diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 12a8ee85..caca89d2 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -13864,8 +13864,56 @@ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, - "max_input_tokens": 32768, + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "lemonade/gpt-oss-20b-mxfp4-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "lemonade/gpt-oss-120b-mxfp-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "lemonade/Gemma-3-4b-it-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "lemonade/Qwen3-4B-Instruct-2507-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 262144, + "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, @@ -17386,6 +17434,8 @@ }, "openrouter/anthropic/claude-opus-4": { "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -17396,6 +17446,7 @@ "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, @@ -17403,6 +17454,9 @@ }, "openrouter/anthropic/claude-opus-4.1": { "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, + "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", "max_input_tokens": 200000, @@ -17413,6 +17467,7 @@ "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, @@ -17420,6 +17475,10 @@ }, "openrouter/anthropic/claude-sonnet-4": { "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, @@ -17432,6 +17491,7 @@ "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, @@ -17439,9 +17499,13 @@ }, "openrouter/anthropic/claude-sonnet-4.5": { "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -17451,6 +17515,7 @@ "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, diff --git a/model_prices_and_context_window.sha256 b/model_prices_and_context_window.sha256 index 7b35b5cc..99cdc582 100644 --- a/model_prices_and_context_window.sha256 +++ b/model_prices_and_context_window.sha256 @@ -1 +1 @@ -427e5769f5d75bd293703a6c2cdc6a2c77b5b68d667f1bd7c4a66a50ff428684 +1a8b6d66c8e67bcccfa9913a7499e090f0f53d890f63f68df2d4e8ba7ffbee7e