diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 02b3cde217a..70904d13c7b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -37752,13 +37752,13 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "input_cost_per_token": 1.35e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5.4e-06, + "output_cost_per_token": 1.7e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" @@ -38585,13 +38585,13 @@ "supports_vision": true }, "vertex_ai/openai/gpt-oss-120b-maas": { - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 9e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-07, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, @@ -38673,13 +38673,13 @@ "supports_web_search": true }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "input_cost_per_token": 2.5e-07, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-06, + "output_cost_per_token": 8.8e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", @@ -38689,13 +38689,13 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-06, + "output_cost_per_token": 1.8e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index bc7330ec99c..3efc714dedf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -37843,13 +37843,13 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "input_cost_per_token": 1.35e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5.4e-06, + "output_cost_per_token": 1.7e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" @@ -38676,13 +38676,13 @@ "supports_vision": true }, "vertex_ai/openai/gpt-oss-120b-maas": { - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 9e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-07, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, @@ -38764,13 +38764,13 @@ "supports_web_search": true }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "input_cost_per_token": 2.5e-07, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-06, + "output_cost_per_token": 8.8e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", @@ -38780,13 +38780,13 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-06, + "output_cost_per_token": 1.8e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global"