diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e04c75655db..7aa362e494e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12735,7 +12735,7 @@ "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12773,7 +12773,7 @@ "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12808,7 +12808,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12840,7 +12840,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12906,7 +12906,7 @@ "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12944,7 +12944,7 @@ "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12981,7 +12981,7 @@ "input_cost_per_token_flex": 2.5e-08, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -13016,7 +13016,7 @@ "input_cost_per_token": 5e-08, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17210,7 +17210,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17229,7 +17229,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17248,7 +17248,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17267,7 +17267,7 @@ "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17286,7 +17286,7 @@ "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e04c75655db..7aa362e494e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -12735,7 +12735,7 @@ "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12773,7 +12773,7 @@ "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12808,7 +12808,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12840,7 +12840,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12906,7 +12906,7 @@ "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12944,7 +12944,7 @@ "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12981,7 +12981,7 @@ "input_cost_per_token_flex": 2.5e-08, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -13016,7 +13016,7 @@ "input_cost_per_token": 5e-08, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17210,7 +17210,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17229,7 +17229,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17248,7 +17248,7 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17267,7 +17267,7 @@ "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -17286,7 +17286,7 @@ "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat",