tokencostauto 0.1.449__tar.gz → 0.1.451__tar.gz

{tokencostauto-0.1.449/tokencostauto.egg-info → tokencostauto-0.1.451}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.449
+Version: 0.1.451
 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-0.1.449 → tokencostauto-0.1.451}/pyproject.toml

@@ -11,7 +11,7 @@ tokencostauto = ["model_prices.json"]
 [project]
 
 name = "tokencostauto"
-version = "0.1.449"
+version = "0.1.451"
 
 authors = [
     { name = "Trisha Pan", email = "trishaepan@gmail.com" },

{tokencostauto-0.1.449 → tokencostauto-0.1.451}/tokencostauto/model_prices.json

@@ -16617,14 +16617,14 @@
         "supports_tool_choice": true
     },
     "azure_ai/grok-3": {
-        "input_cost_per_token": 3.3e-06,
+        "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 1.65e-05,
-        "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_response_schema": false,
         "supports_tool_choice": true,
@@ -16660,14 +16660,14 @@
         "supports_web_search": true
     },
     "azure_ai/grok-3-mini": {
-        "input_cost_per_token": 2.75e-07,
+        "input_cost_per_token": 2.5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 1.38e-06,
-        "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/",
+        "output_cost_per_token": 1.27e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": false,
@@ -18179,7 +18179,7 @@
         "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",
@@ -18218,7 +18218,7 @@
         "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",
@@ -18256,7 +18256,7 @@
         "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",
@@ -18357,7 +18357,7 @@
         "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",
@@ -18396,7 +18396,7 @@
         "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",
@@ -18433,7 +18433,7 @@
         "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",
@@ -20623,7 +20623,7 @@
         "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",
@@ -20642,7 +20642,7 @@
         "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",
@@ -22961,7 +22961,7 @@
         "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": "responses",
@@ -23451,7 +23451,7 @@
         "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",
@@ -23470,7 +23470,7 @@
         "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",
@@ -23720,22 +23720,22 @@
         "supports_tool_choice": true
     },
     "azure_ai/grok-4": {
-        "input_cost_per_token": 5.5e-06,
+        "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 2.75e-05,
-        "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/",
+        "output_cost_per_token": 1.5e-05,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
     "azure_ai/grok-4-fast-non-reasoning": {
-        "input_cost_per_token": 4.3e-07,
-        "output_cost_per_token": 1.73e-06,
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
@@ -23747,28 +23747,28 @@
         "supports_web_search": true
     },
     "azure_ai/grok-4-fast-reasoning": {
-        "input_cost_per_token": 4.3e-07,
-        "output_cost_per_token": 1.73e-06,
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 5e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701",
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_web_search": true
     },
     "azure_ai/grok-code-fast-1": {
-        "input_cost_per_token": 3.5e-06,
+        "input_cost_per_token": 2e-07,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 1.75e-05,
-        "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/",
+        "output_cost_per_token": 1.5e-06,
+        "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -24274,7 +24274,7 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 272000,
         "max_tokens": 272000,
         "mode": "responses",
@@ -24409,7 +24409,7 @@
         "input_cost_per_token": 1.5e-05,
         "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 272000,
         "max_tokens": 272000,
         "mode": "responses",
@@ -26095,7 +26095,7 @@
         "input_cost_per_token": 1.25e-06,
         "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",
@@ -26131,7 +26131,7 @@
         "input_cost_per_token": 1.25e-06,
         "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",
@@ -26202,7 +26202,7 @@
         "input_cost_per_token": 1.25e-06,
         "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": "responses",
@@ -26235,7 +26235,7 @@
         "input_cost_per_token": 2.5e-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": "responses",
@@ -26992,7 +26992,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -27063,7 +27063,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -27096,7 +27096,7 @@
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -28658,7 +28658,7 @@
         "input_cost_per_token": 1.24999e-06,
         "input_dbu_cost_per_token": 1.7857e-05,
         "litellm_provider": "databricks",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "metadata": {
@@ -28673,7 +28673,7 @@
         "input_cost_per_token": 1.24999e-06,
         "input_dbu_cost_per_token": 1.7857e-05,
         "litellm_provider": "databricks",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "metadata": {
@@ -28688,7 +28688,7 @@
         "input_cost_per_token": 2.4997000000000006e-07,
         "input_dbu_cost_per_token": 3.571e-06,
         "litellm_provider": "databricks",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "metadata": {
@@ -28703,7 +28703,7 @@
         "input_cost_per_token": 4.998e-08,
         "input_dbu_cost_per_token": 7.14e-07,
         "litellm_provider": "databricks",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "metadata": {
@@ -29165,7 +29165,7 @@
         "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": "responses",
@@ -29525,6 +29525,7 @@
         "supports_pdf_input": true
     },
     "cerebras/zai-glm-4.6": {
+        "deprecation_date": "2026-01-20",
         "input_cost_per_token": 2.25e-06,
         "litellm_provider": "cerebras",
         "max_input_tokens": 128000,
@@ -31715,7 +31716,7 @@
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -31752,7 +31753,7 @@
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -31820,7 +31821,7 @@
     "gpt-5.2-pro": {
         "input_cost_per_token": 2.1e-05,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -31851,7 +31852,7 @@
     "gpt-5.2-pro-2025-12-11": {
         "input_cost_per_token": 2.1e-05,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -31960,7 +31961,7 @@
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -32296,7 +32297,7 @@
         "cache_read_input_token_cost": 1.75e-07,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -32326,7 +32327,7 @@
         "input_cost_per_image": 0,
         "input_cost_per_token": 2.1e-05,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -35445,5 +35446,70 @@
         "supports_response_schema": true,
         "supports_audio_input": true,
         "supports_audio_output": true
+    },
+    "cerebras/zai-glm-4.7": {
+        "input_cost_per_token": 2.25e-06,
+        "litellm_provider": "cerebras",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 2.75e-06,
+        "source": "https://www.cerebras.ai/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "gpt-5.2-codex": {
+        "cache_read_input_token_cost": 1.75e-07,
+        "cache_read_input_token_cost_priority": 3.5e-07,
+        "input_cost_per_token": 1.75e-06,
+        "input_cost_per_token_priority": 3.5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.4e-05,
+        "output_cost_per_token_priority": 2.8e-05,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "openrouter/openai/gpt-5.2-codex": {
+        "cache_read_input_token_cost": 1.75e-07,
+        "input_cost_per_token": 1.75e-06,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.4e-05,
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_reasoning": true,
+        "supports_tool_choice": true
     }
 }

{tokencostauto-0.1.449 → tokencostauto-0.1.451/tokencostauto.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.449
+Version: 0.1.451
 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