PyPI - tokencostauto - Versions diffs - 0.1.441__py3-none-any.whl → 0.1.443__py3-none-any.whl - Mend

tokencostauto 0.1.441py3-none-any.whl → 0.1.443py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (7) hide show

tokencostauto/model_prices.json CHANGED Viewed

@@ -407,7 +407,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
-        "max_tokens": 4097,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
         "supports_function_calling": true,
@@ -420,7 +420,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 4097,
         "max_output_tokens": 4096,
-        "max_tokens": 4097,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_prompt_caching": true,
@@ -432,7 +432,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 4097,
         "max_output_tokens": 4096,
-        "max_tokens": 4097,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_function_calling": true,
@@ -446,7 +446,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
-        "max_tokens": 16385,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_function_calling": true,
@@ -460,7 +460,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
-        "max_tokens": 16385,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
         "supports_function_calling": true,
@@ -474,7 +474,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
-        "max_tokens": 16385,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
         "supports_prompt_caching": true,
@@ -486,7 +486,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
-        "max_tokens": 16385,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
         "supports_prompt_caching": true,
@@ -597,7 +597,7 @@
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
-        "max_tokens": 16384,
+        "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 1e-06
@@ -608,7 +608,7 @@
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
-        "max_tokens": 16384,
+        "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 1.6e-06,
         "output_cost_per_token_batches": 2e-07
@@ -659,7 +659,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 32768,
         "max_output_tokens": 0,
-        "max_tokens": 32768,
+        "max_tokens": 0,
         "mode": "moderation",
         "output_cost_per_token": 0.0
     },
@@ -668,7 +668,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 32768,
         "max_output_tokens": 0,
-        "max_tokens": 32768,
+        "max_tokens": 0,
         "mode": "moderation",
         "output_cost_per_token": 0.0
     },
@@ -677,7 +677,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 32768,
         "max_output_tokens": 0,
-        "max_tokens": 32768,
+        "max_tokens": 0,
         "mode": "moderation",
         "output_cost_per_token": 0.0
     },
@@ -1063,7 +1063,7 @@
         "litellm_provider": "azure",
         "max_input_tokens": 4097,
         "max_output_tokens": 4096,
-        "max_tokens": 4097,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_function_calling": true,
@@ -1076,7 +1076,7 @@
         "litellm_provider": "azure",
         "max_input_tokens": 4097,
         "max_output_tokens": 4096,
-        "max_tokens": 4097,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_function_calling": true,
@@ -1368,7 +1368,7 @@
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
-        "max_tokens": 16384,
+        "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 4e-07
     },
@@ -1377,7 +1377,7 @@
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
-        "max_tokens": 16384,
+        "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 2e-06
     },
@@ -2496,7 +2496,7 @@
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 8192,
         "max_output_tokens": 2048,
-        "max_tokens": 8192,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_character": 3.75e-07,
         "output_cost_per_token": 1.5e-06,
@@ -2513,7 +2513,7 @@
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 8192,
         "max_output_tokens": 2048,
-        "max_tokens": 8192,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_character": 3.75e-07,
         "output_cost_per_token": 1.5e-06,
@@ -3098,7 +3098,7 @@
         "litellm_provider": "vertex_ai-llama_models",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "metadata": {
             "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA."
         },
@@ -4079,7 +4079,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 66000,
         "max_output_tokens": 4096,
-        "max_tokens": 8192,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2.8e-07,
         "supports_prompt_caching": true,
@@ -4410,7 +4410,7 @@
         "input_cost_per_token": 1.63e-06,
         "litellm_provider": "openrouter",
         "max_output_tokens": 8191,
-        "max_tokens": 100000,
+        "max_tokens": 8191,
         "mode": "chat",
         "output_cost_per_token": 5.51e-06,
         "supports_tool_choice": true
@@ -4419,7 +4419,7 @@
         "input_cost_per_token": 1.102e-05,
         "litellm_provider": "openrouter",
         "max_output_tokens": 8191,
-        "max_tokens": 100000,
+        "max_tokens": 8191,
         "mode": "chat",
         "output_cost_per_token": 3.268e-05,
         "supports_tool_choice": true
@@ -5898,7 +5898,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 2.2e-07,
         "supports_function_calling": true,
@@ -5909,7 +5909,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 9.9e-07,
         "supports_function_calling": true,
@@ -5920,7 +5920,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.6e-05,
         "supports_function_calling": true,
@@ -5931,7 +5931,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
         "supports_function_calling": true,
@@ -5942,7 +5942,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
         "supports_function_calling": true,
@@ -5953,7 +5953,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.3e-07,
         "supports_function_calling": true,
@@ -5964,7 +5964,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
         "supports_function_calling": true,
@@ -5975,7 +5975,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07,
         "supports_function_calling": true,
@@ -5986,7 +5986,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.9e-07,
         "supports_function_calling": true,
@@ -5997,7 +5997,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3.5e-07,
         "supports_function_calling": true,
@@ -6009,7 +6009,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3.5e-07,
         "supports_function_calling": true,
@@ -6021,7 +6021,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_function_calling": true,
@@ -6033,7 +6033,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "supports_function_calling": true,
@@ -6224,7 +6224,7 @@
         "litellm_provider": "ollama",
         "max_input_tokens": 32768,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "supports_function_calling": false
@@ -6234,7 +6234,7 @@
         "litellm_provider": "ollama",
         "max_input_tokens": 32768,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "supports_function_calling": true
@@ -6254,7 +6254,7 @@
         "litellm_provider": "ollama",
         "max_input_tokens": 32768,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "supports_function_calling": true
@@ -6274,7 +6274,7 @@
         "litellm_provider": "ollama",
         "max_input_tokens": 32768,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "supports_function_calling": true
@@ -6356,7 +6356,7 @@
         "litellm_provider": "ollama",
         "max_input_tokens": 8192,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "supports_function_calling": true
@@ -6366,7 +6366,7 @@
         "litellm_provider": "ollama",
         "max_input_tokens": 65536,
         "max_output_tokens": 8192,
-        "max_tokens": 65536,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "supports_function_calling": true
@@ -8005,7 +8005,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 2.2e-07,
         "supports_function_calling": true,
@@ -8016,7 +8016,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 9.9e-07,
         "supports_function_calling": true,
@@ -8027,7 +8027,7 @@
         "litellm_provider": "bedrock",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.6e-05,
         "supports_function_calling": true,
@@ -8058,7 +8058,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 32768,
         "max_output_tokens": 0,
-        "max_tokens": 32768,
+        "max_tokens": 0,
         "mode": "moderation",
         "output_cost_per_token": 0.0
     },
@@ -8067,7 +8067,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 32768,
         "max_output_tokens": 0,
-        "max_tokens": 32768,
+        "max_tokens": 0,
         "mode": "moderation",
         "output_cost_per_token": 0.0
     },
@@ -8076,7 +8076,7 @@
         "litellm_provider": "openai",
         "max_input_tokens": 32768,
         "max_output_tokens": 0,
-        "max_tokens": 32768,
+        "max_tokens": 0,
         "mode": "moderation",
         "output_cost_per_token": 0.0
     },
@@ -9387,7 +9387,7 @@
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_pdf_size_mb": 30,
-        "max_tokens": 8192,
+        "max_tokens": 65536,
         "max_video_length": 1,
         "max_videos_per_prompt": 10,
         "mode": "chat",
@@ -10441,7 +10441,7 @@
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
         "max_pdf_size_mb": 30,
-        "max_tokens": 8192,
+        "max_tokens": 65536,
         "max_video_length": 1,
         "max_videos_per_prompt": 10,
         "mode": "chat",
@@ -10618,7 +10618,7 @@
         "litellm_provider": "snowflake",
         "max_input_tokens": 32768,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "supports_reasoning": true
     },
@@ -10626,14 +10626,14 @@
         "litellm_provider": "snowflake",
         "max_input_tokens": 4096,
         "max_output_tokens": 8192,
-        "max_tokens": 4096,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/claude-3-5-sonnet": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 18000,
         "max_output_tokens": 8192,
-        "max_tokens": 18000,
+        "max_tokens": 8192,
         "mode": "chat",
         "supports_computer_use": true
     },
@@ -10641,147 +10641,147 @@
         "litellm_provider": "snowflake",
         "max_input_tokens": 32000,
         "max_output_tokens": 8192,
-        "max_tokens": 32000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/mistral-large2": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/reka-flash": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 100000,
         "max_output_tokens": 8192,
-        "max_tokens": 100000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/reka-core": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 32000,
         "max_output_tokens": 8192,
-        "max_tokens": 32000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/jamba-instruct": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 256000,
         "max_output_tokens": 8192,
-        "max_tokens": 256000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/jamba-1.5-mini": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 256000,
         "max_output_tokens": 8192,
-        "max_tokens": 256000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/jamba-1.5-large": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 256000,
         "max_output_tokens": 8192,
-        "max_tokens": 256000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/mixtral-8x7b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 32000,
         "max_output_tokens": 8192,
-        "max_tokens": 32000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama2-70b-chat": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 4096,
         "max_output_tokens": 8192,
-        "max_tokens": 4096,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3-8b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 8000,
         "max_output_tokens": 8192,
-        "max_tokens": 8000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3-70b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 8000,
         "max_output_tokens": 8192,
-        "max_tokens": 8000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3.1-8b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3.1-70b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3.3-70b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/snowflake-llama-3.3-70b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 8000,
         "max_output_tokens": 8192,
-        "max_tokens": 8000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3.1-405b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/snowflake-llama-3.1-405b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 8000,
         "max_output_tokens": 8192,
-        "max_tokens": 8000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3.2-1b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/llama3.2-3b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/mistral-7b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 32000,
         "max_output_tokens": 8192,
-        "max_tokens": 32000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "snowflake/gemma-7b": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 8000,
         "max_output_tokens": 8192,
-        "max_tokens": 8000,
+        "max_tokens": 8192,
         "mode": "chat"
     },
     "azure/global/gpt-4o-2024-11-20": {
@@ -11234,7 +11234,7 @@
         "litellm_provider": "watsonx",
         "max_input_tokens": 8192,
         "max_output_tokens": 1024,
-        "max_tokens": 8192,
+        "max_tokens": 1024,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
         "supports_audio_input": false,
@@ -12221,7 +12221,7 @@
         "litellm_provider": "meta_llama",
         "max_input_tokens": 10000000,
         "max_output_tokens": 4028,
-        "max_tokens": 128000,
+        "max_tokens": 4028,
         "mode": "chat",
         "source": "https://llama.developer.meta.com/docs/models",
         "supported_modalities": [
@@ -12238,7 +12238,7 @@
         "litellm_provider": "meta_llama",
         "max_input_tokens": 1000000,
         "max_output_tokens": 4028,
-        "max_tokens": 128000,
+        "max_tokens": 4028,
         "mode": "chat",
         "source": "https://llama.developer.meta.com/docs/models",
         "supported_modalities": [
@@ -12255,7 +12255,7 @@
         "litellm_provider": "meta_llama",
         "max_input_tokens": 128000,
         "max_output_tokens": 4028,
-        "max_tokens": 128000,
+        "max_tokens": 4028,
         "mode": "chat",
         "source": "https://llama.developer.meta.com/docs/models",
         "supported_modalities": [
@@ -12271,7 +12271,7 @@
         "litellm_provider": "meta_llama",
         "max_input_tokens": 128000,
         "max_output_tokens": 4028,
-        "max_tokens": 128000,
+        "max_tokens": 4028,
         "mode": "chat",
         "source": "https://llama.developer.meta.com/docs/models",
         "supported_modalities": [
@@ -13239,7 +13239,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 128000,
-        "max_tokens": 200000,
+        "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."
         },
@@ -13615,14 +13615,14 @@
         "litellm_provider": "featherless_ai",
         "max_input_tokens": 32768,
         "max_output_tokens": 4096,
-        "max_tokens": 32768,
+        "max_tokens": 4096,
         "mode": "chat"
     },
     "featherless_ai/featherless-ai/Qwerky-QwQ-32B": {
         "litellm_provider": "featherless_ai",
         "max_input_tokens": 32768,
         "max_output_tokens": 4096,
-        "max_tokens": 32768,
+        "max_tokens": 4096,
         "mode": "chat"
     },
     "sambanova/Llama-4-Maverick-17B-128E-Instruct": {
@@ -14459,7 +14459,7 @@
         "litellm_provider": "anthropic",
         "max_input_tokens": 1000000,
         "max_output_tokens": 64000,
-        "max_tokens": 1000000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_above_200k_tokens": 2.25e-05,
@@ -16243,7 +16243,7 @@
         "litellm_provider": "watsonx",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supports_audio_input": false,
@@ -16364,7 +16364,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
         "supports_function_calling": true,
@@ -16375,7 +16375,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
         "supports_function_calling": true,
@@ -16386,7 +16386,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 30720,
         "max_output_tokens": 8192,
-        "max_tokens": 32768,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6.4e-06,
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
@@ -16398,7 +16398,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 32768,
-        "max_tokens": 1000000,
+        "max_tokens": 32768,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -16430,7 +16430,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 1000000,
         "max_output_tokens": 16384,
-        "max_tokens": 1000000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_reasoning_token": 5e-07,
         "output_cost_per_token": 2e-07,
@@ -16443,7 +16443,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 129024,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -17076,7 +17076,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 8192,
         "max_output_tokens": 2048,
-        "max_tokens": 8192,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 6.3e-07,
         "supports_tool_choice": true,
@@ -17087,7 +17087,7 @@
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct",
@@ -17220,7 +17220,7 @@
         "litellm_provider": "lambda_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 8192,
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
         "supports_function_calling": true,
@@ -17233,7 +17233,7 @@
         "litellm_provider": "lambda_ai",
         "max_input_tokens": 16384,
         "max_output_tokens": 8192,
-        "max_tokens": 16384,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
         "supports_function_calling": true,
@@ -17508,7 +17508,7 @@
         "litellm_provider": "vertex_ai-llama_models",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "metadata": {
             "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost."
         },
@@ -17524,7 +17524,7 @@
         "litellm_provider": "vertex_ai-llama_models",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
@@ -17537,7 +17537,7 @@
         "litellm_provider": "vertex_ai-llama_models",
         "max_input_tokens": 128000,
         "max_output_tokens": 2048,
-        "max_tokens": 128000,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 1.6e-05,
         "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
@@ -18769,7 +18769,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 512000,
         "max_output_tokens": 4000,
-        "max_tokens": 512000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
@@ -18781,7 +18781,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 192000,
         "max_output_tokens": 4000,
-        "max_tokens": 192000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
@@ -18793,7 +18793,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07,
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
@@ -18805,7 +18805,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
@@ -18817,7 +18817,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1.068e-05,
         "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
@@ -20331,7 +20331,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 8192,
+        "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 8e-07,
         "supports_assistant_prefill": true,
@@ -20774,7 +20774,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 262144,
         "max_output_tokens": 66536,
-        "max_tokens": 262144,
+        "max_tokens": 66536,
         "mode": "chat",
         "output_cost_per_token": 1.6e-06
     },
@@ -20792,7 +20792,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
-        "max_tokens": 1048576,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1e-05
     },
@@ -20801,7 +20801,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 9e-07
     },
@@ -20810,7 +20810,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 300000,
         "max_output_tokens": 8192,
-        "max_tokens": 300000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07
     },
@@ -20819,7 +20819,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 131072,
         "max_output_tokens": 8192,
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3e-07
     },
@@ -20828,7 +20828,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1e-07
     },
@@ -20837,7 +20837,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 32000,
         "max_output_tokens": 4000,
-        "max_tokens": 32000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 3e-07
     },
@@ -20846,7 +20846,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1000000,
         "max_output_tokens": 65536,
-        "max_tokens": 1000000,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06
     },
@@ -20855,7 +20855,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 32000,
         "max_output_tokens": 16384,
-        "max_tokens": 32000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-06
     },
@@ -20882,7 +20882,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 131072,
         "max_output_tokens": 4000,
-        "max_tokens": 131072,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1e-05
     },
@@ -20900,7 +20900,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07
     },
@@ -20918,7 +20918,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 40960,
         "max_output_tokens": 16384,
-        "max_tokens": 40960,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07
     },
@@ -20936,7 +20936,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 32768,
-        "max_tokens": 128000,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05
     },
@@ -20947,7 +20947,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "max_tokens": 200000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06
     },
@@ -20956,7 +20956,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 64000,
-        "max_tokens": 128000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 5e-06
     },
@@ -20974,7 +20974,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 40960,
         "max_output_tokens": 16384,
-        "max_tokens": 40960,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3e-07
     },
@@ -20983,7 +20983,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 96000,
-        "max_tokens": 128000,
+        "max_tokens": 96000,
         "mode": "chat",
         "output_cost_per_token": 1.1e-06
     },
@@ -20992,7 +20992,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3e-05
     },
@@ -21001,7 +21001,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 32000,
         "max_output_tokens": 4000,
-        "max_tokens": 32000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 6e-06
     },
@@ -21010,7 +21010,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 8000,
-        "max_tokens": 200000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05
     },
@@ -21019,7 +21019,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07
     },
@@ -21046,7 +21046,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 6e-06
     },
@@ -21057,7 +21057,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 8192,
-        "max_tokens": 200000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05
     },
@@ -21066,7 +21066,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.4e-07
     },
@@ -21075,7 +21075,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-07
     },
@@ -21084,7 +21084,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 32768,
         "max_output_tokens": 16384,
-        "max_tokens": 32768,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.9e-06
     },
@@ -21093,7 +21093,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 65536,
         "max_output_tokens": 2048,
-        "max_tokens": 65536,
+        "max_tokens": 2048,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06
     },
@@ -21111,7 +21111,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 131000,
         "max_output_tokens": 131072,
-        "max_tokens": 131000,
+        "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 8e-08
     },
@@ -21122,7 +21122,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 4096,
-        "max_tokens": 200000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 7.5e-05
     },
@@ -21142,7 +21142,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
-        "max_tokens": 128000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05
     },
@@ -21153,7 +21153,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "max_tokens": 200000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06
     },
@@ -21162,7 +21162,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1e-07
     },
@@ -21173,7 +21173,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "max_tokens": 200000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8e-06
     },
@@ -21182,7 +21182,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 32000,
-        "max_tokens": 128000,
+        "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05
     },
@@ -21200,7 +21200,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 300000,
         "max_output_tokens": 8192,
-        "max_tokens": 300000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3.2e-06
     },
@@ -21209,7 +21209,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 32768,
         "max_output_tokens": 16384,
-        "max_tokens": 32768,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06
     },
@@ -21218,7 +21218,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
-        "max_tokens": 16385,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06
     },
@@ -21227,7 +21227,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 256000,
         "max_output_tokens": 4000,
-        "max_tokens": 256000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 9e-07
     },
@@ -21236,7 +21236,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.6e-07
     },
@@ -21272,7 +21272,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1048576,
         "max_output_tokens": 8192,
-        "max_tokens": 1048576,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3e-07
     },
@@ -21281,7 +21281,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 4e-08
     },
@@ -21290,7 +21290,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 127000,
         "max_output_tokens": 8000,
-        "max_tokens": 127000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 8e-06
     },
@@ -21310,7 +21310,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 4096,
-        "max_tokens": 200000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06
     },
@@ -21321,7 +21321,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "max_tokens": 200000,
+        "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 6e-05
     },
@@ -21330,7 +21330,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.19e-06
     },
@@ -21350,7 +21350,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1047576,
         "max_output_tokens": 32768,
-        "max_tokens": 1047576,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 1.6e-06
     },
@@ -21361,7 +21361,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
-        "max_tokens": 128000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07
     },
@@ -21370,7 +21370,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 40960,
         "max_output_tokens": 16384,
-        "max_tokens": 40960,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 2.4e-07
     },
@@ -21381,7 +21381,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
-        "max_tokens": 200000,
+        "max_tokens": 32000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-05
     },
@@ -21399,7 +21399,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 127000,
         "max_output_tokens": 8000,
-        "max_tokens": 127000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 5e-06
     },
@@ -21410,7 +21410,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 8192,
-        "max_tokens": 200000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 4e-06
     },
@@ -21419,7 +21419,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 256000,
         "max_output_tokens": 8000,
-        "max_tokens": 256000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1e-05
     },
@@ -21437,7 +21437,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07
     },
@@ -21448,7 +21448,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1047576,
         "max_output_tokens": 32768,
-        "max_tokens": 1047576,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-07
     },
@@ -21459,7 +21459,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05
     },
@@ -21468,7 +21468,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 127000,
         "max_output_tokens": 8000,
-        "max_tokens": 127000,
+        "max_tokens": 8000,
         "mode": "chat",
         "output_cost_per_token": 1e-06
     },
@@ -21477,7 +21477,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 131072,
         "max_output_tokens": 8192,
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-07
     },
@@ -21513,7 +21513,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 7.2e-07
     },
@@ -21522,7 +21522,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
-        "max_tokens": 128000,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1e-05
     },
@@ -21531,7 +21531,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
-        "max_tokens": 8192,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06
     },
@@ -21551,7 +21551,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05
     },
@@ -21560,7 +21560,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1048576,
         "max_output_tokens": 8192,
-        "max_tokens": 1048576,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 6e-07
     },
@@ -21569,7 +21569,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-07
     },
@@ -21578,7 +21578,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 128000,
         "max_output_tokens": 64000,
-        "max_tokens": 128000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06
     },
@@ -21587,7 +21587,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 2.2e-06
     },
@@ -21596,7 +21596,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 40960,
         "max_output_tokens": 16384,
-        "max_tokens": 40960,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3e-07
     },
@@ -21607,7 +21607,7 @@
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1047576,
         "max_output_tokens": 32768,
-        "max_tokens": 1047576,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 8e-06
     },
@@ -21943,7 +21943,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 258048,
         "max_output_tokens": 65536,
-        "max_tokens": 262144,
+        "max_tokens": 65536,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -21981,7 +21981,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 129024,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
@@ -22023,7 +22023,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 1000000,
         "max_output_tokens": 16384,
-        "max_tokens": 1000000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
@@ -22035,7 +22035,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 65536,
-        "max_tokens": 1000000,
+        "max_tokens": 65536,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22084,7 +22084,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 65536,
-        "max_tokens": 1000000,
+        "max_tokens": 65536,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22129,7 +22129,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 65536,
-        "max_tokens": 1000000,
+        "max_tokens": 65536,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22178,7 +22178,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 65536,
-        "max_tokens": 1000000,
+        "max_tokens": 65536,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22223,7 +22223,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 32768,
-        "max_tokens": 1000000,
+        "max_tokens": 32768,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22254,7 +22254,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 32768,
-        "max_tokens": 1000000,
+        "max_tokens": 32768,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22286,7 +22286,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 129024,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_reasoning_token": 4e-06,
         "output_cost_per_token": 1.2e-06,
@@ -22300,7 +22300,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 129024,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_reasoning_token": 4e-06,
         "output_cost_per_token": 1.2e-06,
@@ -22314,7 +22314,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 129024,
         "max_output_tokens": 8192,
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
@@ -22326,7 +22326,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 997952,
         "max_output_tokens": 32768,
-        "max_tokens": 1000000,
+        "max_tokens": 32768,
         "mode": "chat",
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
         "supports_function_calling": true,
@@ -22356,7 +22356,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 129024,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_reasoning_token": 5e-07,
         "output_cost_per_token": 2e-07,
@@ -22370,7 +22370,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 1000000,
         "max_output_tokens": 16384,
-        "max_tokens": 1000000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_reasoning_token": 5e-07,
         "output_cost_per_token": 2e-07,
@@ -22384,7 +22384,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 1000000,
         "max_output_tokens": 8192,
-        "max_tokens": 1000000,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
@@ -22397,7 +22397,7 @@
         "litellm_provider": "dashscope",
         "max_input_tokens": 98304,
         "max_output_tokens": 8192,
-        "max_tokens": 131072,
+        "max_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
         "source": "https://www.alibabacloud.com/help/en/model-studio/models",
@@ -22815,7 +22815,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 2000000,
         "max_output_tokens": 30000,
-        "max_tokens": 2000000,
+        "max_tokens": 30000,
         "mode": "chat",
         "output_cost_per_token": 0,
         "source": "https://openrouter.ai/x-ai/grok-4-fast:free",
@@ -22916,7 +22916,7 @@
         "litellm_provider": "deepseek",
         "max_input_tokens": 131072,
         "max_output_tokens": 65536,
-        "max_tokens": 131072,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1.7e-06,
         "source": "https://api-docs.deepseek.com/quick_start/pricing",
@@ -22937,7 +22937,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 163840,
         "max_output_tokens": 81920,
-        "max_tokens": 163840,
+        "max_tokens": 81920,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
         "supports_function_calling": true,
@@ -22979,7 +22979,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262000,
         "max_output_tokens": 65536,
-        "max_tokens": 262144,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1.8e-06,
         "supports_function_calling": true,
@@ -22991,7 +22991,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "max_tokens": 262144,
+        "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 8.8e-07,
         "supports_function_calling": true,
@@ -23003,7 +23003,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 262144,
         "max_output_tokens": 131072,
-        "max_tokens": 262144,
+        "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "supports_function_calling": true,
@@ -23015,7 +23015,7 @@
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 131072,
         "max_output_tokens": 16384,
-        "max_tokens": 131072,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "supports_function_calling": true,
@@ -23053,7 +23053,7 @@
         "litellm_provider": "vertex_ai-deepseek_models",
         "max_input_tokens": 163840,
         "max_output_tokens": 32768,
-        "max_tokens": 163840,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 5.4e-06,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
@@ -23684,7 +23684,7 @@
     "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": {
         "input_cost_per_token": 0,
         "litellm_provider": "lemonade",
-        "max_tokens": 262144,
+        "max_tokens": 32768,
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "mode": "chat",
@@ -23700,7 +23700,7 @@
         "litellm_provider": "groq",
         "max_input_tokens": 262144,
         "max_output_tokens": 16384,
-        "max_tokens": 278528,
+        "max_tokens": 16384,
         "mode": "chat",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -24496,7 +24496,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1.56e-06,
         "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
@@ -24508,7 +24508,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 256000,
         "max_output_tokens": 4000,
-        "max_tokens": 256000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1.56e-06,
         "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
@@ -24520,7 +24520,7 @@
         "litellm_provider": "oci",
         "max_input_tokens": 128000,
         "max_output_tokens": 4000,
-        "max_tokens": 128000,
+        "max_tokens": 4000,
         "mode": "chat",
         "output_cost_per_token": 1.56e-06,
         "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
@@ -24835,7 +24835,7 @@
     "lemonade/gpt-oss-20b-mxfp4-GGUF": {
         "input_cost_per_token": 0,
         "litellm_provider": "lemonade",
-        "max_tokens": 131072,
+        "max_tokens": 32768,
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "mode": "chat",
@@ -24847,7 +24847,7 @@
     "lemonade/gpt-oss-120b-mxfp-GGUF": {
         "input_cost_per_token": 0,
         "litellm_provider": "lemonade",
-        "max_tokens": 131072,
+        "max_tokens": 32768,
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "mode": "chat",
@@ -24859,7 +24859,7 @@
     "lemonade/Gemma-3-4b-it-GGUF": {
         "input_cost_per_token": 0,
         "litellm_provider": "lemonade",
-        "max_tokens": 128000,
+        "max_tokens": 8192,
         "max_input_tokens": 128000,
         "max_output_tokens": 8192,
         "mode": "chat",
@@ -24871,7 +24871,7 @@
     "lemonade/Qwen3-4B-Instruct-2507-GGUF": {
         "input_cost_per_token": 0,
         "litellm_provider": "lemonade",
-        "max_tokens": 262144,
+        "max_tokens": 32768,
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "mode": "chat",
@@ -25789,7 +25789,7 @@
         "litellm_provider": "azure",
         "max_input_tokens": 272000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.00012,
         "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5",
@@ -25926,7 +25926,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 8192,
+        "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
         "supports_assistant_prefill": true,
@@ -25940,7 +25940,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 204800,
         "max_output_tokens": 204800,
-        "max_tokens": 32768,
+        "max_tokens": 204800,
         "mode": "chat",
         "output_cost_per_token": 1.02e-06,
         "supports_function_calling": true,
@@ -25953,7 +25953,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 202800,
         "max_output_tokens": 131000,
-        "max_tokens": 202800,
+        "max_tokens": 131000,
         "mode": "chat",
         "output_cost_per_token": 1.75e-06,
         "source": "https://openrouter.ai/z-ai/glm-4.6",
@@ -25966,7 +25966,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 202800,
         "max_output_tokens": 131000,
-        "max_tokens": 202800,
+        "max_tokens": 131000,
         "mode": "chat",
         "output_cost_per_token": 1.9e-06,
         "source": "https://openrouter.ai/z-ai/glm-4.6:exacto",
@@ -27739,7 +27739,7 @@
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
-        "max_tokens": 65536,
+        "max_tokens": 32768,
         "mode": "image_generation",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
@@ -27773,7 +27773,7 @@
         "litellm_provider": "gemini",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
-        "max_tokens": 65536,
+        "max_tokens": 32768,
         "mode": "image_generation",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
@@ -27870,7 +27870,7 @@
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
-        "max_tokens": 65536,
+        "max_tokens": 32768,
         "mode": "image_generation",
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
@@ -28314,7 +28314,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
-        "max_tokens": 8192,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28326,7 +28326,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
-        "max_tokens": 8192,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28338,7 +28338,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
-        "max_tokens": 8192,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28350,7 +28350,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
-        "max_tokens": 16384,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28362,7 +28362,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
-        "max_tokens": 8192,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28374,7 +28374,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 32768,
         "max_output_tokens": 4096,
-        "max_tokens": 32768,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28386,7 +28386,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 32768,
         "max_output_tokens": 4096,
-        "max_tokens": 32768,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28398,7 +28398,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 32768,
         "max_output_tokens": 4096,
-        "max_tokens": 32768,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28411,7 +28411,7 @@
         "litellm_provider": "publicai",
         "max_input_tokens": 32768,
         "max_output_tokens": 4096,
-        "max_tokens": 32768,
+        "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
@@ -28424,7 +28424,7 @@
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
-        "max_tokens": 262144,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.5e-06,
         "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905",
@@ -28465,7 +28465,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28484,7 +28484,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
-        "max_tokens": 200000,
+        "max_tokens": 32000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28503,7 +28503,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 32000,
-        "max_tokens": 200000,
+        "max_tokens": 32000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28522,7 +28522,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28541,7 +28541,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28560,7 +28560,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28579,7 +28579,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 64000,
-        "max_tokens": 200000,
+        "max_tokens": 64000,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28598,7 +28598,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
-        "max_tokens": 1048576,
+        "max_tokens": 65535,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28615,7 +28615,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65536,
-        "max_tokens": 1048576,
+        "max_tokens": 65536,
         "metadata": {
             "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
         },
@@ -28647,7 +28647,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "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."
         },
@@ -28662,7 +28662,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "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."
         },
@@ -28677,7 +28677,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "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."
         },
@@ -28692,7 +28692,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "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."
         },
@@ -28737,7 +28737,7 @@
         "litellm_provider": "databricks",
         "max_input_tokens": 200000,
         "max_output_tokens": 128000,
-        "max_tokens": 200000,
+        "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."
         },
@@ -28932,7 +28932,7 @@
         "litellm_provider": "deepseek",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 8192,
+        "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
         "supports_assistant_prefill": true,
@@ -29019,7 +29019,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 8192,
+        "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
         "supports_assistant_prefill": true,
@@ -31608,7 +31608,7 @@
         "litellm_provider": "vertex_ai-deepseek_models",
         "max_input_tokens": 163840,
         "max_output_tokens": 32768,
-        "max_tokens": 163840,
+        "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
         "output_cost_per_token_batches": 8.4e-07,
@@ -32214,7 +32214,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 262144,
         "max_output_tokens": 65536,
-        "max_tokens": 262144,
+        "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
         "supports_function_calling": true,
@@ -32285,7 +32285,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.4e-05,
         "supports_function_calling": true,
@@ -32301,7 +32301,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
-        "max_tokens": 128000,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.4e-05,
         "supports_function_calling": true,
@@ -32315,7 +32315,7 @@
         "litellm_provider": "openrouter",
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
-        "max_tokens": 400000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 0.000168,
         "supports_function_calling": true,
@@ -32329,7 +32329,7 @@
         "litellm_provider": "azure_ai",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 8192,
+        "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
         "supports_assistant_prefill": true,
@@ -32343,7 +32343,7 @@
         "litellm_provider": "azure_ai",
         "max_input_tokens": 163840,
         "max_output_tokens": 163840,
-        "max_tokens": 8192,
+        "max_tokens": 163840,
         "mode": "chat",
         "output_cost_per_token": 1.68e-06,
         "supports_assistant_prefill": true,
@@ -33980,5 +33980,1099 @@
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_tool_choice": true
+    },
+    "novita/deepseek/deepseek-v3.2": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00269,
+        "output_cost_per_token": 0.004,
+        "max_input_tokens": 163840,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.001345,
+        "input_cost_per_token_cache_hit": 0.001345,
+        "supports_reasoning": true
+    },
+    "novita/minimax/minimax-m2.1": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.003,
+        "output_cost_per_token": 0.012,
+        "max_input_tokens": 204800,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.0003,
+        "input_cost_per_token_cache_hit": 0.0003,
+        "supports_reasoning": true
+    },
+    "novita/zai-org/glm-4.7": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.006,
+        "output_cost_per_token": 0.022,
+        "max_input_tokens": 204800,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.0011,
+        "input_cost_per_token_cache_hit": 0.0011,
+        "supports_reasoning": true
+    },
+    "novita/xiaomimimo/mimo-v2-flash": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.001,
+        "output_cost_per_token": 0.003,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.0002,
+        "input_cost_per_token_cache_hit": 0.0002,
+        "supports_reasoning": true
+    },
+    "novita/zai-org/autoglm-phone-9b-multilingual": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00035,
+        "output_cost_per_token": 0.00138,
+        "max_input_tokens": 65536,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_vision": true,
+        "supports_system_messages": true
+    },
+    "novita/moonshotai/kimi-k2-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0048,
+        "output_cost_per_token": 0.02,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/minimax/minimax-m2": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0024,
+        "output_cost_per_token": 0.0096,
+        "max_input_tokens": 204800,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "cache_read_input_token_cost": 0.00024,
+        "input_cost_per_token_cache_hit": 0.00024,
+        "supports_reasoning": true
+    },
+    "novita/paddlepaddle/paddleocr-vl": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00016,
+        "output_cost_per_token": 0.00016,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "supports_vision": true,
+        "supports_system_messages": true
+    },
+    "novita/deepseek/deepseek-v3.2-exp": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00216,
+        "output_cost_per_token": 0.00328,
+        "max_input_tokens": 163840,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-vl-235b-a22b-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00784,
+        "output_cost_per_token": 0.0316,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/zai-org/glm-4.6v": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.003,
+        "output_cost_per_token": 0.009,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.00055,
+        "input_cost_per_token_cache_hit": 0.00055,
+        "supports_reasoning": true
+    },
+    "novita/zai-org/glm-4.6": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0044,
+        "output_cost_per_token": 0.0176,
+        "max_input_tokens": 204800,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.00088,
+        "input_cost_per_token_cache_hit": 0.00088,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-next-80b-a3b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0012,
+        "output_cost_per_token": 0.012,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen3-next-80b-a3b-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0012,
+        "output_cost_per_token": 0.012,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/deepseek/deepseek-ocr": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00024,
+        "output_cost_per_token": 0.00024,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/deepseek/deepseek-v3.1-terminus": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00216,
+        "output_cost_per_token": 0.008,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.00108,
+        "input_cost_per_token_cache_hit": 0.00108,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-vl-235b-a22b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0024,
+        "output_cost_per_token": 0.012,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen3-max": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.01688,
+        "output_cost_per_token": 0.0676,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/skywork/r1v4-lite": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.002,
+        "output_cost_per_token": 0.006,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/deepseek/deepseek-v3.1": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00216,
+        "output_cost_per_token": 0.008,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.00108,
+        "input_cost_per_token_cache_hit": 0.00108,
+        "supports_reasoning": true
+    },
+    "novita/moonshotai/kimi-k2-0905": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0048,
+        "output_cost_per_token": 0.02,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen3-coder-480b-a35b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0024,
+        "output_cost_per_token": 0.0104,
+        "max_input_tokens": 262144,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen3-coder-30b-a3b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0007,
+        "output_cost_per_token": 0.0027,
+        "max_input_tokens": 160000,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/openai/gpt-oss-120b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0004,
+        "output_cost_per_token": 0.002,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/moonshotai/kimi-k2-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00456,
+        "output_cost_per_token": 0.0184,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/deepseek/deepseek-v3-0324": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00216,
+        "output_cost_per_token": 0.00896,
+        "max_input_tokens": 163840,
+        "max_output_tokens": 163840,
+        "max_tokens": 163840,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.00108,
+        "input_cost_per_token_cache_hit": 0.00108
+    },
+    "novita/zai-org/glm-4.5": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0048,
+        "output_cost_per_token": 0.0176,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "cache_read_input_token_cost": 0.00088,
+        "input_cost_per_token_cache_hit": 0.00088,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-235b-a22b-thinking-2507": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0024,
+        "output_cost_per_token": 0.024,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/meta-llama/llama-3.1-8b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0002,
+        "output_cost_per_token": 0.0005,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "supports_system_messages": true
+    },
+    "novita/google/gemma-3-12b-it": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0004,
+        "output_cost_per_token": 0.0008,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/zai-org/glm-4.5v": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0048,
+        "output_cost_per_token": 0.0144,
+        "max_input_tokens": 65536,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.00088,
+        "input_cost_per_token_cache_hit": 0.00088,
+        "supports_reasoning": true
+    },
+    "novita/openai/gpt-oss-20b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00032,
+        "output_cost_per_token": 0.0012,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-235b-a22b-instruct-2507": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00072,
+        "output_cost_per_token": 0.00464,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/deepseek/deepseek-r1-distill-qwen-14b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0012,
+        "output_cost_per_token": 0.0012,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/meta-llama/llama-3.3-70b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00108,
+        "output_cost_per_token": 0.0032,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 120000,
+        "max_tokens": 120000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/qwen/qwen-2.5-72b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00304,
+        "output_cost_per_token": 0.0032,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/mistralai/mistral-nemo": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00032,
+        "output_cost_per_token": 0.00136,
+        "max_input_tokens": 60288,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/minimaxai/minimax-m1-80k": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0044,
+        "output_cost_per_token": 0.0176,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 40000,
+        "max_tokens": 40000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/deepseek/deepseek-r1-0528": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0056,
+        "output_cost_per_token": 0.02,
+        "max_input_tokens": 163840,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "cache_read_input_token_cost": 0.0028,
+        "input_cost_per_token_cache_hit": 0.0028,
+        "supports_reasoning": true
+    },
+    "novita/deepseek/deepseek-r1-distill-qwen-32b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0024,
+        "output_cost_per_token": 0.0024,
+        "max_input_tokens": 64000,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/meta-llama/llama-3-8b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00032,
+        "output_cost_per_token": 0.00032,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_system_messages": true
+    },
+    "novita/microsoft/wizardlm-2-8x22b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00496,
+        "output_cost_per_token": 0.00496,
+        "max_input_tokens": 65535,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "supports_system_messages": true
+    },
+    "novita/deepseek/deepseek-r1-0528-qwen3-8b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00048,
+        "output_cost_per_token": 0.00072,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/deepseek/deepseek-r1-distill-llama-70b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0064,
+        "output_cost_per_token": 0.0064,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/meta-llama/llama-3-70b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0051,
+        "output_cost_per_token": 0.0074,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen3-235b-a22b-fp8": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0016,
+        "output_cost_per_token": 0.0064,
+        "max_input_tokens": 40960,
+        "max_output_tokens": 20000,
+        "max_tokens": 20000,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0016,
+        "output_cost_per_token": 0.0072,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_vision": true,
+        "supports_system_messages": true
+    },
+    "novita/meta-llama/llama-4-scout-17b-16e-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0008,
+        "output_cost_per_token": 0.004,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_vision": true,
+        "supports_system_messages": true
+    },
+    "novita/nousresearch/hermes-2-pro-llama-3-8b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0014,
+        "output_cost_per_token": 0.0014,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen2.5-vl-72b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0064,
+        "output_cost_per_token": 0.0064,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_vision": true,
+        "supports_system_messages": true
+    },
+    "novita/sao10k/l3-70b-euryale-v2.1": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0148,
+        "output_cost_per_token": 0.0148,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/baidu/ernie-4.5-21B-a3b-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00056,
+        "output_cost_per_token": 0.00224,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/sao10k/l3-8b-lunaris": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0005,
+        "output_cost_per_token": 0.0005,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/baichuan/baichuan-m2-32b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00056,
+        "output_cost_per_token": 0.00056,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/thudm/glm-4.1v-9b-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00028,
+        "output_cost_per_token": 0.001104,
+        "max_input_tokens": 65536,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/baidu/ernie-4.5-vl-424b-a47b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00336,
+        "output_cost_per_token": 0.01,
+        "max_input_tokens": 123000,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/baidu/ernie-4.5-300b-a47b-paddle": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00224,
+        "output_cost_per_token": 0.0088,
+        "max_input_tokens": 123000,
+        "max_output_tokens": 12000,
+        "max_tokens": 12000,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/deepseek/deepseek-prover-v2-671b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0056,
+        "output_cost_per_token": 0.02,
+        "max_input_tokens": 160000,
+        "max_output_tokens": 160000,
+        "max_tokens": 160000,
+        "supports_system_messages": true
+    },
+    "novita/qwen/qwen3-32b-fp8": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0008,
+        "output_cost_per_token": 0.0036,
+        "max_input_tokens": 40960,
+        "max_output_tokens": 20000,
+        "max_tokens": 20000,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-30b-a3b-fp8": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00072,
+        "output_cost_per_token": 0.0036,
+        "max_input_tokens": 40960,
+        "max_output_tokens": 20000,
+        "max_tokens": 20000,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/google/gemma-3-27b-it": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.000952,
+        "output_cost_per_token": 0.0016,
+        "max_input_tokens": 98304,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "supports_vision": true,
+        "supports_system_messages": true
+    },
+    "novita/deepseek/deepseek-v3-turbo": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0032,
+        "output_cost_per_token": 0.0104,
+        "max_input_tokens": 64000,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/deepseek/deepseek-r1-turbo": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0056,
+        "output_cost_per_token": 0.02,
+        "max_input_tokens": 64000,
+        "max_output_tokens": 16000,
+        "max_tokens": 16000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/Sao10K/L3-8B-Stheno-v3.2": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0005,
+        "output_cost_per_token": 0.0005,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/gryphe/mythomax-l2-13b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00072,
+        "output_cost_per_token": 0.00072,
+        "max_input_tokens": 4096,
+        "max_output_tokens": 3200,
+        "max_tokens": 3200,
+        "supports_system_messages": true
+    },
+    "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0039,
+        "output_cost_per_token": 0.0039,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-vl-8b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00064,
+        "output_cost_per_token": 0.004,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/zai-org/glm-4.5-air": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00104,
+        "output_cost_per_token": 0.0068,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 98304,
+        "max_tokens": 98304,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-vl-30b-a3b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0016,
+        "output_cost_per_token": 0.0056,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen3-vl-30b-a3b-thinking": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0016,
+        "output_cost_per_token": 0.008,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/qwen/qwen-mt-plus": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.002,
+        "output_cost_per_token": 0.006,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_system_messages": true
+    },
+    "novita/baidu/ernie-4.5-vl-28b-a3b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00112,
+        "output_cost_per_token": 0.00448,
+        "max_input_tokens": 30000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/baidu/ernie-4.5-21B-a3b": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00056,
+        "output_cost_per_token": 0.00224,
+        "max_input_tokens": 120000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/qwen/qwen3-8b-fp8": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00028,
+        "output_cost_per_token": 0.001104,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 20000,
+        "max_tokens": 20000,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen3-4b-fp8": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00024,
+        "output_cost_per_token": 0.00024,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 20000,
+        "max_tokens": 20000,
+        "supports_system_messages": true,
+        "supports_reasoning": true
+    },
+    "novita/qwen/qwen2.5-7b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00056,
+        "output_cost_per_token": 0.00056,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true,
+        "supports_response_schema": true
+    },
+    "novita/meta-llama/llama-3.2-3b-instruct": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.00024,
+        "output_cost_per_token": 0.0004,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/sao10k/l31-70b-euryale-v2.2": {
+        "litellm_provider": "novita",
+        "mode": "chat",
+        "input_cost_per_token": 0.0148,
+        "output_cost_per_token": 0.0148,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_system_messages": true
+    },
+    "novita/qwen/qwen3-embedding-0.6b": {
+        "litellm_provider": "novita",
+        "mode": "embedding",
+        "input_cost_per_token": 0.00056,
+        "output_cost_per_token": 0,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768
+    },
+    "novita/qwen/qwen3-embedding-8b": {
+        "litellm_provider": "novita",
+        "mode": "embedding",
+        "input_cost_per_token": 0.00056,
+        "output_cost_per_token": 0,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096
+    },
+    "novita/baai/bge-m3": {
+        "litellm_provider": "novita",
+        "mode": "embedding",
+        "input_cost_per_token": 0.0001,
+        "output_cost_per_token": 0.0001,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 96000,
+        "max_tokens": 96000
+    },
+    "novita/qwen/qwen3-reranker-8b": {
+        "litellm_provider": "novita",
+        "mode": "rerank",
+        "input_cost_per_token": 0.0004,
+        "output_cost_per_token": 0.0004,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096
+    },
+    "novita/baai/bge-reranker-v2-m3": {
+        "litellm_provider": "novita",
+        "mode": "rerank",
+        "input_cost_per_token": 0.0001,
+        "output_cost_per_token": 0.0001,
+        "max_input_tokens": 8000,
+        "max_output_tokens": 8000,
+        "max_tokens": 8000
     }
 }

tokencostauto 0.1.441__py3-none-any.whl → 0.1.443__py3-none-any.whl

tokencostauto 0.1.441py3-none-any.whl → 0.1.443py3-none-any.whl