tokencostauto 0.1.376__py3-none-any.whl → 0.1.380__py3-none-any.whl

tokencostauto/model_prices.json

@@ -553,6 +553,7 @@
         "supports_tool_choice": true
     },
     "ft:gpt-4o-2024-08-06": {
+        "cache_read_input_token_cost": 1.875e-06,
         "input_cost_per_token": 3.75e-06,
         "input_cost_per_token_batches": 1.875e-06,
         "litellm_provider": "openai",
@@ -565,6 +566,7 @@
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
+        "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
@@ -587,29 +589,28 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_tool_choice": true
     },
     "ft:davinci-002": {
-        "input_cost_per_token": 2e-06,
+        "input_cost_per_token": 1.2e-05,
         "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 16384,
         "mode": "completion",
-        "output_cost_per_token": 2e-06,
+        "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 1e-06
     },
     "ft:babbage-002": {
-        "input_cost_per_token": 4e-07,
+        "input_cost_per_token": 1.6e-06,
         "input_cost_per_token_batches": 2e-07,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 16384,
         "mode": "completion",
-        "output_cost_per_token": 4e-07,
+        "output_cost_per_token": 1.6e-06,
         "output_cost_per_token_batches": 2e-07
     },
     "text-embedding-3-large": {
@@ -7234,7 +7235,7 @@
         "output_cost_per_token": 0.0
     },
     "databricks/databricks-meta-llama-3-1-405b-instruct": {
-        "input_cost_per_token": 5e-06,
+        "input_cost_per_token": 5.00003e-06,
         "input_dbu_cost_per_token": 7.1429e-05,
         "litellm_provider": "databricks",
         "max_input_tokens": 128000,
@@ -7244,8 +7245,8 @@
             "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 1.500002e-05,
-        "output_db_cost_per_token": 0.000214286,
+        "output_cost_per_token": 1.5000020000000002e-05,
+        "output_dbu_cost_per_token": 0.000214286,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
     },
@@ -7292,7 +7293,7 @@
             "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 2.99999e-06,
+        "output_cost_per_token": 2.9999900000000002e-06,
         "output_dbu_cost_per_token": 4.2857e-05,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
@@ -7308,7 +7309,7 @@
             "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 1.5000300000000002e-06,
         "output_dbu_cost_per_token": 2.1429e-05,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
@@ -7324,13 +7325,13 @@
             "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 9.9902e-07,
+        "output_cost_per_token": 1.00002e-06,
         "output_dbu_cost_per_token": 1.4286e-05,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
     },
     "databricks/databricks-mpt-30b-instruct": {
-        "input_cost_per_token": 9.9902e-07,
+        "input_cost_per_token": 1.00002e-06,
         "input_dbu_cost_per_token": 1.4286e-05,
         "litellm_provider": "databricks",
         "max_input_tokens": 8192,
@@ -7340,7 +7341,7 @@
             "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 9.9902e-07,
+        "output_cost_per_token": 1.00002e-06,
         "output_dbu_cost_per_token": 1.4286e-05,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
@@ -7377,7 +7378,7 @@
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
     },
     "databricks/databricks-gte-large-en": {
-        "input_cost_per_token": 1.2999e-07,
+        "input_cost_per_token": 1.2999000000000001e-07,
         "input_dbu_cost_per_token": 1.857e-06,
         "litellm_provider": "databricks",
         "max_input_tokens": 8192,
@@ -7747,8 +7748,7 @@
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_system_messages": true,
-        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_tool_choice": true
     },
     "azure/gpt-4o-2024-11-20": {
         "deprecation_date": "2026-03-01",
@@ -13185,27 +13185,27 @@
         "output_cost_per_token": 9e-07
     },
     "databricks/databricks-claude-3-7-sonnet": {
-        "input_cost_per_token": 2.5e-06,
-        "input_dbu_cost_per_token": 3.571e-05,
+        "input_cost_per_token": 2.9999900000000002e-06,
+        "input_dbu_cost_per_token": 4.2857e-05,
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 128000,
         "max_tokens": 200000,
         "metadata": {
-            "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 1.7857e-05,
-        "output_db_cost_per_token": 0.000214286,
-        "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
+        "output_cost_per_token": 1.5000020000000002e-05,
+        "output_dbu_cost_per_token": 0.000214286,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
     "databricks/databricks-meta-llama-3-3-70b-instruct": {
-        "input_cost_per_token": 1.00002e-06,
-        "input_dbu_cost_per_token": 1.4286e-05,
+        "input_cost_per_token": 5.0001e-07,
+        "input_dbu_cost_per_token": 7.143e-06,
         "litellm_provider": "databricks",
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
@@ -13214,8 +13214,8 @@
             "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
         "mode": "chat",
-        "output_cost_per_token": 2.99999e-06,
-        "output_dbu_cost_per_token": 4.2857e-05,
+        "output_cost_per_token": 1.5000300000000002e-06,
+        "output_dbu_cost_per_token": 2.1429e-05,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
     },
@@ -14261,8 +14261,8 @@
         "tool_use_system_prompt_tokens": 159
     },
     "databricks/databricks-llama-4-maverick": {
-        "input_cost_per_token": 5e-06,
-        "input_dbu_cost_per_token": 7.143e-05,
+        "input_cost_per_token": 5.0001e-07,
+        "input_dbu_cost_per_token": 7.143e-06,
         "litellm_provider": "databricks",
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
@@ -14271,8 +14271,8 @@
             "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)."
         },
         "mode": "chat",
-        "output_cost_per_token": 1.5e-05,
-        "output_dbu_cost_per_token": 0.00021429,
+        "output_cost_per_token": 1.5000300000000002e-06,
+        "output_dbu_cost_per_token": 2.1429e-05,
         "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
         "supports_tool_choice": true
     },
@@ -28335,5 +28335,622 @@
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true
+    },
+    "claude-opus-4-5": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_creation_input_token_cost_above_1hr": 1e-05,
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "anthropic",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159
+    },
+    "databricks/databricks-claude-haiku-4-5": {
+        "input_cost_per_token": 1.00002e-06,
+        "input_dbu_cost_per_token": 1.4286e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 5.00003e-06,
+        "output_dbu_cost_per_token": 7.1429e-05,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-claude-opus-4": {
+        "input_cost_per_token": 1.5000020000000002e-05,
+        "input_dbu_cost_per_token": 0.000214286,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 32000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 7.500003000000001e-05,
+        "output_dbu_cost_per_token": 0.001071429,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-claude-opus-4-1": {
+        "input_cost_per_token": 1.5000020000000002e-05,
+        "input_dbu_cost_per_token": 0.000214286,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 32000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 7.500003000000001e-05,
+        "output_dbu_cost_per_token": 0.001071429,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-claude-opus-4-5": {
+        "input_cost_per_token": 5.00003e-06,
+        "input_dbu_cost_per_token": 7.1429e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 2.5000010000000002e-05,
+        "output_dbu_cost_per_token": 0.000357143,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-claude-sonnet-4": {
+        "input_cost_per_token": 2.9999900000000002e-06,
+        "input_dbu_cost_per_token": 4.2857e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 1.5000020000000002e-05,
+        "output_dbu_cost_per_token": 0.000214286,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-claude-sonnet-4-1": {
+        "input_cost_per_token": 2.9999900000000002e-06,
+        "input_dbu_cost_per_token": 4.2857e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 1.5000020000000002e-05,
+        "output_dbu_cost_per_token": 0.000214286,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-claude-sonnet-4-5": {
+        "input_cost_per_token": 2.9999900000000002e-06,
+        "input_dbu_cost_per_token": 4.2857e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 1.5000020000000002e-05,
+        "output_dbu_cost_per_token": 0.000214286,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-gemini-2-5-flash": {
+        "input_cost_per_token": 3.0001999999999996e-07,
+        "input_dbu_cost_per_token": 4.285999999999999e-06,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_tokens": 1048576,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 2.49998e-06,
+        "output_dbu_cost_per_token": 3.5714e-05,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-gemini-2-5-pro": {
+        "input_cost_per_token": 1.24999e-06,
+        "input_dbu_cost_per_token": 1.7857e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_tokens": 1048576,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 9.999990000000002e-06,
+        "output_dbu_cost_per_token": 0.000142857,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
+    "databricks/databricks-gemma-3-12b": {
+        "input_cost_per_token": 1.5000999999999998e-07,
+        "input_dbu_cost_per_token": 2.1429999999999996e-06,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "max_tokens": 128000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 5.0001e-07,
+        "output_dbu_cost_per_token": 7.143e-06,
+        "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
+    },
+    "databricks/databricks-gpt-5": {
+        "input_cost_per_token": 1.24999e-06,
+        "input_dbu_cost_per_token": 1.7857e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 400000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 9.999990000000002e-06,
+        "output_dbu_cost_per_token": 0.000142857,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving"
+    },
+    "databricks/databricks-gpt-5-1": {
+        "input_cost_per_token": 1.24999e-06,
+        "input_dbu_cost_per_token": 1.7857e-05,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 400000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 9.999990000000002e-06,
+        "output_dbu_cost_per_token": 0.000142857,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving"
+    },
+    "databricks/databricks-gpt-5-mini": {
+        "input_cost_per_token": 2.4997000000000006e-07,
+        "input_dbu_cost_per_token": 3.571e-06,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 400000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 1.9999700000000004e-06,
+        "output_dbu_cost_per_token": 2.8571e-05,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving"
+    },
+    "databricks/databricks-gpt-5-nano": {
+        "input_cost_per_token": 4.998e-08,
+        "input_dbu_cost_per_token": 7.14e-07,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 400000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 3.9998000000000007e-07,
+        "output_dbu_cost_per_token": 5.714000000000001e-06,
+        "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving"
+    },
+    "databricks/databricks-gpt-oss-120b": {
+        "input_cost_per_token": 1.5000999999999998e-07,
+        "input_dbu_cost_per_token": 2.1429999999999996e-06,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 5.9997e-07,
+        "output_dbu_cost_per_token": 8.571e-06,
+        "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
+    },
+    "databricks/databricks-gpt-oss-20b": {
+        "input_cost_per_token": 7e-08,
+        "input_dbu_cost_per_token": 1e-06,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 3.0001999999999996e-07,
+        "output_dbu_cost_per_token": 4.285999999999999e-06,
+        "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
+    },
+    "databricks/databricks-meta-llama-3-1-8b-instruct": {
+        "input_cost_per_token": 1.5000999999999998e-07,
+        "input_dbu_cost_per_token": 2.1429999999999996e-06,
+        "litellm_provider": "databricks",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "max_tokens": 200000,
+        "metadata": {
+            "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
+        },
+        "mode": "chat",
+        "output_cost_per_token": 4.5003000000000007e-07,
+        "output_dbu_cost_per_token": 6.429000000000001e-06,
+        "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
+    },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v3p2": {
+        "input_cost_per_token": 1.2e-06,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 163840,
+        "max_output_tokens": 163840,
+        "max_tokens": 163840,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/chirp": {
+        "input_cost_per_character": 3e-05,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_speech",
+        "source": "https://cloud.google.com/text-to-speech/pricing",
+        "supported_endpoints": [
+            "/v1/audio/speech"
+        ]
+    },
+    "zai/glm-4.6": {
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 2.2e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 128000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4.5": {
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 2.2e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4.5v": {
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 1.8e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4.5-x": {
+        "input_cost_per_token": 2.2e-06,
+        "output_cost_per_token": 8.9e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4.5-air": {
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 1.1e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4.5-airx": {
+        "input_cost_per_token": 1.1e-06,
+        "output_cost_per_token": 4.5e-06,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4-32b-0414-128k": {
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 1e-07,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "zai/glm-4.5-flash": {
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0,
+        "litellm_provider": "zai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "source": "https://docs.z.ai/guides/overview/pricing"
+    },
+    "amazon.nova-2-lite-v1:0": {
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "apac.amazon.nova-2-lite-v1:0": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.75e-06,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "eu.amazon.nova-2-lite-v1:0": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.75e-06,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "us.amazon.nova-2-lite-v1:0": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.75e-06,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_video_input": true,
+        "supports_vision": true
+    },
+    "deepseek/deepseek-v3.2": {
+        "input_cost_per_token": 2.8e-07,
+        "input_cost_per_token_cache_hit": 2.8e-08,
+        "litellm_provider": "deepseek",
+        "max_input_tokens": 163840,
+        "max_output_tokens": 163840,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 4e-07,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "ft:gpt-4.1-2025-04-14": {
+        "cache_read_input_token_cost": 7.5e-07,
+        "input_cost_per_token": 3e-06,
+        "input_cost_per_token_batches": 1.5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "ft:gpt-4.1-mini-2025-04-14": {
+        "cache_read_input_token_cost": 2e-07,
+        "input_cost_per_token": 8e-07,
+        "input_cost_per_token_batches": 4e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 3.2e-06,
+        "output_cost_per_token_batches": 1.6e-06,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "ft:gpt-4.1-nano-2025-04-14": {
+        "cache_read_input_token_cost": 5e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "litellm_provider": "openai",
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "output_cost_per_token_batches": 4e-07,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "ft:o4-mini-2025-04-16": {
+        "cache_read_input_token_cost": 1e-06,
+        "input_cost_per_token": 4e-06,
+        "input_cost_per_token_batches": 2e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "max_tokens": 100000,
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-05,
+        "output_cost_per_token_batches": 8e-06,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "openrouter/deepseek/deepseek-v3.2": {
+        "input_cost_per_token": 2.8e-07,
+        "input_cost_per_token_cache_hit": 2.8e-08,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 163840,
+        "max_output_tokens": 163840,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 4e-07,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "global.anthropic.claude-opus-4-5-20251101-v1:0": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159
     }
 }

{tokencostauto-0.1.376.dist-info → tokencostauto-0.1.380.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.376
+Version: 0.1.380
 Summary: To calculate token and translated USD cost of string and message calls to OpenAI, for example when used by AI agents
 Author-email: Trisha Pan <trishaepan@gmail.com>, Alex Reibman <areibman@gmail.com>, Pratyush Shukla <ps4534@nyu.edu>, Thiago MadPin <madpin@gmail.com>
 Project-URL: Homepage, https://github.com/madpin/tokencostaudo

tokencostauto-0.1.380.dist-info/RECORD

@@ -0,0 +1,9 @@
+tokencostauto/__init__.py,sha256=-4d_ryFH62SgNXPXA8vGPFZoAKtOBjnsg37EB_RkZG8,289
+tokencostauto/constants.py,sha256=_82MlTkTrdrwzyRosQD7d3JdgNP9KAUM-cZo8DE00P0,3395
+tokencostauto/costs.py,sha256=tXsgrTypq-dCHaHtoXcg2XepezWsAvZpl9gEsv_53iE,10679
+tokencostauto/model_prices.json,sha256=GQo71l4_B2fpRWiZG4LAsezobw-GzGLfU87ZiJ1NKbA,1032350
+tokencostauto-0.1.380.dist-info/licenses/LICENSE,sha256=4PLv_CD6Ughnsvg_nM2XeTqGwVK6lQVR77kVWbPq-0U,1065
+tokencostauto-0.1.380.dist-info/METADATA,sha256=92Bcw6am7Ru01cYZY5rvk444pTP3bl0nCg8eyqL2vtk,204076
+tokencostauto-0.1.380.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+tokencostauto-0.1.380.dist-info/top_level.txt,sha256=szZQTUJRotfIaeZCDsOgvofIkLt2ak88RP13oI51-TU,14
+tokencostauto-0.1.380.dist-info/RECORD,,

tokencostauto-0.1.376.dist-info/RECORD

@@ -1,9 +0,0 @@
-tokencostauto/__init__.py,sha256=-4d_ryFH62SgNXPXA8vGPFZoAKtOBjnsg37EB_RkZG8,289
-tokencostauto/constants.py,sha256=_82MlTkTrdrwzyRosQD7d3JdgNP9KAUM-cZo8DE00P0,3395
-tokencostauto/costs.py,sha256=tXsgrTypq-dCHaHtoXcg2XepezWsAvZpl9gEsv_53iE,10679
-tokencostauto/model_prices.json,sha256=ppcRA-03vZZBhzFyGsxg97rrHiitQmiQI38LHlTNX5A,1006772
-tokencostauto-0.1.376.dist-info/licenses/LICENSE,sha256=4PLv_CD6Ughnsvg_nM2XeTqGwVK6lQVR77kVWbPq-0U,1065
-tokencostauto-0.1.376.dist-info/METADATA,sha256=bvFO8RvysChQTCXeFlqeo75XRwE6caFjJWA07-Fx670,204076
-tokencostauto-0.1.376.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tokencostauto-0.1.376.dist-info/top_level.txt,sha256=szZQTUJRotfIaeZCDsOgvofIkLt2ak88RP13oI51-TU,14
-tokencostauto-0.1.376.dist-info/RECORD,,