From 4d16d3bf560880705f79a49e2e67d4b88e77b493 Mon Sep 17 00:00:00 2001 From: shrey kharbanda Date: Thu, 24 Sep 2026 04:57:18 +0000 Subject: [PATCH] fix(sail): gemma-4-31B-it context window is 256000 --- litellm/model_prices_and_context_window_backup.json | 12 +++++++++--- model_prices_and_context_window.json | 12 +++++++++--- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index db4e4754f9e..742fca4f6d5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -58059,12 +58059,18 @@ "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-31B-it": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, "input_cost_per_token": 4e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 6e-07, + "cache_read_input_token_cost_balanced": 8e-08, + "input_cost_per_token_flex": 6e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index db4e4754f9e..742fca4f6d5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -58059,12 +58059,18 @@ "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-31B-it": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, "input_cost_per_token": 4e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 6e-07, + "cache_read_input_token_cost_balanced": 8e-08, + "input_cost_per_token_flex": 6e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true,