From 1aa214e69ce83d89d9ca42b883e583a44a776c3f Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Fri, 28 Aug 2026 09:19:22 -0700 Subject: [PATCH] fix(registry): align gemini-omni-flash-preview limits with the models API The models API reports 131072 input / 65536 output for the preview model and the Interactions API accepts 100k tokens but rejects 130k, so the 1,048,576 input limit copied from the docs was wrong. --- litellm/model_prices_and_context_window_backup.json | 6 +++--- model_prices_and_context_window.json | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f4f627d02fa..537fe511253 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -22994,9 +22994,9 @@ "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f4f627d02fa..537fe511253 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -22994,9 +22994,9 @@ "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06,