diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c3f312beb6..c8728d286b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12367,7 +12367,7 @@ "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", @@ -12405,7 +12405,7 @@ "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", @@ -12440,7 +12440,7 @@ "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", @@ -12472,7 +12472,7 @@ "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", @@ -12538,7 +12538,7 @@ "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", @@ -12576,7 +12576,7 @@ "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", @@ -12613,7 +12613,7 @@ "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", @@ -12648,7 +12648,7 @@ "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", @@ -16842,7 +16842,7 @@ "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", @@ -16861,7 +16861,7 @@ "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", @@ -16880,7 +16880,7 @@ "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", @@ -16899,7 +16899,7 @@ "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", @@ -16918,7 +16918,7 @@ "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 755318159b..88f3e9d057 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -12367,7 +12367,7 @@ "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", @@ -12405,7 +12405,7 @@ "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", @@ -12440,7 +12440,7 @@ "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", @@ -12472,7 +12472,7 @@ "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", @@ -12538,7 +12538,7 @@ "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", @@ -12576,7 +12576,7 @@ "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", @@ -12613,7 +12613,7 @@ "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", @@ -12648,7 +12648,7 @@ "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", @@ -16842,7 +16842,7 @@ "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", @@ -16861,7 +16861,7 @@ "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", @@ -16880,7 +16880,7 @@ "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", @@ -16899,7 +16899,7 @@ "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", @@ -16918,7 +16918,7 @@ "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",