From 671559e591ccbc24d540e9bf9be76f8631f59f16 Mon Sep 17 00:00:00 2001
From: mateo <mateo@berri.ai>
Date: Wed, 2 Sep 2026 20:35:29 +0000
Subject: [PATCH] fix(model_prices): set watsonx max_tokens equal to
 max_output_tokens per registry convention

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

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index f6316fba884..2e717b52b28 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -46960,7 +46960,7 @@
         "supports_vision": false
     },
     "watsonx/ibm/granite-4-h-small": {
-        "max_tokens": 131072,
+        "max_tokens": 20480,
         "max_input_tokens": 131072,
         "max_output_tokens": 20480,
         "input_cost_per_token": 6.36e-08,
@@ -47093,7 +47093,7 @@
         "supports_vision": true
     },
     "watsonx/meta-llama/llama-3-3-70b-instruct": {
-        "max_tokens": 131072,
+        "max_tokens": 128000,
         "max_input_tokens": 131072,
         "max_output_tokens": 128000,
         "input_cost_per_token": 7.526e-07,
@@ -47106,7 +47106,7 @@
         "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
     },
     "watsonx/meta-llama/llama-4-maverick-17b": {
-        "max_tokens": 131072,
+        "max_tokens": 128000,
         "max_input_tokens": 131072,
         "max_output_tokens": 128000,
         "input_cost_per_token": 3.71e-07,
@@ -47119,7 +47119,7 @@
         "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
     },
     "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": {
-        "max_tokens": 131072,
+        "max_tokens": 128000,
         "max_input_tokens": 131072,
         "max_output_tokens": 128000,
         "input_cost_per_token": 3.71e-07,
@@ -47168,7 +47168,7 @@
         "supports_vision": false
     },
     "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": {
-        "max_tokens": 131072,
+        "max_tokens": 32000,
         "max_input_tokens": 131072,
         "max_output_tokens": 32000,
         "input_cost_per_token": 1.06e-07,
@@ -47193,7 +47193,7 @@
         "supports_vision": true
     },
     "watsonx/openai/gpt-oss-120b": {
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "max_input_tokens": 131072,
         "max_output_tokens": 8192,
         "input_cost_per_token": 1.59e-07,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index f6316fba884..2e717b52b28 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -46960,7 +46960,7 @@
         "supports_vision": false
     },
     "watsonx/ibm/granite-4-h-small": {
-        "max_tokens": 131072,
+        "max_tokens": 20480,
         "max_input_tokens": 131072,
         "max_output_tokens": 20480,
         "input_cost_per_token": 6.36e-08,
@@ -47093,7 +47093,7 @@
         "supports_vision": true
     },
     "watsonx/meta-llama/llama-3-3-70b-instruct": {
-        "max_tokens": 131072,
+        "max_tokens": 128000,
         "max_input_tokens": 131072,
         "max_output_tokens": 128000,
         "input_cost_per_token": 7.526e-07,
@@ -47106,7 +47106,7 @@
         "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
     },
     "watsonx/meta-llama/llama-4-maverick-17b": {
-        "max_tokens": 131072,
+        "max_tokens": 128000,
         "max_input_tokens": 131072,
         "max_output_tokens": 128000,
         "input_cost_per_token": 3.71e-07,
@@ -47119,7 +47119,7 @@
         "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
     },
     "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": {
-        "max_tokens": 131072,
+        "max_tokens": 128000,
         "max_input_tokens": 131072,
         "max_output_tokens": 128000,
         "input_cost_per_token": 3.71e-07,
@@ -47168,7 +47168,7 @@
         "supports_vision": false
     },
     "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": {
-        "max_tokens": 131072,
+        "max_tokens": 32000,
         "max_input_tokens": 131072,
         "max_output_tokens": 32000,
         "input_cost_per_token": 1.06e-07,
@@ -47193,7 +47193,7 @@
         "supports_vision": true
     },
     "watsonx/openai/gpt-oss-120b": {
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "max_input_tokens": 131072,
         "max_output_tokens": 8192,
         "input_cost_per_token": 1.59e-07,