-fast-1-0825": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 2e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "deprecation_date": "2026-05-15"
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     },
     "xai/grok-vision-beta": {
         "input_cost_per_image": 5e-06,
@@ -40273,6 +40558,21 @@
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
+    "zai/glm-5.1": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 2.6e-07,
+        "input_cost_per_token": 1.4e-06,
+        "output_cost_per_token": 4.4e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
     "zai/glm-5-code": {
         "cache_creation_input_token_cost": 0,
         "cache_read_input_token_cost": 3e-07,
@@ -40303,6 +40603,21 @@
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
+    "zai/glm-4.7-flash": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
     "zai/glm-4.6": {
         "cache_creation_input_token_cost": 0,
         "cache_read_input_token_cost": 1.1e-07,
@@ -40407,6 +40722,7 @@
         "mode": "chat"
     },
     "openai/sora-2": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
@@ -40420,6 +40736,7 @@
         ]
     },
     "openai/sora-2-pro": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.3,
@@ -44374,6 +44691,7 @@
         ]
     },
     "gpt-4o-mini-transcribe-2025-03-20": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
@@ -44444,6 +44762,7 @@
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 6e-08,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_image": 8e-07,
         "input_cost_per_token": 6e-07,
@@ -44524,6 +44843,7 @@
         "supports_audio_input": true
     },
     "sora-2": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
@@ -44537,6 +44857,7 @@
         ]
     },
     "sora-2-pro": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.3,
@@ -44564,6 +44885,7 @@
     },
     "chatgpt-image-latest": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -45714,6 +46036,7 @@
         "supports_response_schema": true
     },
     "snowflake/claude-sonnet-4-6": {
+        "supports_adaptive_thinking": true,
         "max_tokens": 16384,
         "max_input_tokens": 200000,
         "max_output_tokens": 16384,
@@ -46135,40 +46458,6 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
-    "darkbloom/gemma-4-26b": {
-        "input_cost_per_token": 3e-08,
-        "litellm_provider": "darkbloom",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 1.65e-07,
-        "source": "https://www.darkbloom.dev/",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_native_streaming": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true
-    },
-    "darkbloom/gpt-oss-20b": {
-        "input_cost_per_token": 1.45e-08,
-        "litellm_provider": "darkbloom",
-        "max_input_tokens": 131072,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
-        "mode": "chat",
-        "output_cost_per_token": 7e-08,
-        "source": "https://www.darkbloom.dev/",
-        "supported_endpoints": [
-            "/v1/chat/completions"
-        ],
-        "supports_function_calling": true,
-        "supports_native_streaming": true,
-        "supports_system_messages": true,
-        "supports_tool_choice": true
-    },
     "deepseek/deepseek-v4-pro": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 3.625e-09,
@@ -46325,6 +46614,40 @@
         "supports_reasoning": false,
         "source": "https://pinstripes.io/pricing"
     },
+    "darkbloom/gemma-4-26b": {
+        "input_cost_per_token": 3e-08,
+        "litellm_provider": "darkbloom",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-07,
+        "source": "https://www.darkbloom.dev/",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "darkbloom/gpt-oss-20b": {
+        "input_cost_per_token": 1.45e-08,
+        "litellm_provider": "darkbloom",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 7e-08,
+        "source": "https://www.darkbloom.dev/",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
     "fallback_generalizations": {
         "rules": [
             {
@@ -46381,5 +46704,66 @@
                 }
             }
         ]
+    },
+    "xai/grok-4.20-0309-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
+    },
+    "xai/grok-4.20-multi-agent-0309": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
+    },
+    "xai/grok-build-0.1": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     }
 }
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 8982b4f2565..83185949841 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -2808,6 +2808,7 @@
     },
     "azure/codex-mini": {
         "cache_read_input_token_cost": 3.75e-07,
+        "deprecation_date": "2026-11-15",
         "input_cost_per_token": 1.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -3627,7 +3628,7 @@
         "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/<deployment-name> where deployment-name is your Azure deployment (e.g., azure-model-router)"
     },
     "azure/eu/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.375e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -3644,7 +3645,7 @@
         "supports_vision": true
     },
     "azure/eu/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -3661,6 +3662,7 @@
     },
     "azure/eu/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 1.65e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -3742,6 +3744,7 @@
     },
     "azure/eu/gpt-5-2025-08-07": {
         "cache_read_input_token_cost": 1.375e-07,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -3774,6 +3777,7 @@
     },
     "azure/eu/gpt-5-mini-2025-08-07": {
         "cache_read_input_token_cost": 2.75e-08,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 2.75e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -3840,6 +3844,7 @@
     },
     "azure/eu/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.4e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.38e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -3934,6 +3939,7 @@
     },
     "azure/eu/gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5.5e-09,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 5.5e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -3966,6 +3972,7 @@
     },
     "azure/eu/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-10-21",
         "input_cost_per_token": 1.65e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -4011,6 +4018,7 @@
     },
     "azure/eu/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 1.21e-06,
         "input_cost_per_token_batches": 6.05e-07,
         "litellm_provider": "azure",
@@ -4027,7 +4035,7 @@
     },
     "azure/global-standard/gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.25e-06,
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4044,7 +4052,7 @@
     },
     "azure/global-standard/gpt-4o-2024-11-20": {
         "cache_read_input_token_cost": 1.25e-06,
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4073,7 +4081,7 @@
         "supports_vision": true
     },
     "azure/global/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4090,7 +4098,7 @@
         "supports_vision": true
     },
     "azure/global/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4142,6 +4150,7 @@
     },
     "azure/global/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4476,7 +4485,7 @@
         "supports_web_search": false
     },
     "azure/gpt-4.1-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -4543,7 +4552,7 @@
         "supports_web_search": false
     },
     "azure/gpt-4.1-mini-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1e-07,
         "input_cost_per_token": 4e-07,
         "input_cost_per_token_batches": 2e-07,
@@ -4609,7 +4618,7 @@
         "supports_vision": true
     },
     "azure/gpt-4.1-nano-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2026-10-14",
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -4677,6 +4686,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-05-13": {
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4691,7 +4701,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4708,7 +4718,7 @@
         "supports_vision": true
     },
     "azure/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -4725,6 +4735,7 @@
         "supports_vision": true
     },
     "azure/gpt-audio-2025-08-28": {
+        "deprecation_date": "2027-03-02",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4756,6 +4767,7 @@
         "supports_vision": false
     },
     "azure/gpt-audio-1.5-2026-02-23": {
+        "deprecation_date": "2027-08-24",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -4787,6 +4799,7 @@
         "supports_vision": false
     },
     "azure/gpt-audio-mini-2025-10-06": {
+        "deprecation_date": "2027-04-06",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "azure",
@@ -4866,6 +4879,7 @@
     },
     "azure/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 1.65e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -4933,6 +4947,7 @@
     "azure/gpt-realtime-2025-08-28": {
         "cache_creation_input_audio_token_cost": 4e-06,
         "cache_read_input_token_cost": 4e-06,
+        "deprecation_date": "2027-03-02",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -4965,6 +4980,7 @@
     "azure/gpt-realtime-1.5-2026-02-23": {
         "cache_creation_input_audio_token_cost": 4e-06,
         "cache_read_input_token_cost": 4e-06,
+        "deprecation_date": "2027-08-24",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -5102,6 +5118,7 @@
         "supports_tool_choice": true
     },
     "azure/gpt-4o-transcribe": {
+        "deprecation_date": "2026-10-15",
         "input_cost_per_audio_token": 2.5e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -5114,6 +5131,7 @@
         ]
     },
     "azure/gpt-4o-transcribe-diarize": {
+        "deprecation_date": "2027-04-15",
         "input_cost_per_audio_token": 2.5e-06,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "azure",
@@ -5145,6 +5163,7 @@
     "azure/gpt-5.1-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2027-05-15",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
@@ -5182,6 +5201,7 @@
     "azure/gpt-5.1-chat-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
@@ -5218,6 +5238,7 @@
     "azure/gpt-5.1-codex-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2027-05-15",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
@@ -5251,6 +5272,7 @@
     "azure/gpt-5.1-codex-mini-2025-11-13": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-05-15",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "azure",
@@ -5315,6 +5337,7 @@
     },
     "azure/gpt-5-2025-08-07": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5347,6 +5370,7 @@
     },
     "azure/gpt-5-chat": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -5380,6 +5404,7 @@
     },
     "azure/gpt-5-chat-latest": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -5412,6 +5437,7 @@
     },
     "azure/gpt-5-codex": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2027-03-17",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5474,6 +5500,7 @@
     },
     "azure/gpt-5-mini-2025-08-07": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5538,6 +5565,7 @@
     },
     "azure/gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5e-09,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 5e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5569,6 +5597,7 @@
         "supports_vision": true
     },
     "azure/gpt-5-pro": {
+        "deprecation_date": "2027-04-07",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5633,6 +5662,7 @@
     },
     "azure/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -5697,6 +5727,7 @@
     },
     "azure/gpt-5.1-codex-max": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2027-05-18",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5791,6 +5822,7 @@
     "azure/gpt-5.2-2025-12-11": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2027-06-08",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5827,6 +5859,7 @@
     "azure/gpt-5.2-chat": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5861,6 +5894,7 @@
     "azure/gpt-5.2-chat-2025-12-11": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-05-13",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5894,6 +5928,7 @@
     },
     "azure/gpt-5.2-codex": {
         "cache_read_input_token_cost": 1.75e-07,
+        "deprecation_date": "2027-07-13",
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -5925,6 +5960,7 @@
     "azure/gpt-5.3-chat": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
@@ -5958,6 +5994,7 @@
     },
     "azure/gpt-5.3-codex": {
         "cache_read_input_token_cost": 1.75e-07,
+        "deprecation_date": "2027-08-24",
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -6164,6 +6201,7 @@
         "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,
+        "deprecation_date": "2027-09-02",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_above_272k_tokens": 5e-06,
         "input_cost_per_token_priority": 5e-06,
@@ -6203,6 +6241,7 @@
     "azure/us/gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.8e-07,
         "cache_read_input_token_cost_priority": 5.5e-07,
+        "deprecation_date": "2027-09-02",
         "input_cost_per_token": 2.75e-06,
         "input_cost_per_token_priority": 5.5e-06,
         "output_cost_per_token": 1.65e-05,
@@ -6238,6 +6277,7 @@
     "azure/eu/gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.8e-07,
         "cache_read_input_token_cost_priority": 5.5e-07,
+        "deprecation_date": "2027-09-02",
         "input_cost_per_token": 2.75e-06,
         "input_cost_per_token_priority": 5.5e-06,
         "output_cost_per_token": 1.65e-05,
@@ -6308,6 +6348,7 @@
     "azure/gpt-5.4-pro-2026-03-05": {
         "cache_read_input_token_cost": 3e-06,
         "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "deprecation_date": "2027-09-07",
         "input_cost_per_token": 3e-05,
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "litellm_provider": "azure",
@@ -6390,6 +6431,7 @@
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
         "cache_read_input_token_cost_priority": 1e-06,
         "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_above_272k_tokens": 1e-05,
         "input_cost_per_token_priority": 1e-05,
@@ -6435,6 +6477,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
         "input_cost_per_token_priority": 4e-06,
@@ -6480,6 +6523,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2e-07,
         "input_cost_per_token_above_272k_tokens": 4e-07,
         "input_cost_per_token_priority": 4e-07,
@@ -6566,6 +6610,7 @@
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
         "cache_read_input_token_cost_priority": 1.375e-06,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
         "input_cost_per_token_priority": 1.375e-05,
@@ -6608,6 +6653,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -6650,6 +6696,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -6734,6 +6781,7 @@
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
         "cache_read_input_token_cost_priority": 1.375e-06,
+        "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
         "input_cost_per_token_priority": 1.375e-05,
@@ -6776,6 +6824,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -6818,6 +6867,7 @@
         "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,
+        "deprecation_date": "2028-01-11",
         "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,
@@ -7216,6 +7266,7 @@
     },
     "azure/gpt-5.4-mini-2026-03-17": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2027-09-21",
         "input_cost_per_token": 7.5e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -7286,6 +7337,7 @@
     },
     "azure/gpt-5.4-nano-2026-03-17": {
         "cache_read_input_token_cost": 2e-08,
+        "deprecation_date": "2027-09-21",
         "input_cost_per_token": 2e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -7321,6 +7373,7 @@
     },
     "azure/gpt-image-1": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure",
@@ -7432,6 +7485,7 @@
     },
     "azure/gpt-image-1-mini": {
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2027-04-07",
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "azure",
@@ -7456,6 +7510,7 @@
     },
     "azure/gpt-image-1.5-2025-12-16": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2027-06-16",
         "input_cost_per_token": 5e-06,
         "input_cost_per_image_token": 8e-06,
         "litellm_provider": "azure",
@@ -7483,6 +7538,7 @@
     },
     "azure/gpt-image-2-2026-04-21": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2027-10-21",
         "input_cost_per_token": 5e-06,
         "input_cost_per_image_token": 8e-06,
         "litellm_provider": "azure",
@@ -7613,6 +7669,7 @@
     },
     "azure/o1-2024-12-17": {
         "cache_read_input_token_cost": 7.5e-06,
+        "deprecation_date": "2026-10-21",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7718,7 +7775,7 @@
         "supports_vision": true
     },
     "azure/o3-2025-04-16": {
-        "deprecation_date": "2026-04-16",
+        "deprecation_date": "2026-10-21",
         "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "azure",
@@ -7749,6 +7806,7 @@
     },
     "azure/o3-deep-research": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2026-12-26",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7796,6 +7854,7 @@
     },
     "azure/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 5.5e-07,
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7839,6 +7898,7 @@
         "supports_vision": true
     },
     "azure/o3-pro-2025-06-10": {
+        "deprecation_date": "2026-12-17",
         "input_cost_per_token": 2e-05,
         "input_cost_per_token_batches": 1e-05,
         "litellm_provider": "azure",
@@ -7899,6 +7959,7 @@
     },
     "azure/o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 2.75e-07,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -7939,6 +8000,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-3-large": {
+        "deprecation_date": "2028-02-09",
         "input_cost_per_token": 1.3e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -7947,7 +8009,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-3-small": {
-        "deprecation_date": "2026-04-30",
+        "deprecation_date": "2028-02-09",
         "input_cost_per_token": 2e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -7956,6 +8018,7 @@
         "output_cost_per_token": 0.0
     },
     "azure/text-embedding-ada-002": {
+        "deprecation_date": "2028-02-09",
         "input_cost_per_token": 1e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 8191,
@@ -7987,17 +8050,19 @@
         ]
     },
     "azure/tts-1": {
+        "deprecation_date": "2026-12-15",
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "azure",
         "mode": "audio_speech"
     },
     "azure/tts-1-hd": {
+        "deprecation_date": "2026-12-15",
         "input_cost_per_character": 3e-05,
         "litellm_provider": "azure",
         "mode": "audio_speech"
     },
     "azure/us/gpt-4.1-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 5.5e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_batches": 1.1e-06,
@@ -8031,7 +8096,7 @@
         "supports_web_search": false
     },
     "azure/us/gpt-4.1-mini-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.1e-07,
         "input_cost_per_token": 4.4e-07,
         "input_cost_per_token_batches": 2.2e-07,
@@ -8065,7 +8130,7 @@
         "supports_web_search": false
     },
     "azure/us/gpt-4.1-nano-2025-04-14": {
-        "deprecation_date": "2026-11-04",
+        "deprecation_date": "2026-10-14",
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 1.1e-07,
         "input_cost_per_token_batches": 6e-08,
@@ -8098,7 +8163,7 @@
         "supports_vision": true
     },
     "azure/us/gpt-4o-2024-08-06": {
-        "deprecation_date": "2026-02-27",
+        "deprecation_date": "2027-04-14",
         "cache_read_input_token_cost": 1.375e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -8115,7 +8180,7 @@
         "supports_vision": true
     },
     "azure/us/gpt-4o-2024-11-20": {
-        "deprecation_date": "2026-03-01",
+        "deprecation_date": "2027-04-14",
         "cache_creation_input_token_cost": 1.38e-06,
         "input_cost_per_token": 2.75e-06,
         "litellm_provider": "azure",
@@ -8132,6 +8197,7 @@
     },
     "azure/us/gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 8.3e-08,
+        "deprecation_date": "2027-04-14",
         "input_cost_per_token": 1.65e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -8213,6 +8279,7 @@
     },
     "azure/us/gpt-5-2025-08-07": {
         "cache_read_input_token_cost": 1.375e-07,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 1.375e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8245,6 +8312,7 @@
     },
     "azure/us/gpt-5-mini-2025-08-07": {
         "cache_read_input_token_cost": 2.75e-08,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 2.75e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8277,6 +8345,7 @@
     },
     "azure/us/gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5.5e-09,
+        "deprecation_date": "2027-02-09",
         "input_cost_per_token": 5.5e-08,
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
@@ -8343,6 +8412,7 @@
     },
     "azure/us/gpt-5.1-chat": {
         "cache_read_input_token_cost": 1.4e-07,
+        "deprecation_date": "2026-06-29",
         "input_cost_per_token": 1.38e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 128000,
@@ -8437,6 +8507,7 @@
     },
     "azure/us/o1-2024-12-17": {
         "cache_read_input_token_cost": 8.25e-06,
+        "deprecation_date": "2026-10-21",
         "input_cost_per_token": 1.65e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -8481,7 +8552,7 @@
         "supports_vision": false
     },
     "azure/us/o3-2025-04-16": {
-        "deprecation_date": "2026-04-16",
+        "deprecation_date": "2026-10-21",
         "cache_read_input_token_cost": 5.5e-07,
         "input_cost_per_token": 2.2e-06,
         "litellm_provider": "azure",
@@ -8512,6 +8583,7 @@
     },
     "azure/us/o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 6.05e-07,
+        "deprecation_date": "2026-10-01",
         "input_cost_per_token": 1.21e-06,
         "input_cost_per_token_batches": 6.05e-07,
         "litellm_provider": "azure",
@@ -8528,6 +8600,7 @@
     },
     "azure/us/o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 3.1e-07,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.21e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 200000,
@@ -8544,6 +8617,7 @@
         "supports_vision": true
     },
     "azure/whisper-1": {
+        "deprecation_date": "2026-12-15",
         "input_cost_per_second": 0.0001,
         "litellm_provider": "azure",
         "mode": "audio_transcription",
@@ -11396,6 +11470,7 @@
         "output_cost_per_token": 5e-07
     },
     "chatgpt-4o-latest": {
+        "deprecation_date": "2026-02-17",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -11427,6 +11502,7 @@
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_read_input_token_cost": 1e-07,
+        "deprecation_date": "2026-10-15",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11499,6 +11575,7 @@
         "cache_creation_input_token_cost": 3e-07,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-08,
+        "deprecation_date": "2026-04-20",
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11517,7 +11594,7 @@
         "cache_creation_input_token_cost": 1.875e-05,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 1.5e-06,
-        "deprecation_date": "2026-05-01",
+        "deprecation_date": "2026-01-05",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11535,6 +11612,7 @@
     "claude-4-opus-20250514": {
         "cache_creation_input_token_cost": 1.875e-05,
         "cache_read_input_token_cost": 1.5e-06,
+        "deprecation_date": "2026-06-15",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11563,6 +11641,7 @@
         "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
         "cache_read_input_token_cost": 3e-07,
         "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+        "deprecation_date": "2026-06-15",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "litellm_provider": "anthropic",
@@ -11627,6 +11706,7 @@
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2026-09-29",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
@@ -11812,7 +11892,7 @@
         "cache_creation_input_token_cost_above_1hr": 3e-05,
         "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
-        "deprecation_date": "2026-05-14",
+        "deprecation_date": "2026-06-15",
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
@@ -11839,6 +11919,7 @@
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-11-24",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -12153,7 +12234,7 @@
         "prompt_cache_min_tokens": 1024
     },
     "claude-sonnet-4-20250514": {
-        "deprecation_date": "2026-05-14",
+        "deprecation_date": "2026-06-15",
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_read_input_token_cost": 3e-07,
@@ -12508,6 +12589,7 @@
     },
     "codex-mini-latest": {
         "cache_read_input_token_cost": 3.75e-07,
+        "deprecation_date": "2026-02-12",
         "input_cost_per_token": 1.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -12719,6 +12801,7 @@
         "supports_tool_choice": true
     },
     "computer-use-preview": {
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 8192,
@@ -12746,6 +12829,7 @@
         "supports_vision": true
     },
     "dall-e-2": {
+        "deprecation_date": "2026-05-12",
         "input_cost_per_image": 0.02,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -12756,6 +12840,7 @@
         ]
     },
     "dall-e-3": {
+        "deprecation_date": "2026-05-12",
         "input_cost_per_image": 0.04,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -17281,6 +17366,7 @@
         "output_cost_per_token_batches": 1e-06
     },
     "ft:gpt-3.5-turbo": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_batches": 1.5e-06,
         "litellm_provider": "openai",
@@ -17294,6 +17380,7 @@
         "supports_tool_choice": true
     },
     "ft:gpt-3.5-turbo-0125": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -17327,6 +17414,7 @@
         "supports_tool_choice": true
     },
     "ft:gpt-4-0613": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
@@ -17433,6 +17521,7 @@
     },
     "ft:gpt-4.1-nano-2025-04-14": {
         "cache_read_input_token_cost": 5e-08,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 2e-07,
         "input_cost_per_token_batches": 1e-07,
         "litellm_provider": "openai",
@@ -17451,6 +17540,7 @@
     },
     "ft:o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 1e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 4e-06,
         "input_cost_per_token_batches": 2e-06,
         "litellm_provider": "openai",
@@ -18925,6 +19015,7 @@
     },
     "gemini/gemini-robotics-er-1.5-preview": {
         "cache_read_input_token_cost": 0,
+        "deprecation_date": "2026-04-30",
         "input_cost_per_token": 3e-07,
         "input_cost_per_audio_token": 1e-06,
         "litellm_provider": "gemini",
@@ -19167,6 +19258,7 @@
         "uses_embed_content": true
     },
     "gemini/gemini-embedding-001": {
+        "deprecation_date": "2026-07-14",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "gemini",
         "max_input_tokens": 2048,
@@ -19179,6 +19271,7 @@
         "tpm": 10000000
     },
     "gemini/gemini-embedding-2-preview": {
+        "deprecation_date": "2026-08-10",
         "input_cost_per_audio_per_second": 0.00016,
         "input_cost_per_image": 0.00012,
         "input_cost_per_token": 2e-07,
@@ -19341,6 +19434,7 @@
     },
     "gemini/gemini-2.5-flash": {
         "cache_read_input_token_cost": 3e-08,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "gemini",
@@ -19388,6 +19482,7 @@
     },
     "gemini/gemini-2.5-flash-image": {
         "cache_read_input_token_cost": 3e-08,
+        "deprecation_date": "2026-10-02",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "gemini",
@@ -19480,6 +19575,7 @@
         "supports_reasoning": false
     },
     "gemini/gemini-3-pro-image-preview": {
+        "deprecation_date": "2026-06-25",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -19565,6 +19661,7 @@
         "web_search_billing_unit": "per_query"
     },
     "gemini/gemini-3.1-flash-image-preview": {
+        "deprecation_date": "2026-06-25",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
         "litellm_provider": "gemini",
@@ -19649,6 +19746,7 @@
     },
     "gemini/gemini-2.5-flash-lite": {
         "cache_read_input_token_cost": 1e-08,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -19696,6 +19794,7 @@
     },
     "gemini/gemini-2.5-flash-lite-preview-09-2025": {
         "cache_read_input_token_cost": 1e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -19943,6 +20042,7 @@
     "gemini/gemini-2.5-pro": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
+        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "input_cost_per_token_priority": 1.25e-06,
@@ -20077,6 +20177,7 @@
     },
     "gemini/gemini-3.1-flash-lite-preview": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-05-25",
         "input_cost_per_audio_token": 5e-07,
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "gemini",
@@ -20129,6 +20230,7 @@
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2027-05-07",
         "input_cost_per_audio_token": 5e-07,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
@@ -20896,18 +20998,21 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini/imagen-4.0-fast-generate-001": {
+        "deprecation_date": "2026-08-17",
         "litellm_provider": "gemini",
         "mode": "image_generation",
         "output_cost_per_image": 0.02,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini/imagen-4.0-generate-001": {
+        "deprecation_date": "2026-08-17",
         "litellm_provider": "gemini",
         "mode": "image_generation",
         "output_cost_per_image": 0.04,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
     "gemini/imagen-4.0-ultra-generate-001": {
+        "deprecation_date": "2026-08-17",
         "litellm_provider": "gemini",
         "mode": "image_generation",
         "output_cost_per_image": 0.06,
@@ -20991,6 +21096,7 @@
         "supports_web_search": false
     },
     "gemini/veo-2.0-generate-001": {
+        "deprecation_date": "2026-06-30",
         "litellm_provider": "gemini",
         "max_input_tokens": 1024,
         "max_tokens": 1024,
@@ -22025,6 +22131,7 @@
         "supports_vision": true
     },
     "gpt-3.5-turbo": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -22038,6 +22145,7 @@
         "supports_tool_choice": true
     },
     "gpt-3.5-turbo-0125": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
@@ -22097,6 +22205,7 @@
         "output_cost_per_token": 2e-06
     },
     "gpt-4": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
@@ -22137,7 +22246,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-0613": {
-        "deprecation_date": "2025-06-06",
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
@@ -22151,7 +22260,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-1106-preview": {
-        "deprecation_date": "2026-03-26",
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -22166,6 +22275,7 @@
         "supports_tool_choice": true
     },
     "gpt-4-turbo": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -22182,6 +22292,7 @@
         "supports_vision": true
     },
     "gpt-4-turbo-2024-04-09": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -22363,6 +22474,7 @@
     "gpt-4.1-nano": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 5e-08,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_batches": 5e-08,
         "input_cost_per_token_priority": 2e-07,
@@ -22399,6 +22511,7 @@
     "gpt-4.1-nano-2025-04-14": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 5e-08,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-07,
         "input_cost_per_token_priority": 2e-07,
         "input_cost_per_token_batches": 5e-08,
@@ -22456,6 +22569,7 @@
         "supports_vision": true
     },
     "gpt-4o-2024-05-13": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_batches": 2.5e-06,
         "input_cost_per_token_priority": 8.75e-06,
@@ -22522,6 +22636,7 @@
         "supports_vision": true
     },
     "gpt-4o-audio-preview": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22539,6 +22654,7 @@
         "supports_tool_choice": true
     },
     "gpt-4o-audio-preview-2024-12-17": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22556,6 +22672,7 @@
         "supports_tool_choice": true
     },
     "gpt-4o-audio-preview-2025-06-03": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22573,6 +22690,7 @@
         "supports_tool_choice": true
     },
     "gpt-audio": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22642,6 +22760,7 @@
         "supports_vision": false
     },
     "gpt-audio-2025-08-28": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
@@ -22678,6 +22797,7 @@
         "supports_vision": false
     },
     "gpt-audio-mini": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22714,6 +22834,7 @@
         "supports_vision": false
     },
     "gpt-audio-mini-2025-10-06": {
+        "deprecation_date": "2026-07-23",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22837,6 +22958,7 @@
         "supports_vision": true
     },
     "gpt-4o-mini-audio-preview": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "openai",
@@ -22854,6 +22976,7 @@
         "supports_tool_choice": true
     },
     "gpt-4o-mini-audio-preview-2024-12-17": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "openai",
@@ -22873,6 +22996,7 @@
     "gpt-4o-mini-realtime-preview": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22892,6 +23016,7 @@
     "gpt-4o-mini-realtime-preview-2024-12-17": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 3e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -22936,6 +23061,7 @@
     },
     "gpt-4o-mini-search-preview-2025-03-11": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.5e-07,
         "input_cost_per_token_batches": 7.5e-08,
         "litellm_provider": "openai",
@@ -22986,6 +23112,7 @@
     },
     "gpt-4o-realtime-preview": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -23004,6 +23131,7 @@
     },
     "gpt-4o-realtime-preview-2024-12-17": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -23022,6 +23150,7 @@
     },
     "gpt-4o-realtime-preview-2025-06-03": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -23066,6 +23195,7 @@
     },
     "gpt-4o-search-preview-2025-03-11": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_batches": 1.25e-06,
         "litellm_provider": "openai",
@@ -23098,6 +23228,7 @@
     },
     "gpt-image-1.5": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -23112,6 +23243,7 @@
     },
     "gpt-image-1.5-2025-12-16": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
@@ -23607,6 +23739,7 @@
     "gpt-5.1-chat-latest": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -23726,6 +23859,7 @@
     "gpt-5.2-chat-latest": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-08-10",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -23764,6 +23898,7 @@
     "gpt-5.3-chat-latest": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-08-10",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -24679,6 +24814,7 @@
         "supports_minimal_reasoning_effort": true
     },
     "gpt-5-pro-2025-10-06": {
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
@@ -24718,6 +24854,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
@@ -24793,6 +24930,7 @@
     },
     "gpt-5-chat-latest": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
@@ -24828,6 +24966,7 @@
     },
     "gpt-5-codex": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
@@ -24863,6 +25002,7 @@
     "gpt-5.1-codex": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_priority": 2.5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -24899,6 +25039,7 @@
     },
     "gpt-5.1-codex-max": {
         "cache_read_input_token_cost": 1.25e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
@@ -24934,6 +25075,7 @@
     "gpt-5.1-codex-mini": {
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
@@ -24971,6 +25113,7 @@
     "gpt-5.2-codex": {
         "cache_read_input_token_cost": 1.75e-07,
         "cache_read_input_token_cost_priority": 3.5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -25088,6 +25231,7 @@
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
@@ -25169,6 +25313,7 @@
     "gpt-5-nano-2025-08-07": {
         "cache_read_input_token_cost": 5e-09,
         "cache_read_input_token_cost_flex": 2.5e-09,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "input_cost_per_token_flex": 2.5e-08,
@@ -25208,6 +25353,7 @@
     },
     "gpt-image-1": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -25220,6 +25366,7 @@
     },
     "gpt-image-1-mini": {
         "cache_read_input_token_cost": 2e-07,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "openai",
@@ -25233,6 +25380,7 @@
     "gpt-realtime": {
         "cache_creation_input_audio_token_cost": 4e-07,
         "cache_read_input_token_cost": 4e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -25399,6 +25547,7 @@
     "gpt-realtime-mini": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
@@ -25430,6 +25579,7 @@
     "gpt-realtime-2025-08-28": {
         "cache_creation_input_audio_token_cost": 4e-07,
         "cache_read_input_token_cost": 4e-07,
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_image": 5e-06,
         "input_cost_per_token": 4e-06,
@@ -29258,6 +29408,7 @@
     },
     "o1": {
         "cache_read_input_token_cost": 7.5e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29277,6 +29428,7 @@
     },
     "o1-2024-12-17": {
         "cache_read_input_token_cost": 7.5e-06,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29295,6 +29447,7 @@
         "supports_vision": true
     },
     "o1-pro": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 0.00015,
         "input_cost_per_token_batches": 7.5e-05,
         "litellm_provider": "openai",
@@ -29327,6 +29480,7 @@
         "supports_vision": true
     },
     "o1-pro-2025-03-19": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 0.00015,
         "input_cost_per_token_batches": 7.5e-05,
         "litellm_provider": "openai",
@@ -29400,6 +29554,7 @@
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 8.75e-07,
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 3.5e-06,
@@ -29436,6 +29591,7 @@
     },
     "o3-deep-research": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_batches": 5e-06,
         "litellm_provider": "openai",
@@ -29470,6 +29626,7 @@
     },
     "o3-deep-research-2025-06-26": {
         "cache_read_input_token_cost": 2.5e-06,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 1e-05,
         "input_cost_per_token_batches": 5e-06,
         "litellm_provider": "openai",
@@ -29504,6 +29661,7 @@
     },
     "o3-mini": {
         "cache_read_input_token_cost": 5.5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29521,6 +29679,7 @@
     },
     "o3-mini-2025-01-31": {
         "cache_read_input_token_cost": 5.5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
@@ -29568,6 +29727,7 @@
         "supports_web_search": true
     },
     "o3-pro-2025-06-10": {
+        "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2e-05,
         "input_cost_per_token_batches": 1e-05,
         "litellm_provider": "openai",
@@ -29602,6 +29762,7 @@
         "cache_read_input_token_cost": 2.75e-07,
         "cache_read_input_token_cost_flex": 1.375e-07,
         "cache_read_input_token_cost_priority": 5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
@@ -29627,6 +29788,7 @@
         "cache_read_input_token_cost": 2.75e-07,
         "cache_read_input_token_cost_flex": 1.375e-07,
         "cache_read_input_token_cost_priority": 5e-07,
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
@@ -29650,6 +29812,7 @@
     },
     "o4-mini-deep-research": {
         "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
@@ -29684,6 +29847,7 @@
     },
     "o4-mini-deep-research-2025-06-26": {
         "cache_read_input_token_cost": 5e-07,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
@@ -40085,69 +40249,86 @@
     },
     "xai/grok-4.20-multi-agent-beta-0309": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
     },
     "xai/grok-4.20-beta-0309-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
     },
     "xai/grok-4.20-0309-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
     },
     "xai/grok-4.20-beta-0309-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.25e-06,
         "litellm_provider": "xai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
+        "output_cost_per_token": 2.5e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
     },
     "xai/grok-4.3": {
         "cache_read_input_token_cost": 2e-07,
@@ -40192,8 +40373,8 @@
         "supports_web_search": true
     },
     "xai/grok-4.5": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
         "litellm_provider": "xai",
@@ -40213,8 +40394,8 @@
         "supports_web_search": true
     },
     "xai/grok-4.5-latest": {
-        "cache_read_input_token_cost": 5e-07,
-        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 6e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
         "litellm_provider": "xai",
@@ -40247,51 +40428,64 @@
         "supports_web_search": true
     },
     "xai/grok-code-fast": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 2e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     },
     "xai/grok-code-fast-1": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 2e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "deprecation_date": "2026-05-15"
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     },
     "xai/grok-code-fast-1-0825": {
-        "cache_read_input_token_cost": 2e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 256000,
         "max_output_tokens": 256000,
         "max_tokens": 256000,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 2e-06,
         "source": "https://docs.x.ai/docs/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
-        "deprecation_date": "2026-05-15"
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     },
     "xai/grok-vision-beta": {
         "input_cost_per_image": 5e-06,
@@ -40528,6 +40722,7 @@
         "mode": "chat"
     },
     "openai/sora-2": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
@@ -40541,6 +40736,7 @@
         ]
     },
     "openai/sora-2-pro": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.3,
@@ -44495,6 +44691,7 @@
         ]
     },
     "gpt-4o-mini-transcribe-2025-03-20": {
+        "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1.25e-06,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
@@ -44565,6 +44762,7 @@
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
         "cache_read_input_token_cost": 6e-08,
+        "deprecation_date": "2026-07-23",
         "input_cost_per_audio_token": 1e-05,
         "input_cost_per_image": 8e-07,
         "input_cost_per_token": 6e-07,
@@ -44645,6 +44843,7 @@
         "supports_audio_input": true
     },
     "sora-2": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
@@ -44658,6 +44857,7 @@
         ]
     },
     "sora-2-pro": {
+        "deprecation_date": "2026-09-24",
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.3,
@@ -44685,6 +44885,7 @@
     },
     "chatgpt-image-latest": {
         "cache_read_input_token_cost": 1.25e-06,
+        "deprecation_date": "2026-12-01",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "openai",
@@ -46503,5 +46704,66 @@
                 }
             }
         ]
+    },
+    "xai/grok-4.20-0309-non-reasoning": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
+    },
+    "xai/grok-4.20-multi-agent-0309": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 1000000,
+        "max_tokens": 1000000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true
+    },
+    "xai/grok-build-0.1": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 1e-06,
+        "litellm_provider": "xai",
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "max_tokens": 256000,
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "source": "https://docs.x.ai/docs/models",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true,
+        "input_cost_per_token_above_200k_tokens": 2e-06,
+        "output_cost_per_token_above_200k_tokens": 4e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "supports_response_schema": true,
+        "supports_vision": true
     }
 }
diff --git a/tests/test_litellm/llms/xai/test_xai_cost_calculator.py b/tests/test_litellm/llms/xai/test_xai_cost_calculator.py
index 02fe7c8e68f..a8d9708d2f2 100644
--- a/tests/test_litellm/llms/xai/test_xai_cost_calculator.py
+++ b/tests/test_litellm/llms/xai/test_xai_cost_calculator.py
@@ -432,10 +432,10 @@ class TestXAICostCalculator:
             model="grok-4.20-beta-0309-reasoning", usage=usage
         )
 
-        # Input: 100 tokens * $2e-6 = $0.0002
-        # Output: 200 tokens * $6e-6 = $0.0012
-        expected_prompt_cost = 100 * 2e-6
-        expected_completion_cost = 200 * 6e-6
+        # Input: 100 tokens * $1.25e-6 = $0.000125
+        # Output: 200 tokens * $2.5e-6 = $0.0005
+        expected_prompt_cost = 100 * 1.25e-6
+        expected_completion_cost = 200 * 2.5e-6
 
         assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
         assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
@@ -448,10 +448,10 @@ class TestXAICostCalculator:
             model="grok-4.20-beta-0309-non-reasoning", usage=usage
         )
 
-        # Input: 50 tokens * $2e-6 = $0.0001
-        # Output: 100 tokens * $6e-6 = $0.0006
-        expected_prompt_cost = 50 * 2e-6
-        expected_completion_cost = 100 * 6e-6
+        # Input: 50 tokens * $1.25e-6 = $0.0000625
+        # Output: 100 tokens * $2.5e-6 = $0.00025
+        expected_prompt_cost = 50 * 1.25e-6
+        expected_completion_cost = 100 * 2.5e-6
 
         assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
         assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
@@ -464,10 +464,10 @@ class TestXAICostCalculator:
             model="grok-4.20-multi-agent-beta-0309", usage=usage
         )
 
-        # Input: 200 tokens * $2e-6 = $0.0004
-        # Output: 300 tokens * $6e-6 = $0.0018
-        expected_prompt_cost = 200 * 2e-6
-        expected_completion_cost = 300 * 6e-6
+        # Input: 200 tokens * $1.25e-6 = $0.00025
+        # Output: 300 tokens * $2.5e-6 = $0.00075
+        expected_prompt_cost = 200 * 1.25e-6
+        expected_completion_cost = 300 * 2.5e-6
 
         assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
         assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)

From 76586a8268ada242c77be00df6379cab752b9626 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Mon, 10 Aug 2026 13:21:33 +0000
Subject: [PATCH 2/7] fix(model_prices): drop unverified deprecation dates,
 correct gemini embedding and anthropic opus 4.1

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 .../model_prices_and_context_window_backup.json   | 15 ++++++---------
 model_prices_and_context_window.json              | 15 ++++++---------
 2 files changed, 12 insertions(+), 18 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 83185949841..e003ca42e30 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -11502,7 +11502,6 @@
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_read_input_token_cost": 1e-07,
-        "deprecation_date": "2026-10-15",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11706,7 +11705,6 @@
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
-        "deprecation_date": "2026-09-29",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
@@ -11856,7 +11854,8 @@
         "supports_native_structured_output": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "deprecation_date": "2026-08-05"
     },
     "claude-opus-4-1-20250805": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -11919,7 +11918,6 @@
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_read_input_token_cost": 5e-07,
-        "deprecation_date": "2026-11-24",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -12801,7 +12799,6 @@
         "supports_tool_choice": true
     },
     "computer-use-preview": {
-        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 8192,
@@ -17344,6 +17341,7 @@
         "supports_tool_choice": true
     },
     "ft:babbage-002": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.6e-06,
         "input_cost_per_token_batches": 2e-07,
         "litellm_provider": "text-completion-openai",
@@ -17355,6 +17353,7 @@
         "output_cost_per_token_batches": 2e-07
     },
     "ft:davinci-002": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.2e-05,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "text-completion-openai",
@@ -19258,7 +19257,7 @@
         "uses_embed_content": true
     },
     "gemini/gemini-embedding-001": {
-        "deprecation_date": "2026-07-14",
+        "deprecation_date": "2028-05-14",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "gemini",
         "max_input_tokens": 2048,
@@ -19434,7 +19433,6 @@
     },
     "gemini/gemini-2.5-flash": {
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "gemini",
@@ -19746,7 +19744,6 @@
     },
     "gemini/gemini-2.5-flash-lite": {
         "cache_read_input_token_cost": 1e-08,
-        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -20042,7 +20039,6 @@
     "gemini/gemini-2.5-pro": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "input_cost_per_token_priority": 1.25e-06,
@@ -44655,6 +44651,7 @@
         ]
     },
     "gpt-4o-mini-tts-2025-03-20": {
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
         "mode": "audio_speech",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 83185949841..e003ca42e30 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -11502,7 +11502,6 @@
         "cache_creation_input_token_cost": 1.25e-06,
         "cache_creation_input_token_cost_above_1hr": 2e-06,
         "cache_read_input_token_cost": 1e-07,
-        "deprecation_date": "2026-10-15",
         "input_cost_per_token": 1e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -11706,7 +11705,6 @@
         "cache_creation_input_token_cost_above_1hr": 6e-06,
         "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
         "cache_read_input_token_cost": 3e-07,
-        "deprecation_date": "2026-09-29",
         "input_cost_per_token": 3e-06,
         "input_cost_per_token_above_200k_tokens": 6e-06,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
@@ -11856,7 +11854,8 @@
         "supports_native_structured_output": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "deprecation_date": "2026-08-05"
     },
     "claude-opus-4-1-20250805": {
         "cache_creation_input_token_cost": 1.875e-05,
@@ -11919,7 +11918,6 @@
         "cache_creation_input_token_cost": 6.25e-06,
         "cache_creation_input_token_cost_above_1hr": 1e-05,
         "cache_read_input_token_cost": 5e-07,
-        "deprecation_date": "2026-11-24",
         "input_cost_per_token": 5e-06,
         "litellm_provider": "anthropic",
         "max_input_tokens": 200000,
@@ -12801,7 +12799,6 @@
         "supports_tool_choice": true
     },
     "computer-use-preview": {
-        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 8192,
@@ -17344,6 +17341,7 @@
         "supports_tool_choice": true
     },
     "ft:babbage-002": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.6e-06,
         "input_cost_per_token_batches": 2e-07,
         "litellm_provider": "text-completion-openai",
@@ -17355,6 +17353,7 @@
         "output_cost_per_token_batches": 2e-07
     },
     "ft:davinci-002": {
+        "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.2e-05,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "text-completion-openai",
@@ -19258,7 +19257,7 @@
         "uses_embed_content": true
     },
     "gemini/gemini-embedding-001": {
-        "deprecation_date": "2026-07-14",
+        "deprecation_date": "2028-05-14",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "gemini",
         "max_input_tokens": 2048,
@@ -19434,7 +19433,6 @@
     },
     "gemini/gemini-2.5-flash": {
         "cache_read_input_token_cost": 3e-08,
-        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "gemini",
@@ -19746,7 +19744,6 @@
     },
     "gemini/gemini-2.5-flash-lite": {
         "cache_read_input_token_cost": 1e-08,
-        "deprecation_date": "2026-10-16",
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -20042,7 +20039,6 @@
     "gemini/gemini-2.5-pro": {
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
-        "deprecation_date": "2026-10-16",
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "input_cost_per_token_priority": 1.25e-06,
@@ -44655,6 +44651,7 @@
         ]
     },
     "gpt-4o-mini-tts-2025-03-20": {
+        "deprecation_date": "2026-07-23",
         "input_cost_per_token": 2.5e-06,
         "litellm_provider": "openai",
         "mode": "audio_speech",

From b5b663fd8bcfc4565e1ec12c7ec1cf4047d539f0 Mon Sep 17 00:00:00 2001
From: mateo <mateo@berri.ai>
Date: Mon, 10 Aug 2026 14:13:05 +0000
Subject: [PATCH 3/7] fix(xai): bill the above-200k tier at exactly 200k prompt
 tokens

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 .../litellm_core_utils/llm_cost_calc/utils.py | 21 ++++++++++++--
 litellm/llms/xai/cost_calculator.py           |  8 +++++-
 .../llms/xai/test_xai_cost_calculator.py      | 28 +++++++++++++++++++
 3 files changed, 53 insertions(+), 4 deletions(-)

diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py
index 6574b261774..69d05e72b4f 100644
--- a/litellm/litellm_core_utils/llm_cost_calc/utils.py
+++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py
@@ -202,7 +202,11 @@ def _parse_above_token_threshold(key: str) -> float:
 
 
 def _get_token_base_cost(
-    model_info: ModelInfo, usage: Usage, service_tier: str | None = None
+    model_info: ModelInfo,
+    usage: Usage,
+    service_tier: str | None = None,
+    *,
+    threshold_is_inclusive: bool = False,
 ) -> tuple[float, float, float, float, float]:
     """
     Return prompt cost, completion cost, and cache costs for a given model and usage.
@@ -210,6 +214,9 @@ def _get_token_base_cost(
     If input_tokens > threshold and `input_cost_per_token_above_[x]k_tokens` or `input_cost_per_token_above_[x]_tokens` is set,
     then we use the corresponding threshold cost for all token types.
 
+    `threshold_is_inclusive` switches that comparison to >=, for providers such as xAI
+    that bill the higher tier once the prompt reaches the threshold.
+
     Returns:
         Tuple[float, float, float, float] - (prompt_cost, completion_cost, cache_creation_cost, cache_read_cost)
     """
@@ -262,7 +269,7 @@ def _get_token_base_cost(
                 # Handle both formats: _above_128k_tokens and _above_128_tokens
                 threshold_str = key.split("_above_")[1].split("_tokens")[0]
                 threshold = _parse_above_token_threshold(key)
-                if usage.prompt_tokens > threshold:
+                if usage.prompt_tokens > threshold or (threshold_is_inclusive and usage.prompt_tokens == threshold):
                     # Prefer a service_tier-specific above-threshold key when available,
                     # e.g. input_cost_per_token_priority_above_200k_tokens for Gemini
                     # ON_DEMAND_PRIORITY.  Falls back to the standard key automatically
@@ -705,6 +712,7 @@ def generic_cost_per_token(
     service_tier: str | None = None,
     data_residency: str | None = None,
     model_info: ModelInfo | None = None,
+    threshold_is_inclusive: bool = False,
 ) -> tuple[float, float]:
     """
     Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@@ -716,6 +724,8 @@ def generic_cost_per_token(
         - usage: LiteLLM Usage block, containing anthropic caching information
         - data_residency: optional OpenAI data-residency region (e.g. "eu", "us"),
           used to apply the per-model regional-processing uplift multiplier.
+        - threshold_is_inclusive: bill the above-threshold tier when the prompt is exactly
+          at the threshold, as xAI does.
 
     Returns:
         Tuple[float, float] - prompt_cost_in_usd, completion_cost_in_usd
@@ -777,7 +787,12 @@ def generic_cost_per_token(
         cache_creation_cost,
         cache_creation_cost_above_1hr,
         cache_read_cost,
-    ) = _get_token_base_cost(model_info=model_info, usage=usage, service_tier=service_tier)
+    ) = _get_token_base_cost(
+        model_info=model_info,
+        usage=usage,
+        service_tier=service_tier,
+        threshold_is_inclusive=threshold_is_inclusive,
+    )
 
     prompt_cost = _calculate_input_cost(
         prompt_tokens_details=prompt_tokens_details,
diff --git a/litellm/llms/xai/cost_calculator.py b/litellm/llms/xai/cost_calculator.py
index 384388f3300..b44f8935e17 100644
--- a/litellm/llms/xai/cost_calculator.py
+++ b/litellm/llms/xai/cost_calculator.py
@@ -47,7 +47,13 @@ def cost_per_token(model: str, usage: Usage) -> tuple[float, float]:
         completion_tokens_details=None,
     )
 
-    prompt_cost, completion_cost = generic_cost_per_token(model=model, usage=modified_usage, custom_llm_provider="xai")
+    # xAI bills the higher tier once the prompt reaches 200k tokens, not strictly above it
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model=model,
+        usage=modified_usage,
+        custom_llm_provider="xai",
+        threshold_is_inclusive=True,
+    )
 
     return prompt_cost, completion_cost
 
diff --git a/tests/test_litellm/llms/xai/test_xai_cost_calculator.py b/tests/test_litellm/llms/xai/test_xai_cost_calculator.py
index a8d9708d2f2..32141bead0e 100644
--- a/tests/test_litellm/llms/xai/test_xai_cost_calculator.py
+++ b/tests/test_litellm/llms/xai/test_xai_cost_calculator.py
@@ -456,6 +456,34 @@ class TestXAICostCalculator:
         assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
         assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
 
+    def test_grok_4_20_at_exactly_200k_prompt_tokens_uses_higher_tier(self):
+        """xAI bills the >=200k tier once the prompt reaches 200k, so the boundary is inclusive."""
+        usage = Usage(prompt_tokens=200_000, completion_tokens=1_000, total_tokens=201_000)
+
+        prompt_cost, completion_cost = cost_per_token(
+            model="grok-4.20-0309-reasoning", usage=usage
+        )
+
+        expected_prompt_cost = 200_000 * 2.5e-6
+        expected_completion_cost = 1_000 * 5e-6
+
+        assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
+        assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
+
+    def test_grok_4_20_just_below_200k_prompt_tokens_uses_base_tier(self):
+        """One token under the boundary still bills at the base rates."""
+        usage = Usage(prompt_tokens=199_999, completion_tokens=1_000, total_tokens=200_999)
+
+        prompt_cost, completion_cost = cost_per_token(
+            model="grok-4.20-0309-reasoning", usage=usage
+        )
+
+        expected_prompt_cost = 199_999 * 1.25e-6
+        expected_completion_cost = 1_000 * 2.5e-6
+
+        assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
+        assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
+
     def test_grok_4_20_multi_agent_cost_calculation(self):
         """Test cost calculation for grok-4.20-multi-agent-beta-0309 model."""
         usage = Usage(prompt_tokens=200, completion_tokens=300, total_tokens=500)

From cb0c96bf462cb8335d2f7f646d8fda9bf81435c4 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Mon, 10 Aug 2026 14:14:27 +0000
Subject: [PATCH 4/7] feat(model_prices): add missing OpenAI transcription,
 Anthropic Mythos, Gemini robotics streaming and Mistral models

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 235 ++++++++++++++++++
 model_prices_and_context_window.json          | 235 ++++++++++++++++++
 2 files changed, 470 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index e003ca42e30..90491cefd3c 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -46762,5 +46762,240 @@
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
         "supports_response_schema": true,
         "supports_vision": true
+    },
+    "gpt-transcribe": {
+        "input_cost_per_second": 7.5e-05,
+        "litellm_provider": "openai",
+        "mode": "audio_transcription",
+        "source": "https://platform.openai.com/docs/models/gpt-transcribe",
+        "supported_endpoints": [
+            "/v1/audio/transcriptions",
+            "/v1/realtime/transcription_sessions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "gpt-live-transcribe": {
+        "input_cost_per_second": 0.0002833333333333333,
+        "litellm_provider": "openai",
+        "mode": "audio_transcription",
+        "source": "https://platform.openai.com/docs/models/gpt-live-transcribe",
+        "supported_endpoints": [
+            "/v1/realtime",
+            "/v1/realtime/transcription_sessions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "gpt-realtime-translate": {
+        "input_cost_per_second": 0.0005666666666666667,
+        "litellm_provider": "openai",
+        "max_input_tokens": 16000,
+        "max_output_tokens": 2000,
+        "max_tokens": 2000,
+        "mode": "realtime",
+        "source": "https://platform.openai.com/docs/models/gpt-realtime-translate",
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true
+    },
+    "claude-mythos-5": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_1hr": 2e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "prompt_cache_min_tokens": 512,
+        "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://docs.claude.com/en/docs/about-claude/models/overview",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "claude-mythos-preview": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_1hr": 2e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "prompt_cache_min_tokens": 512,
+        "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://docs.claude.com/en/docs/about-claude/models/overview",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "gemini/gemini-robotics-er-2-streaming-preview": {
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.014,
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014
+        },
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "mistral/mistral-small-2603": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "mistral/labs-leanstral-1-5": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "mistral/mistral-moderation-2603": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 131072,
+        "mode": "moderation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.mistral.ai/models/model-cards/mistral-moderation-26-03"
+    },
+    "mistral/voxtral-mini-2602": {
+        "input_cost_per_second": 5e-05,
+        "litellm_provider": "mistral",
+        "mode": "audio_transcription",
+        "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02",
+        "supported_endpoints": [
+            "/v1/audio/transcriptions"
+        ],
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "mistral/voxtral-mini-transcribe-realtime-2602": {
+        "input_cost_per_second": 0.0001,
+        "litellm_provider": "mistral",
+        "mode": "audio_transcription",
+        "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02",
+        "supported_endpoints": [
+            "/v1/audio/transcriptions"
+        ],
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "mistral/voxtral-mini-tts-2603": {
+        "litellm_provider": "mistral",
+        "mode": "audio_speech",
+        "output_cost_per_character": 1.6e-05,
+        "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ],
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "audio"
+        ],
+        "supports_audio_output": true
     }
 }
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index e003ca42e30..90491cefd3c 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -46762,5 +46762,240 @@
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,
         "supports_response_schema": true,
         "supports_vision": true
+    },
+    "gpt-transcribe": {
+        "input_cost_per_second": 7.5e-05,
+        "litellm_provider": "openai",
+        "mode": "audio_transcription",
+        "source": "https://platform.openai.com/docs/models/gpt-transcribe",
+        "supported_endpoints": [
+            "/v1/audio/transcriptions",
+            "/v1/realtime/transcription_sessions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "gpt-live-transcribe": {
+        "input_cost_per_second": 0.0002833333333333333,
+        "litellm_provider": "openai",
+        "mode": "audio_transcription",
+        "source": "https://platform.openai.com/docs/models/gpt-live-transcribe",
+        "supported_endpoints": [
+            "/v1/realtime",
+            "/v1/realtime/transcription_sessions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "gpt-realtime-translate": {
+        "input_cost_per_second": 0.0005666666666666667,
+        "litellm_provider": "openai",
+        "max_input_tokens": 16000,
+        "max_output_tokens": 2000,
+        "max_tokens": 2000,
+        "mode": "realtime",
+        "source": "https://platform.openai.com/docs/models/gpt-realtime-translate",
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true
+    },
+    "claude-mythos-5": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_1hr": 2e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "prompt_cache_min_tokens": 512,
+        "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://docs.claude.com/en/docs/about-claude/models/overview",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "claude-mythos-preview": {
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_1hr": 2e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 1e-05,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 5e-05,
+        "prompt_cache_min_tokens": 512,
+        "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://docs.claude.com/en/docs/about-claude/models/overview",
+        "supports_adaptive_thinking": true,
+        "supports_assistant_prefill": false,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_max_reasoning_effort": true,
+        "supports_output_config": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_sampling_params": false,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "gemini/gemini-robotics-er-2-streaming-preview": {
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.014,
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014
+        },
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "web_search_billing_unit": "per_query"
+    },
+    "mistral/mistral-small-2603": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "mistral/labs-leanstral-1-5": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "mistral/mistral-moderation-2603": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 131072,
+        "mode": "moderation",
+        "output_cost_per_token": 0.0,
+        "source": "https://docs.mistral.ai/models/model-cards/mistral-moderation-26-03"
+    },
+    "mistral/voxtral-mini-2602": {
+        "input_cost_per_second": 5e-05,
+        "litellm_provider": "mistral",
+        "mode": "audio_transcription",
+        "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02",
+        "supported_endpoints": [
+            "/v1/audio/transcriptions"
+        ],
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "mistral/voxtral-mini-transcribe-realtime-2602": {
+        "input_cost_per_second": 0.0001,
+        "litellm_provider": "mistral",
+        "mode": "audio_transcription",
+        "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02",
+        "supported_endpoints": [
+            "/v1/audio/transcriptions"
+        ],
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true
+    },
+    "mistral/voxtral-mini-tts-2603": {
+        "litellm_provider": "mistral",
+        "mode": "audio_speech",
+        "output_cost_per_character": 1.6e-05,
+        "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ],
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "audio"
+        ],
+        "supports_audio_output": true
     }
 }

From 69def0545d24471107cfae4270b160fde15f80a5 Mon Sep 17 00:00:00 2001
From: mateo <mateo@berri.ai>
Date: Mon, 10 Aug 2026 16:01:41 +0000
Subject: [PATCH 5/7] refactor(model_prices): keep fallback_generalizations
 last in the registry

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 114 +++++++++---------
 model_prices_and_context_window.json          | 114 +++++++++---------
 2 files changed, 114 insertions(+), 114 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 90491cefd3c..873b1eb24d7 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -46645,63 +46645,6 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
-    "fallback_generalizations": {
-        "rules": [
-            {
-                "name": "bedrock-claude-ids",
-                "pattern": "^(?:[a-z-]+\\.)?anthropic\\.claude-",
-                "description": "A Bedrock-syntax Claude id, for every version: anthropic.claude- at the start of the name, optionally behind a single dotted geo segment (us./eu./au./jp./apac./global./us-gov.). Anchored to the start because routing rules see the raw request string and provider inference feeds the proxy's provider/* wildcard access checks: an id under an unrecognized namespace such as bedrockz/anthropic.claude-... must stay unroutable rather than resolve to bedrock and slip through a bedrock/* key. Routes to bedrock before the bare-id Anthropic rule is consulted.",
-                "model_info": {
-                    "litellm_provider": "bedrock"
-                }
-            },
-            {
-                "name": "anthropic-claude-ids",
-                "pattern": "^claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?$",
-                "description": "A bare Claude family-major id with an optional minor and an optional 8-digit date suffix, anchored to the whole name, so claude-newfamily-5 routes like claude-newfamily-5-1 does. Routes an unmapped Claude id that carries no provider namespace to the Anthropic API.",
-                "model_info": {
-                    "litellm_provider": "anthropic"
-                }
-            },
-            {
-                "name": "claude-family-baseline",
-                "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?",
-                "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.",
-                "model_info": {
-                    "mode": "chat",
-                    "max_input_tokens": 200000,
-                    "max_output_tokens": 64000,
-                    "max_tokens": 64000,
-                    "supports_function_calling": true,
-                    "supports_parallel_function_calling": true,
-                    "supports_vision": true,
-                    "supports_tool_choice": true,
-                    "supports_assistant_prefill": true,
-                    "supports_prompt_caching": true,
-                    "supports_response_schema": true,
-                    "supports_reasoning": true,
-                    "supports_pdf_input": true,
-                    "supports_system_messages": true
-                }
-            },
-            {
-                "name": "claude-adaptive-thinking",
-                "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
-                "description": "Claude at version 4.6 or higher, in any id shape that contains claude-<family>-: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new versions and new families with no code change.",
-                "model_info": {
-                    "supports_adaptive_thinking": true
-                }
-            },
-            {
-                "name": "claude-mid-conversation-system",
-                "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
-                "description": "Claude at version 4.8 or higher, in any id shape that contains claude-<family>-: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.",
-                "model_info": {
-                    "supports_mid_conversation_system": true
-                }
-            }
-        ]
-    },
     "xai/grok-4.20-0309-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
         "input_cost_per_token": 1.25e-06,
@@ -46997,5 +46940,62 @@
             "audio"
         ],
         "supports_audio_output": true
+    },
+    "fallback_generalizations": {
+        "rules": [
+            {
+                "name": "bedrock-claude-ids",
+                "pattern": "^(?:[a-z-]+\\.)?anthropic\\.claude-",
+                "description": "A Bedrock-syntax Claude id, for every version: anthropic.claude- at the start of the name, optionally behind a single dotted geo segment (us./eu./au./jp./apac./global./us-gov.). Anchored to the start because routing rules see the raw request string and provider inference feeds the proxy's provider/* wildcard access checks: an id under an unrecognized namespace such as bedrockz/anthropic.claude-... must stay unroutable rather than resolve to bedrock and slip through a bedrock/* key. Routes to bedrock before the bare-id Anthropic rule is consulted.",
+                "model_info": {
+                    "litellm_provider": "bedrock"
+                }
+            },
+            {
+                "name": "anthropic-claude-ids",
+                "pattern": "^claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?$",
+                "description": "A bare Claude family-major id with an optional minor and an optional 8-digit date suffix, anchored to the whole name, so claude-newfamily-5 routes like claude-newfamily-5-1 does. Routes an unmapped Claude id that carries no provider namespace to the Anthropic API.",
+                "model_info": {
+                    "litellm_provider": "anthropic"
+                }
+            },
+            {
+                "name": "claude-family-baseline",
+                "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?",
+                "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.",
+                "model_info": {
+                    "mode": "chat",
+                    "max_input_tokens": 200000,
+                    "max_output_tokens": 64000,
+                    "max_tokens": 64000,
+                    "supports_function_calling": true,
+                    "supports_parallel_function_calling": true,
+                    "supports_vision": true,
+                    "supports_tool_choice": true,
+                    "supports_assistant_prefill": true,
+                    "supports_prompt_caching": true,
+                    "supports_response_schema": true,
+                    "supports_reasoning": true,
+                    "supports_pdf_input": true,
+                    "supports_system_messages": true
+                }
+            },
+            {
+                "name": "claude-adaptive-thinking",
+                "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
+                "description": "Claude at version 4.6 or higher, in any id shape that contains claude-<family>-: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new versions and new families with no code change.",
+                "model_info": {
+                    "supports_adaptive_thinking": true
+                }
+            },
+            {
+                "name": "claude-mid-conversation-system",
+                "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
+                "description": "Claude at version 4.8 or higher, in any id shape that contains claude-<family>-: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.",
+                "model_info": {
+                    "supports_mid_conversation_system": true
+                }
+            }
+        ]
     }
 }
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 90491cefd3c..873b1eb24d7 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -46645,63 +46645,6 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
-    "fallback_generalizations": {
-        "rules": [
-            {
-                "name": "bedrock-claude-ids",
-                "pattern": "^(?:[a-z-]+\\.)?anthropic\\.claude-",
-                "description": "A Bedrock-syntax Claude id, for every version: anthropic.claude- at the start of the name, optionally behind a single dotted geo segment (us./eu./au./jp./apac./global./us-gov.). Anchored to the start because routing rules see the raw request string and provider inference feeds the proxy's provider/* wildcard access checks: an id under an unrecognized namespace such as bedrockz/anthropic.claude-... must stay unroutable rather than resolve to bedrock and slip through a bedrock/* key. Routes to bedrock before the bare-id Anthropic rule is consulted.",
-                "model_info": {
-                    "litellm_provider": "bedrock"
-                }
-            },
-            {
-                "name": "anthropic-claude-ids",
-                "pattern": "^claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?$",
-                "description": "A bare Claude family-major id with an optional minor and an optional 8-digit date suffix, anchored to the whole name, so claude-newfamily-5 routes like claude-newfamily-5-1 does. Routes an unmapped Claude id that carries no provider namespace to the Anthropic API.",
-                "model_info": {
-                    "litellm_provider": "anthropic"
-                }
-            },
-            {
-                "name": "claude-family-baseline",
-                "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?",
-                "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.",
-                "model_info": {
-                    "mode": "chat",
-                    "max_input_tokens": 200000,
-                    "max_output_tokens": 64000,
-                    "max_tokens": 64000,
-                    "supports_function_calling": true,
-                    "supports_parallel_function_calling": true,
-                    "supports_vision": true,
-                    "supports_tool_choice": true,
-                    "supports_assistant_prefill": true,
-                    "supports_prompt_caching": true,
-                    "supports_response_schema": true,
-                    "supports_reasoning": true,
-                    "supports_pdf_input": true,
-                    "supports_system_messages": true
-                }
-            },
-            {
-                "name": "claude-adaptive-thinking",
-                "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
-                "description": "Claude at version 4.6 or higher, in any id shape that contains claude-<family>-: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new versions and new families with no code change.",
-                "model_info": {
-                    "supports_adaptive_thinking": true
-                }
-            },
-            {
-                "name": "claude-mid-conversation-system",
-                "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
-                "description": "Claude at version 4.8 or higher, in any id shape that contains claude-<family>-: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.",
-                "model_info": {
-                    "supports_mid_conversation_system": true
-                }
-            }
-        ]
-    },
     "xai/grok-4.20-0309-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
         "input_cost_per_token": 1.25e-06,
@@ -46997,5 +46940,62 @@
             "audio"
         ],
         "supports_audio_output": true
+    },
+    "fallback_generalizations": {
+        "rules": [
+            {
+                "name": "bedrock-claude-ids",
+                "pattern": "^(?:[a-z-]+\\.)?anthropic\\.claude-",
+                "description": "A Bedrock-syntax Claude id, for every version: anthropic.claude- at the start of the name, optionally behind a single dotted geo segment (us./eu./au./jp./apac./global./us-gov.). Anchored to the start because routing rules see the raw request string and provider inference feeds the proxy's provider/* wildcard access checks: an id under an unrecognized namespace such as bedrockz/anthropic.claude-... must stay unroutable rather than resolve to bedrock and slip through a bedrock/* key. Routes to bedrock before the bare-id Anthropic rule is consulted.",
+                "model_info": {
+                    "litellm_provider": "bedrock"
+                }
+            },
+            {
+                "name": "anthropic-claude-ids",
+                "pattern": "^claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?$",
+                "description": "A bare Claude family-major id with an optional minor and an optional 8-digit date suffix, anchored to the whole name, so claude-newfamily-5 routes like claude-newfamily-5-1 does. Routes an unmapped Claude id that carries no provider namespace to the Anthropic API.",
+                "model_info": {
+                    "litellm_provider": "anthropic"
+                }
+            },
+            {
+                "name": "claude-family-baseline",
+                "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?",
+                "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number.",
+                "model_info": {
+                    "mode": "chat",
+                    "max_input_tokens": 200000,
+                    "max_output_tokens": 64000,
+                    "max_tokens": 64000,
+                    "supports_function_calling": true,
+                    "supports_parallel_function_calling": true,
+                    "supports_vision": true,
+                    "supports_tool_choice": true,
+                    "supports_assistant_prefill": true,
+                    "supports_prompt_caching": true,
+                    "supports_response_schema": true,
+                    "supports_reasoning": true,
+                    "supports_pdf_input": true,
+                    "supports_system_messages": true
+                }
+            },
+            {
+                "name": "claude-adaptive-thinking",
+                "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
+                "description": "Claude at version 4.6 or higher, in any id shape that contains claude-<family>-: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new versions and new families with no code change.",
+                "model_info": {
+                    "supports_adaptive_thinking": true
+                }
+            },
+            {
+                "name": "claude-mid-conversation-system",
+                "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
+                "description": "Claude at version 4.8 or higher, in any id shape that contains claude-<family>-: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.",
+                "model_info": {
+                    "supports_mid_conversation_system": true
+                }
+            }
+        ]
     }
 }

From 726abc68a6ef5b562d4bc620d9331365a91cb6a0 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Mon, 10 Aug 2026 10:51:52 -0700
Subject: [PATCH 6/7] fix(cost_calc): apply xAI's inclusive 200k threshold to
 the token-type breakdown

Derive threshold inclusivity from the provider inside generic_cost_per_token and
get_token_type_cost_breakdown so the spend-log breakdown can never disagree with
the billed totals at exactly 200k prompt tokens
---
 .../litellm_core_utils/llm_cost_calc/utils.py | 18 +++++--
 litellm/llms/xai/cost_calculator.py           |  8 +---
 .../llm_cost_calc/test_llm_cost_calc_utils.py | 48 +++++++++++++++++++
 3 files changed, 62 insertions(+), 12 deletions(-)

diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py
index 69d05e72b4f..d08535eca19 100644
--- a/litellm/litellm_core_utils/llm_cost_calc/utils.py
+++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py
@@ -49,6 +49,12 @@ _SERVICE_TIER_TO_COST_KEY_SUFFIX: Final[Mapping[str, str]] = MappingProxyType(
     }
 )
 
+_INCLUSIVE_THRESHOLD_PROVIDERS: Final = frozenset({"xai"})
+
+
+def _uses_inclusive_token_thresholds(custom_llm_provider: str | None) -> bool:
+    return custom_llm_provider in _INCLUSIVE_THRESHOLD_PROVIDERS
+
 
 def _get_token_detail_value(details: object, key: str) -> int | None:
     if isinstance(details, dict):
@@ -712,7 +718,6 @@ def generic_cost_per_token(
     service_tier: str | None = None,
     data_residency: str | None = None,
     model_info: ModelInfo | None = None,
-    threshold_is_inclusive: bool = False,
 ) -> tuple[float, float]:
     """
     Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@@ -724,8 +729,6 @@ def generic_cost_per_token(
         - usage: LiteLLM Usage block, containing anthropic caching information
         - data_residency: optional OpenAI data-residency region (e.g. "eu", "us"),
           used to apply the per-model regional-processing uplift multiplier.
-        - threshold_is_inclusive: bill the above-threshold tier when the prompt is exactly
-          at the threshold, as xAI does.
 
     Returns:
         Tuple[float, float] - prompt_cost_in_usd, completion_cost_in_usd
@@ -791,7 +794,7 @@ def generic_cost_per_token(
         model_info=model_info,
         usage=usage,
         service_tier=service_tier,
-        threshold_is_inclusive=threshold_is_inclusive,
+        threshold_is_inclusive=_uses_inclusive_token_thresholds(custom_llm_provider),
     )
 
     prompt_cost = _calculate_input_cost(
@@ -924,7 +927,12 @@ def get_token_type_cost_breakdown(
         cache_creation_cost_rate,
         cache_creation_cost_above_1hr_rate,
         cache_read_cost_rate,
-    ) = _get_token_base_cost(model_info=model_info, usage=usage, service_tier=service_tier)
+    ) = _get_token_base_cost(
+        model_info=model_info,
+        usage=usage,
+        service_tier=service_tier,
+        threshold_is_inclusive=_uses_inclusive_token_thresholds(custom_llm_provider),
+    )
 
     reasoning_tokens = (
         _parse_completion_tokens_details(usage)["reasoning_tokens"]
diff --git a/litellm/llms/xai/cost_calculator.py b/litellm/llms/xai/cost_calculator.py
index b44f8935e17..384388f3300 100644
--- a/litellm/llms/xai/cost_calculator.py
+++ b/litellm/llms/xai/cost_calculator.py
@@ -47,13 +47,7 @@ def cost_per_token(model: str, usage: Usage) -> tuple[float, float]:
         completion_tokens_details=None,
     )
 
-    # xAI bills the higher tier once the prompt reaches 200k tokens, not strictly above it
-    prompt_cost, completion_cost = generic_cost_per_token(
-        model=model,
-        usage=modified_usage,
-        custom_llm_provider="xai",
-        threshold_is_inclusive=True,
-    )
+    prompt_cost, completion_cost = generic_cost_per_token(model=model, usage=modified_usage, custom_llm_provider="xai")
 
     return prompt_cost, completion_cost
 
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index 0970e029ad8..12ed66de878 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -2143,6 +2143,54 @@ def test_token_type_cost_breakdown_matches_real_gemini_numbers():
     assert breakdown.cache_creation_cost == 0.0
 
 
+def test_token_type_cost_breakdown_xai_at_exactly_200k_uses_higher_tier_rates():
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    usage = Usage(
+        prompt_tokens=200_000,
+        completion_tokens=2_000,
+        total_tokens=202_000,
+        completion_tokens_details=CompletionTokensDetailsWrapper(
+            reasoning_tokens=1_500, text_tokens=500
+        ),
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            cached_tokens=50_000, text_tokens=150_000
+        ),
+    )
+
+    breakdown = get_token_type_cost_breakdown(
+        model="grok-4.20-0309-reasoning", custom_llm_provider="xai", usage=usage
+    )
+
+    assert breakdown.reasoning_cost == pytest.approx(1_500 * 5e-06)
+    assert breakdown.cache_read_cost == pytest.approx(50_000 * 4e-07)
+
+
+def test_token_type_cost_breakdown_xai_just_below_200k_uses_base_tier_rates():
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    usage = Usage(
+        prompt_tokens=199_999,
+        completion_tokens=2_000,
+        total_tokens=201_999,
+        completion_tokens_details=CompletionTokensDetailsWrapper(
+            reasoning_tokens=1_500, text_tokens=500
+        ),
+        prompt_tokens_details=PromptTokensDetailsWrapper(
+            cached_tokens=50_000, text_tokens=149_999
+        ),
+    )
+
+    breakdown = get_token_type_cost_breakdown(
+        model="grok-4.20-0309-reasoning", custom_llm_provider="xai", usage=usage
+    )
+
+    assert breakdown.reasoning_cost == pytest.approx(1_500 * 2.5e-06)
+    assert breakdown.cache_read_cost == pytest.approx(50_000 * 2e-07)
+
+
 def test_token_type_cost_breakdown_includes_cache_creation_from_top_level_usage():
     """
     Bedrock/Anthropic report cache tokens as top-level usage fields; the Usage

From 9ec99cf9cec27ae5b8700ec5f0c0b5cf5495f1b2 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Mon, 10 Aug 2026 10:51:52 -0700
Subject: [PATCH 7/7] fix(model_prices): gpt-5-pro max output is 272k per
 OpenAI docs

---
 litellm/model_prices_and_context_window_backup.json | 8 ++++----
 model_prices_and_context_window.json                | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 873b1eb24d7..bfa506ee991 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -24778,8 +24778,8 @@
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 272000,
+        "max_tokens": 272000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -24815,8 +24815,8 @@
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 272000,
+        "max_tokens": 272000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 873b1eb24d7..bfa506ee991 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -24778,8 +24778,8 @@
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 272000,
+        "max_tokens": 272000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,
@@ -24815,8 +24815,8 @@
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 400000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_output_tokens": 272000,
+        "max_tokens": 272000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "output_cost_per_token_batches": 6e-05,