From 9b43fdff330739318186d089a6b58b335f34dbc1 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Fri, 28 Aug 2026 19:33:52 +0000
Subject: [PATCH] feat(models): sync together_ai model registry 2026-08-28

---
 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 b9415c17d81..0ee8fc113e2 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -38682,7 +38682,7 @@
     "together_ai/openai/gpt-oss-20b": {
         "input_cost_per_token": 5e-08,
         "litellm_provider": "together_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
         "source": "https://www.together.ai/models/gpt-oss-20b",
@@ -38904,14 +38904,14 @@
         "source": "https://docs.together.ai/docs/serverless-models"
     },
     "together_ai/Qwen/Qwen3.8-2.4T-A95B": {
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 2.5e-06,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token": 2e-06,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1010000,
         "max_output_tokens": 1010000,
         "max_tokens": 1010000,
         "mode": "chat",
-        "output_cost_per_token": 6.25e-06,
+        "output_cost_per_token": 6e-06,
         "source": "https://docs.together.ai/docs/serverless-models",
         "supports_prompt_caching": true
     },
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index b9415c17d81..0ee8fc113e2 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -38682,7 +38682,7 @@
     "together_ai/openai/gpt-oss-20b": {
         "input_cost_per_token": 5e-08,
         "litellm_provider": "together_ai",
-        "max_input_tokens": 128000,
+        "max_input_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
         "source": "https://www.together.ai/models/gpt-oss-20b",
@@ -38904,14 +38904,14 @@
         "source": "https://docs.together.ai/docs/serverless-models"
     },
     "together_ai/Qwen/Qwen3.8-2.4T-A95B": {
-        "cache_read_input_token_cost": 5e-07,
-        "input_cost_per_token": 2.5e-06,
+        "cache_read_input_token_cost": 2.5e-07,
+        "input_cost_per_token": 2e-06,
         "litellm_provider": "together_ai",
         "max_input_tokens": 1010000,
         "max_output_tokens": 1010000,
         "max_tokens": 1010000,
         "mode": "chat",
-        "output_cost_per_token": 6.25e-06,
+        "output_cost_per_token": 6e-06,
         "source": "https://docs.together.ai/docs/serverless-models",
         "supports_prompt_caching": true
     },