tokencostauto 0.1.449__py3-none-any.whl → 0.1.462__py3-none-any.whl

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,
@@ -17766,8 +17766,8 @@
         "supports_tool_choice": true
     },
     "gemini/gemini-2.5-flash-lite": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_audio_token": 5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
         "max_audio_length_hours": 8.4,
@@ -17813,8 +17813,8 @@
         "tpm": 250000
     },
     "gemini-2.5-flash-lite": {
-        "cache_read_input_token_cost": 2.5e-08,
-        "input_cost_per_audio_token": 5e-07,
+        "cache_read_input_token_cost": 1e-08,
+        "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_audio_length_hours": 8.4,
@@ -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",
@@ -18720,13 +18720,14 @@
         "supports_vision": true
     },
     "groq/openai/gpt-oss-20b": {
-        "input_cost_per_token": 1e-07,
+        "cache_read_input_token_cost": 3.75e-08,
+        "input_cost_per_token": 7.5e-08,
         "litellm_provider": "groq",
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
-        "output_cost_per_token": 5e-07,
+        "output_cost_per_token": 3e-07,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -18735,13 +18736,14 @@
         "supports_web_search": true
     },
     "groq/openai/gpt-oss-120b": {
+        "cache_read_input_token_cost": 7.5e-08,
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "groq",
         "max_input_tokens": 131072,
         "max_output_tokens": 32766,
         "max_tokens": 32766,
         "mode": "chat",
-        "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token": 6e-07,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -20623,7 +20625,7 @@
         "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 +20644,7 @@
         "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 +22963,7 @@
         "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",
@@ -23080,7 +23082,7 @@
         "supports_tool_choice": true
     },
     "gemini-2.5-flash-lite-preview-09-2025": {
-        "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost": 1e-08,
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -23260,7 +23262,7 @@
         "supports_web_search": true
     },
     "gemini/gemini-2.5-flash-lite-preview-09-2025": {
-        "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost": 1e-08,
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -23451,7 +23453,7 @@
         "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 +23472,7 @@
         "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 +23722,22 @@
         "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 +23749,28 @@
         "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 +24276,7 @@
         "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 +24411,7 @@
         "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 +26097,7 @@
         "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 +26133,7 @@
         "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 +26204,7 @@
         "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 +26237,7 @@
         "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 +26994,7 @@
         "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 +27065,7 @@
         "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 +27098,7 @@
         "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",
@@ -28134,15 +28136,15 @@
         "tool_use_system_prompt_tokens": 159
     },
     "us.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,
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_read_input_token_cost": 5.5e-07,
+        "input_cost_per_token": 5.5e-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,
+        "output_cost_per_token": 2.75e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -28658,7 +28660,7 @@
         "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 +28675,7 @@
         "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 +28690,7 @@
         "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 +28705,7 @@
         "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 +29167,7 @@
         "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 +29527,7 @@
         "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 +31718,7 @@
         "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 +31755,7 @@
         "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 +31823,7 @@
     "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 +31854,7 @@
     "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 +31963,7 @@
         "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 +32299,7 @@
         "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 +32329,7 @@
         "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",
@@ -33982,13 +33985,13 @@
         ]
     },
     "vertex_ai/zai-org/glm-4.7-maas": {
-        "input_cost_per_token": 3e-07,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "vertex_ai-zai_models",
         "max_input_tokens": 200000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token": 2.2e-06,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -35445,5 +35448,214 @@
         "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
+    },
+    "azure/gpt-5.2-codex": {
+        "cache_read_input_token_cost": 1.75e-07,
+        "input_cost_per_token": 1.75e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1.4e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/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": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "dall-e-2": {
+        "input_cost_per_image": 0.02,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits",
+            "/v1/images/variations"
+        ]
+    },
+    "dall-e-3": {
+        "input_cost_per_image": 0.04,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "supported_endpoints": [
+            "/v1/images/generations"
+        ]
+    },
+    "gemini-2.5-computer-use-preview-10-2025": {
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_above_200k_tokens": 1.5e-05,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.2-codex": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.2": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.1-codex-max": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.1-codex-mini": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "sarvam/sarvam-m": {
+        "cache_creation_input_token_cost": 0,
+        "cache_creation_input_token_cost_above_1hr": 0,
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 0,
+        "litellm_provider": "sarvam",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_reasoning": true
     }
 }

{tokencostauto-0.1.449.dist-info → tokencostauto-0.1.462.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.449
+Version: 0.1.462
 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-0.1.462.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=aDFZZR6fnd6N4Fdc-zL3m6tsqmR8KiCelIqRuvx8oas,1265556
+tokencostauto-0.1.462.dist-info/licenses/LICENSE,sha256=4PLv_CD6Ughnsvg_nM2XeTqGwVK6lQVR77kVWbPq-0U,1065
+tokencostauto-0.1.462.dist-info/METADATA,sha256=bLqFKmPlxZSRF2VHZpr91xFCtaAPO1hdtx9yMt8TEbg,204076
+tokencostauto-0.1.462.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
+tokencostauto-0.1.462.dist-info/top_level.txt,sha256=szZQTUJRotfIaeZCDsOgvofIkLt2ak88RP13oI51-TU,14
+tokencostauto-0.1.462.dist-info/RECORD,,

{tokencostauto-0.1.449.dist-info → tokencostauto-0.1.462.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tokencostauto-0.1.449.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=4MmQTNpNS3KNIbeLVss71S1D9YYkN2nLCmPIhBnMLl4,1258836
-tokencostauto-0.1.449.dist-info/licenses/LICENSE,sha256=4PLv_CD6Ughnsvg_nM2XeTqGwVK6lQVR77kVWbPq-0U,1065
-tokencostauto-0.1.449.dist-info/METADATA,sha256=Rw8U0zJEphYOT0W-Q0fuJbhuT5f91sQdzKXaXghGg-g,204076
-tokencostauto-0.1.449.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tokencostauto-0.1.449.dist-info/top_level.txt,sha256=szZQTUJRotfIaeZCDsOgvofIkLt2ak88RP13oI51-TU,14
-tokencostauto-0.1.449.dist-info/RECORD,,