From cf7aedf16dec4b9417430e864058407b689b1090 Mon Sep 17 00:00:00 2001 From: "oytun.kutrup" Date: Thu, 2 Oct 2025 15:46:13 +0300 Subject: [PATCH 1/2] Azure gpt-5 price update. --- model_prices_and_context_window.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 832ff36bfb86..f136e3721051 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1904,7 +1904,7 @@ ] }, "azure/gpt-5": { - "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, From abde54b7437989d61042c5b32b1c73c7f24c4cc0 Mon Sep 17 00:00:00 2001 From: "oytun.kutrup" Date: Thu, 2 Oct 2025 17:17:21 +0300 Subject: [PATCH 2/2] Some outdated Azure, Gemini, Bedrock prices updated. --- model_prices_and_context_window.json | 50 ++++++++++++++-------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f136e3721051..18fe4a6f4d33 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1205,13 +1205,13 @@ }, "azure/gpt-3.5-turbo-0125": { "deprecation_date": "2025-03-31", - "input_cost_per_token": 5e-07, + "input_cost_per_token": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.5e-06, + "output_cost_per_token": 1.65e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true @@ -1391,25 +1391,25 @@ "supports_tool_choice": true }, "azure/gpt-4-turbo": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -1559,7 +1559,7 @@ "supports_web_search": false }, "azure/gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", @@ -1591,7 +1591,7 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", @@ -1936,7 +1936,7 @@ "supports_vision": true }, "azure/gpt-5-2025-08-07": { - "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2001,7 +2001,7 @@ "supports_vision": true }, "azure/gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2033,7 +2033,7 @@ "supports_vision": true }, "azure/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2065,7 +2065,7 @@ "supports_vision": true }, "azure/gpt-5-mini-2025-08-07": { - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2097,7 +2097,7 @@ "supports_vision": true }, "azure/gpt-5-nano": { - "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2129,7 +2129,7 @@ "supports_vision": true }, "azure/gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2559,7 +2559,7 @@ "supports_vision": true }, "azure/o4-mini": { - "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost": 2.8e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -2588,7 +2588,7 @@ "supports_vision": true }, "azure/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost": 2.8e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -14002,13 +14002,13 @@ "supports_tool_choice": false }, "meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 9.9e-07, + "output_cost_per_token": 7.2e-07, "supports_function_calling": true, "supports_tool_choice": false }, @@ -14024,13 +14024,13 @@ "supports_tool_choice": false }, "meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 1.6e-07, "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true @@ -14058,13 +14058,13 @@ "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true @@ -14217,13 +14217,13 @@ "supports_tool_choice": true }, "mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 8e-06, + "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 1.2e-05, "supports_function_calling": true }, "mistral.mistral-large-2407-v1:0": { @@ -18292,7 +18292,7 @@ }, "text-embedding-004": { "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048,