tokencostauto 0.1.355__py3-none-any.whl → 0.1.359__py3-none-any.whl

tokencostauto/model_prices.json

@@ -26620,10 +26620,12 @@
         "supports_web_search": true
     },
     "gemini-3-pro-preview": {
-        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
         "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_audio_length_hours": 8.4,
         "max_audio_per_prompt": 1,
@@ -26637,10 +26639,12 @@
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_batches": 6e-06,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions"
+            "/v1/completions",
+            "/v1/batch"
         ],
         "supported_modalities": [
             "text",
@@ -26664,9 +26668,11 @@
         "supports_web_search": true
     },
     "gemini/gemini-3-pro-preview": {
-        "cache_read_input_token_cost": 3.125e-07,
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "gemini",
         "max_audio_length_hours": 8.4,
         "max_audio_per_prompt": 1,
@@ -26680,11 +26686,13 @@
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_batches": 6e-06,
         "rpm": 2000,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
-            "/v1/completions"
+            "/v1/completions",
+            "/v1/batch"
         ],
         "supported_modalities": [
             "text",
@@ -27010,5 +27018,823 @@
         "supports_system_messages": false,
         "supports_tool_choice": true,
         "supports_vision": true
+    },
+    "azure/eu/gpt-5.1": {
+        "cache_read_input_token_cost": 1.4e-07,
+        "input_cost_per_token": 1.38e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/eu/gpt-5.1-chat": {
+        "cache_read_input_token_cost": 1.4e-07,
+        "input_cost_per_token": 1.38e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/eu/gpt-5.1-codex": {
+        "cache_read_input_token_cost": 1.4e-07,
+        "input_cost_per_token": 1.38e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.1e-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
+    },
+    "azure/eu/gpt-5.1-codex-mini": {
+        "cache_read_input_token_cost": 2.8e-08,
+        "input_cost_per_token": 2.75e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2.2e-06,
+        "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
+    },
+    "azure/global/gpt-5.1": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/global/gpt-5.1-chat": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/global/gpt-5.1-codex": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-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
+    },
+    "azure/global/gpt-5.1-codex-mini": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2e-06,
+        "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
+    },
+    "azure/gpt-5.1": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/gpt-5.1-chat": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/gpt-5.1-codex": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "input_cost_per_token": 1.25e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-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
+    },
+    "azure/gpt-5.1-codex-mini": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2e-06,
+        "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
+    },
+    "azure/us/gpt-5.1": {
+        "cache_read_input_token_cost": 1.4e-07,
+        "input_cost_per_token": 1.38e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/us/gpt-5.1-chat": {
+        "cache_read_input_token_cost": 1.4e-07,
+        "input_cost_per_token": 1.38e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+    "azure/us/gpt-5.1-codex": {
+        "cache_read_input_token_cost": 1.4e-07,
+        "input_cost_per_token": 1.38e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1.1e-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
+    },
+    "azure/us/gpt-5.1-codex-mini": {
+        "cache_read_input_token_cost": 2.8e-08,
+        "input_cost_per_token": 2.75e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2.2e-06,
+        "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
+    },
+    "vertex_ai/gemini-3-pro-preview": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65535,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_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_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "vertex_ai/gemini-2.5-flash-image": {
+        "litellm_provider": "vertex_ai-language-models",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.039,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image"
+    },
+    "vertex_ai/imagen-3.0-capability-001": {
+        "litellm_provider": "vertex_ai-image-models",
+        "mode": "image_generation",
+        "output_cost_per_image": 0.04,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects"
+    },
+    "cerebras/gpt-oss-120b": {
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "cerebras",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 6.9e-07,
+        "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "gemini-3-pro-image-preview": {
+        "input_cost_per_image": 0.0011,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 65536,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.134,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "gemini/gemini-3-pro-image-preview": {
+        "input_cost_per_image": 0.0011,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 65536,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.134,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "openrouter/google/gemini-3-pro-preview": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "openrouter",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65535,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_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_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "together_ai/zai-org/GLM-4.6": {
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "together_ai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 200000,
+        "max_tokens": 200000,
+        "mode": "chat",
+        "output_cost_per_token": 2.2e-06,
+        "source": "https://www.together.ai/models/glm-4-6",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "vertex_ai/gemini-3-pro-image-preview": {
+        "input_cost_per_image": 0.0011,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 65536,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.134,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+    },
+    "xai/grok-4-1-fast": {
+        "cache_read_input_token_cost": 5e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000.0,
+        "max_output_tokens": 2000000.0,
+        "max_tokens": 2000000.0,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
+        "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "xai/grok-4-1-fast-reasoning": {
+        "cache_read_input_token_cost": 5e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000.0,
+        "max_output_tokens": 2000000.0,
+        "max_tokens": 2000000.0,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
+        "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "xai/grok-4-1-fast-reasoning-latest": {
+        "cache_read_input_token_cost": 5e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000.0,
+        "max_output_tokens": 2000000.0,
+        "max_tokens": 2000000.0,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
+        "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "xai/grok-4-1-fast-non-reasoning": {
+        "cache_read_input_token_cost": 5e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000.0,
+        "max_output_tokens": 2000000.0,
+        "max_tokens": 2000000.0,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
+        "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "xai/grok-4-1-fast-non-reasoning-latest": {
+        "cache_read_input_token_cost": 5e-08,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_128k_tokens": 4e-07,
+        "litellm_provider": "xai",
+        "max_input_tokens": 2000000.0,
+        "max_output_tokens": 2000000.0,
+        "max_tokens": 2000000.0,
+        "mode": "chat",
+        "output_cost_per_token": 5e-07,
+        "output_cost_per_token_above_128k_tokens": 1e-06,
+        "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning",
+        "supports_audio_input": true,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_web_search": true
     }
 }

{tokencostauto-0.1.355.dist-info → tokencostauto-0.1.359.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.355
+Version: 0.1.359
 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-0.1.359.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=xKn3KixDcaBUPEiu4bU-SsGyKuKSzKrO3bShsv2_fN4,988335
+tokencostauto-0.1.359.dist-info/licenses/LICENSE,sha256=4PLv_CD6Ughnsvg_nM2XeTqGwVK6lQVR77kVWbPq-0U,1065
+tokencostauto-0.1.359.dist-info/METADATA,sha256=0EhAJ8xBit7MZQWQd4XLYjVJNa-0LKq8DnBIRLmmDl8,204076
+tokencostauto-0.1.359.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+tokencostauto-0.1.359.dist-info/top_level.txt,sha256=szZQTUJRotfIaeZCDsOgvofIkLt2ak88RP13oI51-TU,14
+tokencostauto-0.1.359.dist-info/RECORD,,

tokencostauto-0.1.355.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=InjFY52gPQIEmewG9tXwCb1Np4Vd9NN9NvLe9Jo2aaw,959967
-tokencostauto-0.1.355.dist-info/licenses/LICENSE,sha256=4PLv_CD6Ughnsvg_nM2XeTqGwVK6lQVR77kVWbPq-0U,1065
-tokencostauto-0.1.355.dist-info/METADATA,sha256=5BQJ1JzFqsHoGiozHKRroLwZJuQow__oO0ex97FASfY,204076
-tokencostauto-0.1.355.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tokencostauto-0.1.355.dist-info/top_level.txt,sha256=szZQTUJRotfIaeZCDsOgvofIkLt2ak88RP13oI51-TU,14
-tokencostauto-0.1.355.dist-info/RECORD,,