From a9ac442857a5ce21fb0980e0db9f12b7a0b2a49d Mon Sep 17 00:00:00 2001
From: bap1106 <bap1106@users.noreply.github.com>
Date: Mon, 28 Sep 2026 15:29:19 +0700
Subject: [PATCH] fix(clf_ai_gateway): sync prices and reasoning_effort levels
 with the live catalog

CLF AI Gateway raised its launch discount from 40% to 60% off list on
2026-09-26. It also re-measured every model's reasoning_effort levels
against the current Workers AI behaviour.

- input/output/cached per-token prices for all 9 models now match
  GET https://api.clfaigateway.dev/v1/public/models to the nano; qwen3.8-27b
  cached input also follows the upstream cached rate published on 2026-09-25
- reasoning_effort_levels: add "max" to deepseek-v4-flash, deepseek-v4-pro,
  glm-5.2 and glm-5.3-flash; add "none" to kimi-k2.6 (it really disables
  thinking there); drop "none" from glm-5.3 (upstream runs it as "max")

Context windows, output limits and vision flags are unchanged and were
checked against the same endpoint.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 ...odel_prices_and_context_window_backup.json | 66 ++++++++++---------
 model_prices_and_context_window.json          | 66 ++++++++++---------
 2 files changed, 70 insertions(+), 62 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index a678359210f..fcd2726b6dc 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -78778,9 +78778,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 8.4e-07,
-        "output_cost_per_token": 2.64e-06,
-        "cache_read_input_token_cost": 1.56e-07,
+        "input_cost_per_token": 5.6e-07,
+        "output_cost_per_token": 1.76e-06,
+        "cache_read_input_token_cost": 1.04e-07,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78788,7 +78788,6 @@
         "supports_tool_choice": true,
         "supports_reasoning": true,
         "reasoning_effort_levels": [
-            "none",
             "low",
             "medium",
             "high",
@@ -78803,9 +78802,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 3e-07,
-        "cache_read_input_token_cost": 1.8e-08,
+        "input_cost_per_token": 6e-08,
+        "output_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 1.2e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78816,7 +78815,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78828,9 +78828,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 8.4e-07,
-        "output_cost_per_token": 2.64e-06,
-        "cache_read_input_token_cost": 1.56e-07,
+        "input_cost_per_token": 5.6e-07,
+        "output_cost_per_token": 1.76e-06,
+        "cache_read_input_token_cost": 1.04e-07,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78841,7 +78841,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78852,8 +78853,8 @@
         "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 3.6e-08,
-        "output_cost_per_token": 2.4e-07,
+        "input_cost_per_token": 2.4e-08,
+        "output_cost_per_token": 1.6e-07,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78873,9 +78874,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 7.92e-07,
-        "output_cost_per_token": 2.376e-06,
-        "cache_read_input_token_cost": 2.6e-08,
+        "input_cost_per_token": 5.28e-07,
+        "output_cost_per_token": 1.584e-06,
+        "cache_read_input_token_cost": 1.7e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78886,7 +78887,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78897,9 +78899,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 2.64e-07,
-        "output_cost_per_token": 7.92e-07,
-        "cache_read_input_token_cost": 8e-09,
+        "input_cost_per_token": 1.76e-07,
+        "output_cost_per_token": 5.28e-07,
+        "cache_read_input_token_cost": 5e-09,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78910,7 +78912,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78921,9 +78924,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 5.7e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 9.6e-08,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 1.6e-06,
+        "cache_read_input_token_cost": 6.4e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78931,6 +78934,7 @@
         "supports_tool_choice": true,
         "supports_reasoning": true,
         "reasoning_effort_levels": [
+            "none",
             "low",
             "medium",
             "high"
@@ -78945,9 +78949,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 5.7e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 1.14e-07,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 1.6e-06,
+        "cache_read_input_token_cost": 7.6e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78969,9 +78973,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 2.7e-07,
-        "output_cost_per_token": 1.92e-06,
-        "cache_read_input_token_cost": 2.7e-07,
+        "input_cost_per_token": 1.8e-07,
+        "output_cost_per_token": 1.28e-06,
+        "cache_read_input_token_cost": 2e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index a678359210f..fcd2726b6dc 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -78778,9 +78778,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 8.4e-07,
-        "output_cost_per_token": 2.64e-06,
-        "cache_read_input_token_cost": 1.56e-07,
+        "input_cost_per_token": 5.6e-07,
+        "output_cost_per_token": 1.76e-06,
+        "cache_read_input_token_cost": 1.04e-07,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78788,7 +78788,6 @@
         "supports_tool_choice": true,
         "supports_reasoning": true,
         "reasoning_effort_levels": [
-            "none",
             "low",
             "medium",
             "high",
@@ -78803,9 +78802,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 9e-08,
-        "output_cost_per_token": 3e-07,
-        "cache_read_input_token_cost": 1.8e-08,
+        "input_cost_per_token": 6e-08,
+        "output_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 1.2e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78816,7 +78815,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78828,9 +78828,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 8.4e-07,
-        "output_cost_per_token": 2.64e-06,
-        "cache_read_input_token_cost": 1.56e-07,
+        "input_cost_per_token": 5.6e-07,
+        "output_cost_per_token": 1.76e-06,
+        "cache_read_input_token_cost": 1.04e-07,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78841,7 +78841,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78852,8 +78853,8 @@
         "max_tokens": 131072,
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 3.6e-08,
-        "output_cost_per_token": 2.4e-07,
+        "input_cost_per_token": 2.4e-08,
+        "output_cost_per_token": 1.6e-07,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78873,9 +78874,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 7.92e-07,
-        "output_cost_per_token": 2.376e-06,
-        "cache_read_input_token_cost": 2.6e-08,
+        "input_cost_per_token": 5.28e-07,
+        "output_cost_per_token": 1.584e-06,
+        "cache_read_input_token_cost": 1.7e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78886,7 +78887,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78897,9 +78899,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 2.64e-07,
-        "output_cost_per_token": 7.92e-07,
-        "cache_read_input_token_cost": 8e-09,
+        "input_cost_per_token": 1.76e-07,
+        "output_cost_per_token": 5.28e-07,
+        "cache_read_input_token_cost": 5e-09,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78910,7 +78912,8 @@
             "low",
             "medium",
             "high",
-            "xhigh"
+            "xhigh",
+            "max"
         ],
         "supports_response_schema": true,
         "supports_system_messages": true,
@@ -78921,9 +78924,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 5.7e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 9.6e-08,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 1.6e-06,
+        "cache_read_input_token_cost": 6.4e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78931,6 +78934,7 @@
         "supports_tool_choice": true,
         "supports_reasoning": true,
         "reasoning_effort_levels": [
+            "none",
             "low",
             "medium",
             "high"
@@ -78945,9 +78949,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 5.7e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 1.14e-07,
+        "input_cost_per_token": 3.8e-07,
+        "output_cost_per_token": 1.6e-06,
+        "cache_read_input_token_cost": 7.6e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,
@@ -78969,9 +78973,9 @@
         "max_tokens": 131072,
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "input_cost_per_token": 2.7e-07,
-        "output_cost_per_token": 1.92e-06,
-        "cache_read_input_token_cost": 2.7e-07,
+        "input_cost_per_token": 1.8e-07,
+        "output_cost_per_token": 1.28e-06,
+        "cache_read_input_token_cost": 2e-08,
         "litellm_provider": "clf_ai_gateway",
         "mode": "chat",
         "supports_function_calling": true,